Robotics papers — 2026-09-24

Today's work centers on building a safe multi-robot coordination framework, which is crucial because ensuring robots can operate together reliably in complex environments is the key to real deployment. We explored how vision-language models and large language models can reason about reachability to achieve this, specifically looking at DreamAvoid, which tests policies during the critical phase of training to proactively avoid failures. This testing approach connects directly into developing a scalable framework for decentralized perception-action communication loops, allowing robots to operate without constant central control. We also looked at how to evolve vision-language-action models into agents capable of on-the-fly tool use, which suggests a pathway toward more flexible robot behavior.

A related effort involved accelerating vision-language models post-training using reactive force injection, aiming to make them more robust quickly. Furthermore, we examined FLINT for fast lightweight inference concerning traversability, which is important for real-time decision-making in navigation tasks. Finally, we considered the limitations of flow-matching priors when fine-tuning large behavior models and touched upon intelligence across different embodiments to see how these coordination challenges manifest broadly.

The most crucial piece of work this morning is the development of BEE, which tackles real-world reinforcement learning by incorporating vision and language into action models. This approach matters because it aims to make autonomous systems more robust when facing novel situations outside their training data. BEE involves intervention-adaptive real-world reinforcement learning using vision-language-action models to improve how robots interact with their environment. This means the system learns not just from rewards, but also by observing and responding to interventions in the actual world.

Moving down in significance, InternW0 presents a foundational physical world model designed for efficient real-world interactions between agents. This model is important because it provides a structured understanding of how physical objects behave in space. Next, Kairos focuses on grounded forecasting of presence and directional flow within four-dimensional scene graphs. This work helps systems predict where things will be and how they will move in complex environments.

The research on Automotive mmWave Spinning Radar Place Recognition uses spatially gated feature-correlation representation to improve place recognition for spinning radar systems. This is a specific technical improvement aimed at better localization when using radar technology in automotive settings. Finally, the work on BEE connects these ideas by providing an intervention-adaptive framework that can be grounded by world models like InternW0 and enhanced by language understanding, suggesting a path toward more reliable physical agent behavior.

The work on controlling collectives of AI agents in reasoning space is particularly important because it addresses the growing challenge of managing complex, coordinated artificial intelligence systems. One approach explored was using spatial transformers to control these groups, which essentially means mapping out how different agents should interact based on their location within a conceptual space. This method suggests that by imposing structure on the agent interactions, we can gain better oversight of their collective behavior.

Another significant piece of research focused on distillation for efficient multitask manipulation policies because it aims to make complex AI systems run more smoothly and use less computational power. They tried using conditional flow matching to distill these policies, which is a technique that simplifies a large model into a smaller one while preserving its core functionality for various tasks. This distillation work connects directly to how we might improve the efficiency of the vision-language-action models being developed.

Then there was the development of MemBodied, which introduces recurrent associative memory specifically for vision-language-action models. This system is designed to give these models a kind of short-term memory that helps them maintain context across different visual and linguistic inputs while performing actions. This builds upon the idea of having more robust internal state management within these multimodal systems.

A related concept emerged in where should I join, which uses language-guided goal prediction for robot group joining. This work tackles the problem of how robots can coordinate to form a group based on shared language instructions and predicted outcomes, suggesting a path toward more intuitive social interaction for physical agents.

Finally, the effort on median temporal ensembling presents an important method for training-free robust aggregation of action-chunked visuomotor policies. This technique allows researchers to combine different sets of movement policies without needing extensive retraining, which is crucial when dealing with the diverse datasets mentioned elsewhere in the field.

The most significant advance today involves the work on generalizable robotic insertion, which is crucial because it moves us closer to robots that can perform complex tasks in novel environments without extensive retraining. A study explored this by developing a framework for generalizable robotic insertion using world models, suggesting a method where the robot learns how to insert objects by first building an internal representation of the environment.

This concept builds upon other related efforts; specifically, there was work on forgetmimic which focuses on motion unlearning for humanoid control, aiming to allow robots to forget specific movements they have performed while still learning new ones. This is important because it addresses the safety and adaptability of reinforcement learning systems when deployed in physical settings.

Then there is the research into lifd, which anchors diffusion for 3D-aware scene memory in robotic manipulation; this means creating a robust way for robots to remember what they see in a 3D space so they can manipulate objects accurately. This memory system is key because it allows the robot to maintain context during complex physical interactions.

Another piece of work addresses resilience through resilient motion planning for free-flying space robots under actuator failures, which tackles the problem of ensuring a robot can still navigate safely even when parts of its hardware fail in zero gravity. This addresses reliability in extreme operational conditions.

Finally, there is the work on leap-cbf, which introduces a safety filter for uncertain systems using least-effort adversarial potentials; this technique helps manage risk by creating a buffer against unpredictable outcomes during operation. This filtering mechanism complements the planning and memory systems discussed earlier by adding a layer of real-time safety assurance.

The most significant development today involves the work on HEROIC, which addresses the critical need for open-vocabulary identification and cross-robot collaboration in complex environments. This work tackles how different robots can effectively share knowledge to recognize novel objects or situations they haven't been explicitly trained on, which is vital for real-world deployment.

A related piece of research focused on Co-VLA, which proposes a consensus-based federated training method for vision-language models to improve their performance across diverse datasets. This approach aims to build more robust models by having multiple agents train collaboratively without sharing raw data, making the resulting vision-language actions more generalized.

Then there is SmellDiffusion, which introduces diffusion-based navigation for quadruped robots using olfactory scene graphs to understand their surroundings. This means the robot can navigate based on scent information mapped onto a structured representation of the scene, which is a step toward more intuitive environmental perception.

SkipVLA attempts to speed up robot manipulation tasks by skipping VLA steps and incorporating classical planning techniques, suggesting that this method can achieve faster execution of complex physical actions. This contrasts with DR-MPC, which focuses on fast and feasible dynamics-relaxed model predictive control specifically for legged locomotion, aiming to make walking more efficient.

RoboFind addresses the challenge of personalized object search by creating a multi-agent system designed for people who are blind or have low vision, allowing them to search for specific items effectively. This is distinct from StageGuard, which learns stage transitions for long-horizon robot tasks using agentic distillation to manage complex sequences of actions.

The most significant work today involves the development of a hierarchical hypergraph representation for off-road path and mission planning because it provides a structured way to model complex environmental constraints. This approach attempts to map out relationships between different terrain features and potential paths, which is crucial for autonomous navigation in unstructured settings.

FlipToSee introduced a probabilistic stable placement prior for active visual exploration through regrasping, which means the system learns where it should look next by considering the stability of its grasp while actively exploring its surroundings. This informs how robots can gather necessary information efficiently.

V2-STRep focuses on creating VLM-grounded structured task representations for reusable robot skills that are acquired from generated videos, essentially teaching robots complex actions by looking at examples. This builds upon the planning work by providing the learned behaviors needed to execute those planned paths.

Compliance for Free is learning identifiable impedance through bilateral teleoperation, which means a robot learns how stiff or compliant it should be when interacting with objects by having a human guide it remotely. This physical interaction knowledge is vital for safe contact during navigation.

Bayesian Continuum Robot Dynamics and State Estimation deals with modeling the dynamics and estimating the state of continuum robots using Bayesian methods, which helps predict how these flexible systems will move under uncertainty. This dynamic understanding informs the path planning efforts by providing realistic movement predictions.

The most significant piece of work today involved the development of Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation, which matters because it moves beyond simple visual imitation to create robots that understand the physical effort required during tasks. This research explored how to train robotic systems to handle force and work constraints by regularizing the learning process with energy terms, a method that guides the robot toward physically plausible actions.

A related effort focused on VT-MUSE, which is a multimodal unified sequential visuotactile representation learning system designed for manipulation, aiming to fuse visual and touch data into a single understanding of how to interact with objects. This work builds upon the need for better physical interaction models, as it seeks to capture the nuances of force and tactile feedback in complex tasks.

Another piece involved LEAP, which is a learning emergent active perception system tailored for quadruped navigation, suggesting a way for robots to actively decide what information they need from their surroundings to move effectively. This contrasts with purely reactive systems by introducing an element of intelligent information seeking during locomotion.

Then there was the work on Ordinal Neural Collapse as a representation prior for visual navigation, which investigates how imposing an ordinal structure on neural representations can help guide visual navigation systems by providing a more structured way for the network to interpret spatial data. This is interesting because it tackles how the brain might organize visual information efficiently.

Finally, LapaTrack-3D was presented, which focuses on 6 Degrees of Freedom pre-operative shape tracking for laparoscopic surgery, showing progress in accurately predicting and tracking complex physical shapes during minimally invasive procedures. This work speaks to the practical application of high-fidelity shape understanding in medical robotics.

The most significant development today involves the work on OmniMimic, which successfully augmented motion for multi-style quadruped locomotion by completing dynamics. This means the system learned how to move a robot in various styles by predicting its physical behavior, which is crucial for real-world off-road navigation.

This relates to CoRef-GS, a method that uses cooperative referring Gaussian splatting for understanding scenes across multiple agents. This allows different robots to share and interpret complex environments collaboratively.

DexTouch-WM focused on learning action-conditioned tactile world models directly from human touch, which is a key step toward making robot manipulation more dexterous. This model learns how to interact with the physical world through touch, building a richer understanding of contact dynamics.

Navi-Agent tackled unlocalized monocular navigation by developing an agent that can navigate without explicit localization information. This suggests a new way for robots to move around without needing perfect GPS or map data.

Finally, ULTRA presented a unified multimodal control system for autonomous humanoid whole-body locomotion and manipulation. This work aims to integrate vision and other inputs into a single control scheme for complex human-like actions.

Today's papers

• Safe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis. [paper]
• A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops. [paper]
• DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies. [paper]
• Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection. [paper]
• Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use. [paper]
• FLINT: Fast Lightweight Inference for Traversability. [paper]
• The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models. [paper]
• Intelligence Across Embodiments. [paper]
• Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning. [paper]
• Evolving Inspectable O-RAN Slicing xApps with LLMs. [paper]
• Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation. [paper]
• BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models. [paper]
• Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs. [paper]
• Behaviora - A Conceptual Architecture for External and Internal Behavior of Robots and Agents. [paper]
• InternW0: A Foundational Physical World Model for Efficient Real-World Interactions. [paper]
• InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies. [paper]
• Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching. [paper]
• Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers. [paper]
• MemBodied: Recurrent Associative Memory for Vision-Language-Action Models. [paper]
• Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction. [paper]
• A 3D-Printable Dataset for Fair Testing and Comparisons of Tactile Sensors. [paper]
• Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies. [paper]
• Less Language, More Latents: Annotation-Efficient VLAs for Driving. [paper]
• EvEMTBench: An Open Benchmark for Machine Learning in Power System Protection. [paper]
• Generalizable Robotic Insertion with World Models. [paper]
• Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3. [paper]
• LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials. [paper]
• ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control. [paper]
• LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation. [paper]
• Underwater Visual Target Tracking with Target-Specific Depth Estimation and Adaptive Model-Fusion Predictive Control. [paper]
• Resilient Motion Planning for Free-Flying Space Robots under Actuator Failures. [paper]
• RotateIt! Fast and Reliable Single-Arm Garment Unfolding via Online-Adaptive Dynamic Rotation. [paper]
• Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models. [paper]
• SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs. [paper]
• HEROIC: Heterogeneous Evidential Reasoning for Open-Vocabulary Identification and Cross-Robot Collaboration. [paper]
• SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation. [paper]
• How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation. [paper]
• DR-MPC: Fast and Feasible Dynamics-Relaxed Model-Predictive Control for Legged Locomotion. [paper]
• RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision. [paper]
• StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation. [paper]
• HOPHY: A Hierarchical Hypergraph Representation for Off-Road Path and Mission Planning. [paper]
• Time-Efficient Iterative Learning Planning for Safety-Critical Dynamic Obstacle Avoidance. [paper]
• FlipToSee: A Probabilistic Stable Placement Prior for Active Visual Exploration via Regrasping. [paper]
• Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation. [paper]
• Bayesian Continuum Robot Dynamics and State Estimation. [paper]
• V2-STRep: VLM-Grounded Structured Task Representations for Reusable Robot Skills Acquired from Generated Videos. [paper]
• VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control. [paper]
• Safe learning-based control via function-based uncertainty quantification. [paper]
• Experimental Design for Controller Selection in Synthetic Biology. [paper]
• DefVINS: Visual-Inertial Odometry for Deformable Scenes. [paper]
• LEAP: Learning Emergent Active Perception for Quadruped Navigation. [paper]
• Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation. [paper]
• Ordinal Neural Collapse as a Representation Prior for Visual Navigation. [paper]
• 4D Radar Perception Algorithms for Autonomous Driving: A Review. [paper]
• VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation. [paper]
• LapaTrack-3D: 6 DoF pre-operative shape tracking for laparoscopic surgery. [paper]
• Feeling Terrain Before Crossing: World Models for Off-Road Navigation. [paper]
• Learning Foresight without Explicit Trajectories for 3D Diffusion Policies. [paper]
• INSPECT: Learning Robot View Selection from Assistant Use. [paper]
• CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding. [paper]

The papers

• Nonlinear-Gain Distributed Zeroth-Order Optimization for Networked Black-Box Control — This letter studies distributed stochastic optimization over a peer-to-peer network when agents can query only zeroth-order function values, proposing ZOOM-PB, a coordinate-sampling method that blends each local ZO estimate with a fractional-power response while maintaining only [episode]
• Composite Adaptive Higher-Order Control Barrier Functions for Joint Frequency-RoCoF Safety in Low-Inertia SIDS Microgrids —
• Hardware-Free Robotics Laboratories in Mixed Reality —
• H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space —
• Tilt as a Certified Resource: Preserving Motor Wrench-Rate Authority on Articulated Multirotors —
• Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3 —
• Safe learning-based control via function-based uncertainty quantification —
• Formation Keeping Control for Deorbiting an Uncooperative Satellite by Laser Ablation —
• Search, Ground, Plan: Functional Sufficiency for Task and Motion Planning under Incomplete Scene Knowledge —
• Incentive Design for Multi-Agent Systems: A Bilevel Optimization Framework for Coordinating Independent Agents and Convergence Analysis —
• Stochastic Data-driven Predictive Control of Linear Systems with Sub-Gaussian Disturbances using Causal Predictors —
• Human-Centricity in Industry 5.0: A Survey of Worker Sensing, Adaptive Operations, and Human-in-the-Loop Systems —
• Nonlinear Dynamic Modeling and Receding-Horizon NMPC of an Electric Unicycle on a Tensioned Cable —
• Hardware-in-the-Loop Evaluation of Game-Theoretic Autonomous Driving —
• Recursive Parameter Identification of Nonlinear Stochastic State-Space Models via Sequentialized Ensemble Kalman Inversion —
• NaviScale: Generating Large-Scale Semantic Map Datasets for Object Navigation —
• Anchor-Free Hidden-Target Seeking via Certified Self-Calibration under Correlated Odometry —
• Assessment of the N-1 voltage security of a future Nordic energy system —
• Smoothness as a Constraint for Stable Humanoid Locomotion —
• WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors —
• Causal-History Test-Time Scaling for Failure Recovery in Autoregressive World-Action Models —
• Distribution-Free Budgeted Stealthy Attack Scheduling for Remote State Estimation —
• Vision-Language Models as copilots for Autonomous UAV Navigation: Analysis of Latency and Reliability in Degraded Environments —
• ME-Brain-1.0: Memory, Cognition and Action for Evolving Embodied Intelligence —
• RoboFolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects —
• SeeQ: Training Generalist Value Functions for Long-Horizon Robotic Manipulation —
• Compact but Moving: Intervention-Relevant Geometry in Recurrent World Models —
• Switchable-Polarity Electropermanent Magnet: Reconfigurable Magnetic Fields for Scalable Fluidic Control —
• Predict Before You Step: Auditable Occupancy Forecasting for Dynamic Obstacle Avoidance under Sparse Guidance —
• MetaPusher: Meta Learning and Planning for Nonprehensile Manipulation of Unseen Objects with Rapid Online Adaption —
• What is the Better Curriculum: Controller-Shaped Grasping Behavior for Contact Force-Sensitive Manipulation —
• SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration —
• PIVOT: Physically Informed Vision-Language Off-Road Traversability for Field Robot Navigation —
• What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior —
• DefVINS: Visual-Inertial Odometry for Deformable Scenes —
• HiRE: Hindsight Reward Editing for Policy Finetuning —
• Beyond the Flat Seafloor: A Closed-Form Two-View Constraint to Aid Sidescan Sonar Reconstruction —
• Experimental Design for Controller Selection in Synthetic Biology —
• Designing Grid-Aware Dynamic Specifications for Large Data Center Loads —
• Agents in the Scene: An Agentic Framework for Resource-Efficient Site-Specific Base Station Deployment —
• Remote Surfaces at Your Fingertips: Electrovibration-Based Tactile Feedback for Robot Teleoperation via Touchscreen Interfaces —
• Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations —
• GLASS: Architecture-Tuned, Composable, Device-Side Linear Algebra for Edge Robotics and Beyond —
• Realizations of Linear Systems with Prescribed Sparsity Patterns —
• HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing —
• SPROUT: The Open-Source Soft Growing Robot for Search and Rescue —
• OpenFlyScan: A Quality-Guided Aerial Reconstruction System for Consumer Drones —
• Sparse One-Step-Ahead Optimal Control of Time-Varying Affine Opinion Networks: Tracking and Competitive Games —
• Equivalent-Agent Guidance for Cooperative UAV Payload Transportation —
• V2-STRep: VLM-Grounded Structured Task Representations for Reusable Robot Skills Acquired from Generated Videos —
• VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation —
• A Duality Reformulation of the Companion-Matrix Lyapunov Problem —
• Optimization Design and Simulation Validation of a Variable Stiffness Actuator Based on a Crossed Four-Bar Mechanism —
• A Stochastic Mean-CVaR Framework for BESS Multi-Market Bidding Strategies —
• Sliding Mode Control of Cardiac Rhythms in the Sinoatrial Node using Gaussian Process Regression —
• Predicting Viral Evolution from a Single Early Measurement Using the Target Cell Limited Model —
• Hybrid Sequential Feedback Optimization for Wind Farm Power Maximization —
• Chance-Constrained Nonlinear Covariance Control via Robust Linearization Remainder Bounds —
• X2Real: an eXtensive simulation benchmark for real-world generalist policies —
• FLINT: Fast Lightweight Inference for Traversability —
• Observability and parameter estimation of a generic model for aggregated distributed energy resources —
• Noninvasive Anisotropic Identification of Magnetic Properties in Toroidal Shaped Magnetic Steel —
• Equivalent Modeling of Load-Side Systems With Distributed Renewable Generation Considering Fault Responses and Nodal Voltage Coherence —
• Almost Sure Convergence of Networked Policy Gradient over Time-Varying Networks in Markov Potential Games —
• On unified asymmetric barrier Lyapunov functions —
• Leader-Follower Formation Control with Prescribed Convergence Rates under Bearing Persistence of Excitation —
• Towards Intent-Aware Human-Robot Teaming: A Platform for Search-and-Rescue Operations —
• Robust Active-Perception Control for Global-State-Free Aerial-Ground Cooperation —
• FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving —
• Probabilistic Scene Graphs: Hierarchical Representation and Real-time System —
• A Duality-Based Optimization Formulation of Safe Control Design with State Uncertainties —
• Model Predictive Control with Multiple Constraint Horizons —
• Learning State-Action Control Barrier Functions for Model-Free Control under Constraints —
• Fast Direction-Conditioned Reachability for Motion Prediction Under Model Uncertainty —
• Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning —
• Structured World-State Reasoning for Agentic Robotic Search —
• WAVE-Go: World-Model Navigation with Adaptive Execution for Wheel-Legged Robots —
• ReRadar: Robust Radar Global Localization via Rotation-Equivariant Descriptor Learning —
• Remote Human-Robot Interaction In Greenhouses via Virtual Reality: How Plant Canopy Structure Affects Leaf Disease and Soil Moisture Inspection —
• Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal Localization —
• GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains —
• SCRAMPPI: Contingency-Constrained Planning using Hamilton-Jacobi Reachability —
• AthenaZero: A low-inertia, bimanual robot for dynamic manipulation —
• Towards Interaction Regulation from Human Feedback via Free Energy Minimization —
• LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot Manipulation —
• MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligence —
• StenoVLA-3D: 3D-Aware Reasoning VLA for Navigation Through Gastrointestinal Stenoses —
• Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems —
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation —
• Characterizing Wildlife Response to Biomimetic and Conventional Underwater Vehicles —
• REDACT: Robust Perceptive Locomotion under Unseen Visual Corruption —
• Market-Driven Equilibria for Distributed Photovoltaic Panel Investment —
• Action-Directed Information for Distributed Control and Agentic Interaction —
• FastLoop: Parallel Loop Closing with GPU-Acceleration in Visual SLAM —
• Network Risk Estimation: A Risk Estimation Paradigm for Cyber Networks —
• Robust Macroscopic Density Control of Heterogeneous Multi-Agent Systems —
• Understanding Engagement and Intrusiveness in Assistive Human-Robot Interaction Using Individual Traits —
• Contact-Rich Motion Planning via GPU-Parallel Mode Evaluation —
• ZeroTouch: Tactile-Supervised Visual Contact Estimation for Contact-Rich Manipulation —
• AgenticSwarm: Semantic Perception and Adaptive Task Allocation for Heterogeneous Multi-UAV Missions —
• MAAP: Multi-Agent Active Perception for Collaborative Manipulation —
• Situation Aware Locomotion for Dual Mobile Cobots in Shared Environments —
• Boreas Road Trip: A Multi-Sensor Autonomous Driving Dataset on Challenging Roads —
• JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation —
• I-Perceive: A Foundation Model for Vision-Language Active Perception —
• React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies —
• AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison —
• Simultaneous Forward and Inverse Human-in-the-Loop Optimization —
• The EventCV Library for Event-Based Robotic Vision —
• HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness —
• Same World, Different Knowledge: When Isolated Audits Misjudge World-Model Repairs —
• Design of Adaptive PID Controller Based On Asynchronous Advantage Actor Critic Learning Method for QuadCopter Control —
• MicroHookACT: Monocular Microscopic Vision Guided Visuomotor Policy for Flexible Microelectrode Hooking —
• TRACE: Coverage Path Planning for Unknown Environments Using Hierarchical Coverage Tree —
• OmniPlanner: Universal Exploration and Inspection Path Planning Across Robot Morphologies —
• Fast and Robust Temporal Logic Planning via ADMM-based Trajectory Optimization —
• "Dear LLaVA, Please Drive": A Depth-Aware Vision-Language Agent for Closed-Loop Robotic Control —
• Distributed ISAC-Enabled Multimodal Recovery of Missing 2-D LiDAR Measurements —
• Task aware Dynamic Movement Primitives for failure detection and recovery in contact rich manipulation —
• AquaCap: A Training-Free Underwater Embodied Agent with Code-as-Policy —
• Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer —
• Analysis and Design of Desaturation Short-Circuit Protection for SiC MOSFET Under High Switching Voltage Transients —
• Splat-CBF: Safe Next-Best-View Control in 3D Gaussian-Splat Maps —
• VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation —
• Safe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis —
• A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops —
• Constrained Optimization-Based Yaw-Rate Reference Map Generation for Active Rear Steering Control of Four-Wheel Steering Vehicles —
• Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use —
• MemBodied: Recurrent Associative Memory for Vision-Language-Action Models —
• A 3D-Printable Dataset for Fair Testing and Comparisons of Tactile Sensors —
• Embodied Snap: Octopus-Inspired Distributed Reach-and-Attach with a Speed-Limited Soft Arm —
• StrataVLA: Hierarchical and Efficient 3D Geometric Grounding for Vision-Language-Action Models —
• Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies —
• Layered e-skin for Shear Sensing —
• Internal-Model-Control-Based Virtual Admittance Emulation for Enhanced Grid-Forming Performance —
• Do Spinning Radar Doppler Velocity Measurements Improve Vehicle Detection and Tracking? —
• CORL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles —
• Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulation —
• Dynamics-Induced Commitment in Learning-Based Robotic Penalty Kicks —
• Project SCOUT: Interceptor Drone for Perimeter Defense —
• Vision-based Underwater Formation Control With Input Saturations via Barrier Lyapunov Functions —
• PASSAGE: Scaling Scene-Aligned Motion Learning for Perceptive Humanoid Traversal in Cluttered Environments —
• PileBelief: Persistent Physical State for Interaction-Driven World Modeling —
• ForceRFT: Refining VLA Actions through Force-Guided Residual Reinforcement Learning —
• NavDreamer: Video Models as Zero-Shot 3D Navigators —
• ERUPT: An Open Toolkit for Interfacing with Robot Motion Planners in Extended Reality —
• Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching —
• Iterative Single-Loop Coordination of Transmission and Distribution Systems and DER Aggregators with Limited Information Sharing —
• Visibility-Aware Mobile Grasping in Dynamic Environments —
• A Reconfigurable Dual-Opposition Architecture for Single-Hand Assembly and Manipulation —
• VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies —
• Two-Timescale Asymptotic Simulations of Hybrid Inclusions with Applications to Stochastic Hybrid Optimization —
• DITTO: Dexterous Interface for Transparent TeleOperation —
• NeuRIO: A Streaming Neural Estimator for Zero-Shot Sim-to-Real Multi-Robot Relative Inertial Odometry —
• Multisource human-in-the-loop digital twin testbed for connected and autonomous vehicles in mixed traffic flow —
• LEMCA: LLM-Guided Synthesis of Efficient Mode-Switching Control Architectures —
• LOInK: Learned Optimal Inverse Kinematics via Structured Neural Surrogate Models —
• Distributed Infrastructure Sensors and Cues for Robotic Fire-Fighting and Safety System on a Lunar Base —
• Anti-Gravity Walking by a Flying Humanoid Robot via Thrust-Rate Input Whole-Body Model Predictive Control —
• Duty Factor Predicts Robust Constrained Quadrupedal Locomotion Across Gait Types —
• Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies —
• PAMoR: Parameterized Affective Motion Generation in Real Time for Humanoid Robots —
• BEACON: Belief-Enabled Adaptive CONtrol for Imitation Learning under Uncertainty —
• OJOx: Specification-Conditioned Demonstrations for Embodied AI in Construction —
• DeViGrasp: Robust Visual Mobile Grasping for Quadruped Manipulators under Degraded Perception —
• Noctif3R: Feed-Forward Monocular Real-Time SLAM for Photon-Limited Scenes on Embedded Hardware —
• Verti-WM: A Physics-Aided Exteroceptive World Model for Off-Road Reinforcement Learning —
• Decentralized Multi-Robot Exploration with Probabilistic Peer Intent and Multi-hop Plan Propagation —
• Certificates Synthesis for A Class of Observational Properties in Stochastic Systems: A Unified Approach —
• A High-Payload Wall-Climbing Robot Using Passive Bistable Suction Cups —
• CRISP: Contact-Rich Robotic Simulation Platform with Extensive Geometries and Contact Solvers —
• Route-MHT: Multimodal Transformer Guardrails for Thermal Visual Place Recognition —
• Shake to Learn: Dynamic Interrogation of Hidden Object Physics for Robotic Manipulation with Physical Reservoir Computing —
• MIRA-PRM: Mission-Informed Reusable Roadmap Planning for Mobile Gas-Sensing Inspection —
• AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance —
• Gripper-Aware Automatic Dense Packing of Irregular Objects —
• Skel-WAM: A Hand-Skeleton-Conditioned World Action Model for Human-to-Robot Manipulation Transfer —
• Sandwich-Residuals: Parameter-Efficient Test-time Adaptation of World Models —
• Learning Distance-Conditioned Object Transport for Humanoid Loco-Manipulation from a Single Motion Clip —
• Model-Free Control for Residential Heating: Deployment and Simulation of Nonlinear Data-Enabled Predictive Control —
• A Gesture-Based Visual Learning Model for Acoustophoretic Interactions using a Swarm of AcoustoBots —
• Accelerating Optimization over Graphs of Convex Sets via Neural Network Approximations —
• Improved Droop Control in DC Microgrids via Voltage-Locked Loop Synchronization —
• CounterPlay: Counterfactual Post-Training for Self-Play Driving Policies —
• On a Closed-Loop Controller for the Coevolutionary Model of Actions and Opinions via Broadcasting Information —
• Safe Real-Time Policy Steering via Noise-Space Trajectory Optimization for One-Step Generative Policies —
• When Should Robots Intervene? Balancing Engagement and Intrusiveness in Human-Robot Interaction —
• A Novel Path-Tracking Algorithm for Automated Tractor-Trailer Forward and Backward Maneuvers —
• Firing Rate Neural Network Implementations of Model Predictive Control —
• Variable-Resolution Virtual Maps for Autonomous Exploration with Unmanned Surface Vehicles (USVs) —
• EditWM: Event-Decomposed World Modeling with Incremental Correction for End-to-End Autonomous Driving —
• CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution —
• High-Bandwidth Biomimetic Finger for Tactile-Transparent Remote Texture Sensing —
• Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations —
• An Empirical Study and Open Testbed for Federated Fine-Tuning of Vision-Language-Action Models —
• Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement —
• A Direct Rigid Transmission 2-DoF Wrist Extension for Tendon-Driven Hand —
• AquaWorld: Structure-Consistent Underwater World Generation for Robot Simulation —
• OpenRoIS: A Community-Driven Open-Source Middleware Implementing the Robotic Interaction Service (RoIS) Framework for Physical Robots and Virtual Agents —
• Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction —
• Learning-Based Augmentation and Adaptation for Grid Sim-to-Real Model Discrepancy —
• GDLAM: Group-Disentangled Latent Action Model for Highly Disentangled Embodied Pretraining —
• On sparsity and directional forgetting in adaptive control —
• LIMBO: Learning and Internalizing Model-Free Barrier Objectives for Agile and Safe Whole-Body Control —
• Robotic Multiphase Interaction: Manipulating Coupled Liquid and Solid Dynamics with a World Model —
• A Unified Dynamic Force Guidance Framework for Performance-Optimized Kinesthetic Teaching —
• FAN: Foresight Action Normalization for Continual Adaptation of Vision-Language-Action Models —
• Rate-cost Trade-offs in H-infinity Control with Initial State Uncertainty —
• A Distributed Step-by-step Finite-time Consensus Design for Heterogeneous Battery Energy Storage Devices with Droop Control —
• Expressive Power of WSTL Formulas for Learning to Rank —
• Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models —
• SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation —
• HOPHY: A Hierarchical Hypergraph Representation for Off-Road Path and Mission Planning —
• Time-Efficient Iterative Learning Planning for Safety-Critical Dynamic Obstacle Avoidance —
• FlipToSee: A Probabilistic Stable Placement Prior for Active Visual Exploration via Regrasping —
• Bayesian Continuum Robot Dynamics and State Estimation —
• VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control —
• UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents —
• InterMASH: A Unified Geometric Representation for Grasp Synthesis —
• Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation —
• Implementation of Tightly-Coupled SLAM Fusion of GPS, IMU, and LiDAR for Autonomous Vehicles —
• Stabilizing Fast Dynamical Systems Using Time-of-Flight Cameras —
• Energy-based Regularization for Learning Residual Dynamics in Neural MPC for Omnidirectional Aerial Robots —
• A Quantitative Framework for Navigating Controller Design Tradeoffs under Computational Constraints —
• Performance Guarantees for Data-Driven Sequential Decision-Making —
• Orchestrating Wheeled Mobile Robots Online without Conflicts —
• Observing and Controlling Features in Vision-Language-Action Models —
• Vision-Based Robotic Disassembly Combined with Real-Time MFA Data Acquisition —
• CoAd: Constant-Time Planning for Continuous Goal Manipulation with Compressed Library and Online Adaptation —
• Robotic Tele-Operation for Upper Aerodigestive Tract Microsurgery: System Design and Validation —
• Highly-Efficient Differentiable Simulation for Robotics —
• Fast Risk Certification of Candidate Trajectories under Uncertain Time-Varying Constraints —
• TactileReflex: Noise-Statistics-Driven Vision-Tactile Reflex Control for Force-Sensitive Manipulation —
• Allometric Scaling Laws for Bipedal Robots —
• A Deployment Study of Identity-Gated Drone Gesture Control —
• Real-World Reinforcement Learning with MPC Scaffolding for Dexterous Manipulation —
• Behaviora - A Conceptual Architecture for External and Internal Behavior of Robots and Agents —
• INSPECT: Learning Robot View Selection from Assistant Use —
• WM-VS: Progress-Aligned World Models for Closed-Loop Visual Servoing —
• PROBE-X: Learning-Free Cross-FOV Place Recognition —
• DistAL: Distance-based Advantage Learning for VLA Fine-Tuning —
• OHRID-Retail: An Open Multimodal Dataset of Human Activity in Retail Environments —
• Safety-Critical Scenarios Emerge from Initial Scenes —
• AnyViewDex: View-Invariant Dexterous Manipulation from RGB Observations —
• Equivariant Filter Design for Acoustic and Depth Aided Inertial Navigation Systems —
• ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning —
• Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations —
• Visual Sim-to-Real Learning for Robotic Insertion under Geometric Variations: Application to Rebar Installation —
• Towards High-DoF Dexterous Manipulation through VLA Post-Training —
• OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots —
• PathCover: A Fast Convex Decomposition along a Path via Randomized Iterative Space Partitioning (RISP) on Point Clouds —
• More than a Manipulator: Planning Propellant-Free Attitude Maneuvers for Free-Floating Spacecraft —
• Colosseum V2: Benchmarking Generalization for Vision-Language-Action Models —
• Generalizable Optimal Control with Transformers: One Policy Across Diverse Systems —
• Unified Learning of Temporal Task Structure and Action Timing for Bimanual Robot Manipulation —
• Hybrid Imitation Learning: Teleoperation Augmentation Primitives that Policies Learn to Trigger —
• BiRoAD: Learning Shared and Role-Adaptive Representations for Bimanual Manipulation —
• EmoPose: Vision-Language Model Guided Emotion-Aware Gesture Generation for Humanoid Robots —
• Behavior Trees for Robotic Systems: An Empirical Study on Practices and Experiences —
• When to Waddle: A Comparative Study of Bipedal Torso-Stabilization on Low-Friction Surfaces —
• Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation —
• Stochastic Barrier Certificates in the Presence of Dynamic Obstacles —
• 3PoinTr: From Human Videos to Robot Policies with 3D Point-Track Plans —
• Density-Driven Area Coverage for Nonholonomic Multi-Robot Systems with Safety Guarantee —
• REBOOT: From Failure to Recovery - A Dataset and Benchmark for Precision Assembly —
• Tracker-Free Robotic Ultrasound Calibration with a Spherical-Marker Phantom and Threshold-Free Center Localization —
• Embedding Physics Priors in Robot Learning: A Survey —
• CHOREO: Every Humanoid Skill as a Trajectory —
• GraphPoint: Semantic Entity Graphs and Point Trajectories for Compositional Robot Manipulation —
• OmniRisk: Omnidirectional Trajectory-Risk Learning for Agile Quadrotor Dynamic Avoidance —
• A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series —
• CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation —
• AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation —
• Elevator-VIGS: Separating Elevator Motion from Robot Motion in Visual-Inertial Gaussian Splatting SLAM —
• RopeFormer: Cross-Trial Adaptation from Interaction History for Dynamic Rope Manipulation —
• HEARTH: An Object-Centric RGB-Thermal-3D Dataset for Temperature-Aware Robot Manipulation —
• Shared Execution-Clock Drifting Policy for Dynamic Precision Manipulation —
• Steering Through Contact: A Finite-Support Motion Model for Single-Track Center-Articulated Robots —
• Scenario MPC with STL Specifications and Pareto-Based Feasibility Repair —
• Anticipatory Robot Goalkeeping via Monotone Optimal Stopping —
• MR-SPITE: Accelerating Multi-Robot Conflict Scans via Hierarchical Swept-Volume Approximations —
• BarrierFormer: Transformer-Guided Predictive Barrier Enforcement for Safe Robot Control —
• Physical-Touch Observability from Wrist Wrench in Granular Scooping —
• Expert-Play Contouring Control: Faster-than-Demonstration Planning from Slow Expert and Fast Play —
• Rapidly-Iterating Grid-Based Near-Optimal Kinodynamic Motion Planning —
• GraspTune: Tactile-Driven Execution Refinement for Robust Grasping —
• Steering Multirobot Behavior via Closed-Loop Affine Activation Editing —
• Cosserat Modeling of Trimmed Helicoid Soft Arms with a Separated-Section Constitutive Law —
• Laser-Tracker-Assisted Camera-to-Robot Calibration for Mobile Robots —
• An Open Panoramic Aerial Robot: Airframe-Integrated Multi-Fisheye Sensing, Onboard ERP Formation, and Field Evaluation —
• Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study —
• Towards Adaptive Interaction Strategies for Human Companion Robot via Deep Reinforcement Learning —
• Prescribed-Time Contracting-Boundary Control of a Tendon-Driven Flexible Arm —
• Forgetting While Remembering, an Invariant Online Data-Driven Predictive Control Formulation —
• Source--Grid Coupling in Power System Oscillations: Observational Equivalence, Feedback Detectability, and Modal Interaction —
• Data-Driven Compositional Safety Verification of Interconnected Monotone Systems —
• A Recursive CBF Framework for Safety under State Uncertainty —
• Reliability Assessment and Performance Enhancement of Reset Control Systems —
• A Physics Informed Learning Augmented Framework for Grid-Aware P2P Energy Trading —
• Hyperlyve: Hyperplane Partitioning for Neural Lyapunov Verification —
• Grid-Supporting Equipment Supply Chains Constrain the Feasible Pace of Power System Expansion —
• An Evolutionary Algorithm for Actuator-Sensor-Communication Co-Design in Distributed Control —
• When Persistency is not Exciting in Data-Driven Predictive Control —
• Explicit Second-Order Bounds on the Domain of Validity for Lyapunov-Schmidt Reduction —
• Physics-Informed Neural Network Surrogates with Polynomial Chaos-Based Uncertainty Propagation for Stochastic Model Predictive Control —
• AgentHomeID - Agent-based modelling of building stock transformation: A multi-scale framework for policy assessment and infrastructure planning —
• Engagement-Aware Agentic Pursuit-Evasion —
• Scalable Supervisory HVAC Control for Linear Objectives —
• Optimal Allocation of Grid-Forming Frequency Shaping Control —
• Paying for Space: Incentive-Aware Motion Planning for Multi-Agent Collision Avoidance —
• Generalizable Optimal Control with Transformers: Closed-Loop Certification and Near-Optimality Guarantees —
• Impact of RTK Augmentation and INS Integration on GNSS Positioning Accuracy and Continuity: A Benchmarking Study on Inland Waterways —
• Distributed Multiconsensus Control of BESSs Based on Centrality of Eigenvectors —
• Optimal Operation Method for Computing Power-Electric Power Coordination Considering End-to-End Completion Latency of Computing Tasks —
• Risk-Averse Lander Site Selection under Altitude-Limited Information —
• Learning Safe-by-Design Neural Network Controllers —
• Failure-Aware Iterative Learning of State-Control Invariant Sets —
• Distributed Cooperative Control with Prescribed Performance of BESSs with A Unified Discharge Constrain for Power Allocation under Dynamic Load —
• On the Observability and Redundancy of Intelligent Transportation Networks —
• Optimization of Fault-Tolerant Thruster Configurations for Satellite Control —
• Holonic Graceful Transitions Across Centralized, Decentralized, Distributed, and Local Control in DER-rich Cyber-Power Distribution System —
• Merging Large Language Models and Battery Physics for User-Aware Electric Vehicle Driving Management —
• Robust Strictly Positive Real Synthesis for Sixth-Order Interval Polynomial Families —
• Enhanced ShockBurst for Ultra Low-Power On-Demand Sensing —
• Stochastic MPC under Heavy-Tailed Disturbances: An Extreme Value Theory Approach —
• SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation —
• Fine Wrist Control as a Marker of Surgical Teleoperation Expertise —
• SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation —
• CDKF-Track: Cluster-aware Data-Driven Kalman Filtering for Cooperative 3D Multi-Object Tracking —
• Contact-Stable Deformable Tissue Simulation Using Implicit Integration and Live-Pose Grasp Constraints for Laparoscopic Surgery Robot Policy Evaluation —
• EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation —
• Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation —
• Higher-Order Approximation of Exit Functionals in Sampling-Based Stochastic Model Predictive Control —
• Multimodal Voice Activity Projection for Social Robot Mediation: Expected Behavior and Deployment Constraints —
• Automatic Labelling for Bimanual Mobile Manipulation —
• Dissecting Advantage-Guided Post-Training for Vision-Language-Action Policies —
• BladeMaster: Real-Time Robotic Cutting Simulation with Online-Generated Persistent Discontinuities —
• CAST: Collision-Aware Assembly with Construction Robots using Simultaneous Trajectory Estimation and Planning —
• A Topological Representation with Object-Path Graphs for Open-Vocabulary Instance Navigation —
• Partial-Scan-and-Move Source Seeking for Mobile Robots —
• Stability-aware Residual Reinforcement Learning Framework for Robotic Manipulator Disturbance Compensation —
• Active perception for robotic harvesting: 3D reconstruction and localisation of tomatoes hidden within clusters in a Mediterranean greenhouse —
• Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning —
• Less Language, More Latents: Annotation-Efficient VLAs for Driving —
• NanoBench: A Multi-Task Benchmark Dataset for Nano-Quadrotor System Identification, Control, and State Estimation —
• AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation —
• TRACER: Adaptive Multi-Robot Social Navigation via Joint Human-Response Prediction and Interaction-Aware Replanning —
• Toward 3D Printable Non-Planar Electroadhesive Structures for Active Anchoring —
• From Gameplay to Policy: Towards Scalable Robot Data Collection via Gamified Robot-Free Interaction —
• DetAug: Obstacle-Blind Trajectory Augmentation for Zero-shot Obstacle Avoidance —
• Indicators of resilience for autonomous control systems —
• TacBPM: A Tactile-conditioned Behavior Prior Model for Dexterous Reorientation —
• CLASP: A Cluster-Level Autonomous Selective Picking Robot with a Soft Rolling-Band Gripper for Fresh-Market Blueberry Harvesting —
• RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous Driving —
• Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning —
• VLEM: Real-Time 3D Vision-Language Embedding Mapping —
• UMI-Bridge: Action-Anchored Latent Alignment across Human and Robot Manipulation Data —
• DynoFluxBench: Benchmarking Kinodynamic Space-Time Planners in Dynamic Environments —
• Characterizing Refraction-Induced Ranging Bias in Underwater Collaborative Localization —
• Online Multimodal Workload Assessment in Contact-Rich Physical Human-Robot Interaction —
• VCTP: Vehicle-Conditioned Terrain Planning for Off-Road Navigation —
• Vision-Language Grounded Task-Context-Aware Imitation Learning for Robotic Disassembly —
• Human-Centric Grasp State Assessment: Toward Transferring Subjective Evaluation to Robots —
• CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning —
• Primitive-Informed Sampling-Based MPC for Multi-Fingered Dexterous Manipulation —
• Finite-Time Curvature-Constrained Vector Field for Saturation-Free Motion Planning of Nonholonomic Robots —
• Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization —
• AERO-VIS: Asynchronous Event-based Real-time Onboard Visual-Inertial SLAM —
• Real-Time Maneuver Planning for Fixed-Wing UAVs in Unsteady Flows Using a GPU-Accelerated Vortex Particle Model —
• An Environment-Adaptive Position/Force Control Based on Physical Property Estimation —
• A Foldable and Agile Soft Electromagnetic Robot for Multimodal Navigation in Confined and Unstructured Environments —
• Kinematic Interface for the Wild: Modular Bimanual Loco-Manipulation Capture from 360 Cameras Alone —
• Stabilizing Trajectory Outputs in End-to-End Autonomous Driving via SC-IMM Based Teacher Signals —
• Interconnections of Dissipative Networks Through a Dynamic Scattering Controller —
• VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoing —
• HINT-Blimp: Human INTent Inference from Multimodal Cues for Robotic Blimps —
• Planning Trajectories that Bounce: Reflection Classes for Collision-Tolerant Robots —
• Design and Modeling of a Single-Port Three-Arm Robotic Tool for Minimally Invasive Neurosurgery —
• Vision-Based Control of a Tether-Suspended Aerial Radiation Sensing Payload —
• Memory That Changes Action Is Not Memory That Guides It: Counterfactual Auditing of History-Conditioned Robot Policies —
• A Quasi-Direct-Drive Underactuated Asymmetric Hand for Dexterous and Efficient Grasping and Manipulation —
• RoboCaf'e in the Open: Interaction Continuity in Long-Term Public Human-Robot Interaction —
• CoPRE: Improving Sensitivity in Proprioceptive Contact Detection for Low-Cost Robot Arms —
• BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction —
• Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization —
• Spatial and Semantic Reasoning for LLM-Driven Robot Navigation via MCP —
• A Sample-Based Approach for Hierarchical Information-Theoretic Compression of Probabilistic Occupancy Grids —
• Watch, Recall, Act: Always-On Robots in Concurrent Embodied Streams —
• Amplify: A Lightweight Library for Reproducible Nonlinear Programming Problems in Robotics —
• TANDEM: Task and Motion Planning with As-Needed Demonstrations for Efficient Vision-Language-Action Model Fine-tuning —
• Large-Scale Geometric Map-Based Localization of UAVs in GNSS-Denied Urban Environments —
• Contact-Implicit Stein Projected ADMM for Discovery of Diverse Contact-Rich Manipulation Strategies —
• Talk2Escape: Conversational Grounding for Vision-and-Language Navigation —
• Dynamic, Decentralized Spatial Code Reuse for OCDMA LiDAR in Robot Swarms —
• BrickCraft-Duo: Efficient Dual-Arm Skill Learning and Refinement for Compositional Long-Horizon Assembly —
• Learning Control Policies from Heterogeneous Multi-Horizon Time Series in Battery Energy Management Systems —
• Complementary Filtering on SO(3) for Attitude Estimation with Scalar Measurements —
• Probably Approximately Correct Guarantees for Data-Driven Reachability Analysis: A Theoretical and Empirical Comparison —
• Backup-Based Safety Filters: A Comparative Review of Backup CBF, Model Predictive Shielding, and gatekeeper —
• SHAFT: A Slack-Compensating, Helical-Buckling-Attenuating Flexible-Shaft Transmission for Lightweight Multi-DoF Manipulation —
• Lend me an Ear: Speech Enhancement Using a Robotic Arm with a Microphone Array —
• Learning, fast and slow: a two-fold data-based model adaptation algorithm for processes under varying operating conditions —
• J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively in Inverse Kinematic Control of Serial Manipulators —
• Correct-by-Construction Vision-based Pose Estimation using Geometric Generative Models —
• HiBerNAC: Hierarchical Brain-inspired Robotic Neural Agent Collective for Disentangling Complex Manipulation —
• Programmable Telescopic Soft Pneumatic Actuators for Deployable and Shape Morphing Soft Robots —
• Wildfire Risk Metric Impact on Public Safety Power Shut-off Cost Savings —
• First Experimental Demonstration of Natural Hovering Extremum Seeking: A New Paradigm in Flapping Flight Physics —
• When Digital Twins Meet Large Language Models: Realistic, Interactive, and Editable Simulation for Autonomous Driving —
• End2Race: An End-to-End Learning Framework for Multi-Vehicle Autonomous Racing —
• Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning —
• MarineCraft: Enabling Rapid Prototyping of Underwater Robots via Modular Construction —
• Feedback-Modulated Harmonic Policies for Quadruped Locomotion —
• Adaptive-MHE: A Sampling-Based Adaptive MPC for Legged Loco-Manipulation via Moving Horizon Estimation —
• LiLi: Lie Theory Based 3D LiDAR Scan Alignment Degeneracy Detection —
• Volumetric Harmonic Field Navigation for Quadrotors —
• ViLoMan: Learning Visual-Proprioceptive Whole-Body Loco-Manipulation Skills for Humanoid Robots —
• A Morphing Aerial Robot With Thruster-Integrated Flexible Continuum Links for Shape Adaptive Aerial Manipulation —
• KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation —
• Calibrated Probabilistic Obstruction Reasoning with Vision-Language Models for Grasping in Clutter —
• M cubed P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation —
• Gimbal-Based Human Tracking for Companion Robots Using Continual Learning —
• Veo-Act: Enhancing VLA Policies with Frontier Video Models —
• Model-Based Adaptive Precision Control for Tabletop Planar Pushing Under Uncertain Dynamics —
• 2Fast-2Lamaa: Large-Scale Lidar-Inertial Localization and Mapping with Continuous Distance Fields —
• RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation —
• Approximating High Dimensional Self-Motion Manifolds via Deep Generative Models —
• LUMO: Designing Luminous Contact Morphology for Repeatable Whole-Finger Contact Observation —
• Prior Evolution and Task Alignment for Aerial Grasping —
• Fetch My Beer: Synthetic-to-real Hierarchical Policy for Smooth Pick-and-place —
• Technical Report: One-Step Drifting Action Heads for GR00T N1.7 —
• TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer —
• How to Better Train VLAs: Lessons Learned From the REAL-I Challenge at ICRA 2026 —
• Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion —
• REVOLVE: An Automated Closed-Loop Framework for Evolving Robot Manipulation with Minimal Human Intervention —
• OccPlanner: Goal-Aware Occupancy-Conditioned Diffusion Planner for PixelGoal Navigation —
• MoWAM: Explicit Future Motion Prediction for Efficient World Action Models —
• TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces —
• Mechanical Precision Weeding with a Quadruped Robot —
• Vehicle Trajectory Prediction via Neural Fusion of Multiple EKF-Based Trajectory Candidates —
• Tele-Traversability: Rethinking Traversability for Teleoperated Ground Robots in Terrain Navigation —
• ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation —
• Degeneracy-Resilient Teach and Repeat for Geometrically Challenging Environments Using FMCW Lidar —
• Information-Based Trajectory Planning for Spacecraft-to-Spacecraft Tracking and Navigation in Cislunar Space —
• Geometric Shortcuts for Complex Trunk Postures: Dual-Helicity Coupling Enables Low-Dimensional Control —
• STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation —
• EgoPush: Egocentric Multi-Object Rearrangement for Mobile Robots via Constrained Teacher Observability —
• Self-excited actuation enables adaptive and resilient flapping-wing flight —
• DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation —
• Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving —
• Integrated Identification of Collaborative Robots for Robot Assisted 3D Printing Processes —
• Ultrafast Sampling-based Kinodynamic Planning via Differential Flatness —
• Learning to Stack: Cube-Stacking Imitation Learning from Virtual Reality Demonstrations —
• CaSCo: Cascade-Aware Soft-Collision Motion Planning —
• SEAM: Submap-Anchored Evidence for Lifelong LiDAR Mapping under Trajectory Deformation —
• Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation —
• Custom PX4 firmware for autonomous hybrid aerial-marine missions —
• Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions —
• Distributed Model Predictive Control with Connectivity-based Contracts —
• GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control —
• Affective Shared Autonomy: Temporal Affect Dynamics and Subjective Evaluation in Bimanual Teleoperation Tasks —
• Runtime Safety Filtering for Two-Terminal Hazards in Robotic Battery Recycling —
• Recovering Aggressively Pruned Vision-Language-Action Models with Offline Hidden-State Distillation —
• From Wizard-of-Oz Human-Robot Dialogue Collection to a Taxonomy of Robot Response Decisions: A Retrospective Analysis of Assistive Pilot Interactions —
• Dynamic-LIVO: A Dynamic-Aware LiDAR-Inertial-Visual Odometry System Using Spatio-Temporal Normals —
• Distributed Event-Triggered Distance-Based Formation Control for Multi-Agent Systems —
• Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies —
• "What's going to happen after I'm gone?": Parent Perspectives on Technology in Supporting Independent Living for Adults with Intellectual Disabilities —
• Learning Holistic Whole-Body Loco-Manipulation with a Bipedal Mobile Manipulator —
• Contact-Constrained Lower-Limb Joint-Offset Calibration for Humanoid Robots —
• Strategic Transformer for Resource-Constrained Multi-Object Navigation in Ultra-Large-Scale Environments —
• Ultra-Low-Impedance Robotic Gripper for High-Bandwidth and Transparent Physical Interaction —
• Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning —
• Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotors —
• RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier —
• Semantic SLAM in Precision Agriculture using Bayesian Inference —
• Spatial-Semantic Uncertainty in VLM-Based Target Search: Balancing Exploration and Identification —
• Imagine-TAMP: Imagination-Guided Task and Motion Planning in Partial Observability —
• Graph-Based Design of Soft Grippers with Multi-Objective Quality-Diversity Optimisation —
• Execution-Aware Pre-Execution Ranking for Grasp-Conditioned Robotic Placement —
• Decoupling Physical Speed from Path Parameterization in Singularity-Free Guiding Vector Fields —
• VAST: V2X/Dynamic Map-Aware Autonomous Driving Systems Validation Toolchain —
• WorldContact: A Contact-Centric World Model for Scalable Robot Learning —
• SLAMSqueezeBench: Comparing SLAM Systems under Resource Constraints —
• Pose-aware Legged Robot Semantic Exploration with Omnidirectional Perception in Confined Unknown Environments —
• Geometrically-Constrained Radar-Inertial Odometry via Continuous Point-Pose Uncertainty Modeling —
• Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions —
• SmallSatSim: A GPU-Accelerated Microgravity Robotics Toolkit for Planning, Control, and Policy Learning —
• Design and Biomechanical Evaluation of a Lightweight Low-Complexity Soft Bilateral Ankle Exoskeleton —
• Sim2Real Diffusion: Leveraging Foundation Vision Language Models for Adaptive Automated Driving —
• Dense to MoE Adaptation for Compact Vision Language Action Policies —
• Gait-Dependent Effects on Quadruped Locomotion for Load-Carrying using Passive Mechanism —
• Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation —
• SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning —
• LoCal-RIO: Radar-Inertial Odometry with Loop-Closure IMU Bias Calibration —
• Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibration —
• Walking on the Slope: Stable Bipedal Gaits with Genetic-Algorithm-Optimized Trajectories —
• Towards AI-enhanced control: a numerical technique for trajectory smoothing of a parallel robot for pancreatic surgery —
• FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models —
• EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation —
• Thor: Towards Human-Inspired Whole-Body Reactions for Intense Contact-Rich Environments —
• TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation —
• Imagine then Verify: Affordance-Targeted Active Perception for Task-Oriented Grasping in Cluttered Scenes —
• STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots —
• Smartphone GNSS Booster: Centimeter-Level Pedestrian Positioning Using a Portable Signal Re-Radiator —
• Receding-Horizon Pushing with Composable Object-Centric Policies —
• SCULPT-VLA: Learning Structured Control through Staged Action Grounding —
• Robust Safety Filtering for Input-Constrained Underactuated Linear Systems —
• Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts —
• Preserving Full 6-DOF Actuation Under Abrupt Total Rotor Failures: Passive Fault-Tolerant Flight Control Using a Biaxial-Tilt Hexacopter —
• MoE-ACT: Scaling Multi-Task Bimanual Manipulation with Sparse Task-Conditioned Mixture-of-Experts Transformers —
• Stability-Aligned Residual Adaptation for Rapid Recovery from Dynamics Shifts —
• Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models —
• GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots —
• Interoceptive Robots for Convergent Shared Control in Collaborative Construction Work —
• Goal-Conditioned Neural ODEs with Guaranteed Safety and Stability for Learning-Based All-Pairs Motion Planning —
• PINGU: Extending Air-Bearing Spacecraft Emulators with Open-Source Actuators and Learned Control for Contact-Rich Proximity Operations —
• Manipulation Feasible Navigation Among Movable Obstacles with Discrete Contact Pushing —
• MicroPush: A Lightweight Simulator for Sim-to-Real Microrobotic Pushing and Assembly —
• Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation —
• Towards Reliable Underwater Diver-Robot Interaction: Gesture Design, Interaction Logic, and Real-World Evaluation —
• DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement —
• ARSTAG: An Agentic Real2Sim2Real System for Task-Specific Robot Data Generation —
• Robotic Valve Turning: Axial Misalignment Correction Using Reaction Torque Feedback —
• Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning —
• What Matters in Designing World Action Models: An Empirical Study —
• Spatiotemporal Calibration of Doppler Velocity Logs for Underwater Robots —
• Odometry-Aided Real-Time Mapping for Underwater Robots Using Forward-Looking Sonar —
• Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D —
• Object-Centered Reconstruction for Vision-Based 3D Force Estimation —
• FlockDiffusion: Assignment-Conditioned Diffusion for Multi-Drone Task Allocation and Completion —
• PRIMO: Prior-Informed Odometry from Human-Motion Tracking for Humanoid Robots —
• Unleashing the Agility of Wheeled-Legged Robots for High-Dynamic Reflexive Obstacle Evasion —
• CAR: Cross-Vehicle Kinodynamics Adaptation via Mobility Representation —
• MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning —
• Steerable and Reactive Grasping Through Modular Design with a Three-Point Interface —
• BayesianGS-SLAM: Uncertainty-Aware Neural Rendering SLAM via Probabilistic Formulation —
• Safety Control of a Hyper-redundant Robot via Adaptive Weighted Control Barrier Functions —
• Topology-Informed Visual Prompting For Vision Language Action Policies —
• FORTE: Task-Adaptive Force Capability Optimization for Mobile Manipulators —
• MIRA: Real-Time Full-Duplex Human-Robot Interaction for Embodied Companions —
• World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild —
• Expanding the Workspace of Electromagnetic Navigation Systems Using Dynamic Feedback for Single- and Multi-agent Control —
• Learning to Drive on Mars: Visual Multimodal Traversability Estimation for Off-World Navigation —
• Audio-based UAV Localization with Adaptive Temporal Correspondence via Reinforcement Learning —
• AquaOrbit: Sim-to-Real Reinforcement Learning for Underwater Target Orbiting under Intermittent Visual Feedback —
• Grounded Action Model: 3D Grounding as a Foundation for Robotics —
• ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks —
• UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains —
• Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Tracking —
• Zephyron: Integrated Design and Analytical Evaluation of a Solar-Assisted Mobile Manipulator for Multimodal Environmental Reconnaissance and Distributed Visual Inference —
• Deploying Foundation Models for Embodied Navigation —
• DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation —
• A Deployable Four-Finger Payload for Teleoperated Free-Flying Manipulation with Astrobee —
• Norm2Tex: Augmenting Visuo-Tactile Simulations with Texture —
• Capability-Aware Arbitration for Semantic Intent-Based Shared Control —
• Beyond Visual Quality: A Study of Test-Time Planning with World Action Models —
• Toward Human-in-the-Loop Robot Failure Recovery: Bridging Communication Gaps in Human-Robot Collaboration —
• SPARSER: Sparse Variable Projection by Exploiting Separable Structure in Robotic Perception —
• ScaleMPA: Rethinking Scalable RRT* Acceleration With a Grid-Native Representation —
• InsertAnything: Generalizable Contact-Rich Precision Insertion from Simulation to Reality —
• MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation —
• When Does Touch Matter? Charting the Vision-Interaction Gap in Cluttered Dexterous Grasping —
• Benchmarking Robots for Everyday Environments: From Lab Experiments to Real-World Operations —
• ArborSplat: Online Semantic Gaussian Splatting SLAM for Orchards —
• SafeLoop: Risk-Aware Rollback for Vision-Language-Action Manipulation —
• The Cartesian Hand: In-Hand Manipulation with All-Linear Fingers —
• An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM —
• AgriGen: Large-Scale Scene Generation Framework for Photorealistic Agricultural Robotics Simulation —
• A Reconfigurable Bidirectional Cable-Driven Hip Exoskeleton with Swappable Bench/Backpack Dual-configuration Actuation —
• PAKT: Physically-Aligned Kinesthetic Teaching for Reinforcement Learning —
• PLAT: Sparse Timed Keyframe Motion Tracking for Humanoid Control via Privileged Latent Transition Learning —
• Unsigned Distance Maps on 2D Point Cloud Registration —
• History-Conditioned Flow Matching for Probabilistic Dynamics of Tendon-Driven Continuum Robots —
• Anatomy of Uncertainty: Expressive Descriptors of Robot Motion for Nonverbal Human-Robot Communication —
• MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos —
• Relative Contact Velocity-Controlled Hand-Object Mechanism for Dexterous Tool Manipulation —
• Impact-Time Guidance via Normal Contraction to a Time-to-Go Isochron —
• DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving —
• Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation —
• MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection —
• Generalists Act, Specialists Intervene: Modular Stage-Selective Reinforcement Learning for Vision-Language-Action Manipulation —
• Hierarchical Floorplan-Guided Vision-Language Exploration for Embodied Question Answering —
• Shaft-Configuration-Adaptive Catheter Tip Position Estimation via Motor-History Conditioned Residual Learning —
• Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving —
• Fisheye-VLA: Decoupling Coverage and Acuity for Manipulation with a Single Fisheye Camera —
• SG-CPG: Severity-Gated Central Pattern Generators for Adaptive Quadruped Locomotion under Continuous Actuator Degradation —
• Brace Yourself: Task-Conditioned Environmental Bracing for Forceful Humanoid Manipulation —
• SEG-JPEG: Simple Visual Semantic Communications for Remote Operation of Automated Vehicles over Unreliable Wireless Networks —
• Mitigating Overconfidence in Nonlinear Kalman Filters via Covariance Recalibration —
• Safety-Constrained Model Predictive Control for an Omnidirectional Walking Assistive Robot Using Control Barrier Function —
• Designing an Efficient Excavator Bucket for Lunar ISRU: A Comparative Study with Vision-Based Fill and Displacement Analysis —
• Induced Riemannian Metrics for Motion Planning with Constraints —
• MultiPush: Learning to Rearrange with Teams of Car-Like Pushers —
• MSK-Bench: Benchmarking Full-Body Musculoskeletal Motor Control Across Tasks, Control Paradigms, and Physiological Metrics —
• What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency —
• Control Architecture for Safe Grasping of Fragile Objects Using a Coarse Position-Controlled Gripper —
• Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization —
• Spiking Neural Network Control of a Flapping-Wing Robot on Resource-Constrained Hardware —
• TM-APR: Thermal Temporal-Memory Localization via Analytic Online Adaptation —
• Beyond End-Task Success: How to Audit Visual Experience Retrieval in Robotics —
• Learning Air-Ground Motion Control with Temporal Mode Switching and Cross-Terrain Tracking —
• Generalizing Manipulation Skills with a Local Coding Agent —
• RoboTwin-Phys: Do WAMs and VLAs Understand the Physical World? —
• Angular momentum analysis on Karate roundhouse kicks: a longitudinal case study —
• CAR-EnKF: A Covariance-Adaptive and Recalibrated Ensemble Kalman Filter Framework —
• Stability and Sensitivity Analysis for Objective Misspecifications Among Model Predictive Game Controllers —
• Learning Expressive Humanoid Locomotion from Monocular Runway Videos for Robot Fashion Shows —
• Bend the Clock: Predicting Ahead to Beat Latency in Event-Based Object Detection —
• VibeAct: Vibration to Actions for Contact-Rich Reactive Robot Dexterity —
• Duet: Dual-Robot Understanding via Efficient Teaching —
• Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees —
• Robust Trajectory Tracking of Autonomous Surface Vehicle via Lie Algebraic Online MPC —
• Collision-Affording Point Trees: SIMD-Amenable Nearest Neighbors for Fast Collision Checking —
• phi-RIE: From Photorealistic Reconstruction to Interactive Environments —
• An Aerial Manipulator for Perception-Driven Flower Targeting Toward Contactless Pollination in Vertical Farming —
• Advances in Modeling Techniques for Ventricular Assist Devices: A Comprehensive Review and Future Directions —
• Distributed Power Allocation Scheme with Prescribed Performance and Intermittent Dynamics for BESSs with Discharge Rate Constraints in Microgrids —
• Detection of Synchronized AI Data Center Load Episodes Using SCADA Telemetry —
• On asymptotic stability of the time-varying Kalman filter for unstabilizable linear systems: an optimization perspective —
• Macroscopic Motion Patterns from Generalized Velocity Rigidity in Multi-Agent Networks —
• Chaotically Paced Transit of an Embedded-Leader Swarm with Local Spring-Damper Formation Control —
• On the Optimal Co-location of Data Centers with Renewable Energy Sources in SIDS —
• Imagine2Act: Leveraging Object-Action Motion Consistency from Imagined Goals for Robotic Manipulation —
• LLM-Powered Socially Assistive Robot-Delivered Cognitive Behavioral Therapy Exercises: an Exploratory Study with University Students —
• Probabilistic Hazard Analysis Framework with Stochastic Optimal Control for Deteriorating Civil Infrastructure Systems —
• Nonlinear Moving-Horizon Estimation Using State- and Control-Dependent Models —
• Data-Driven Sub-Optimal LQ Regulator for Linear Input-Delay Systems based on Informativity —
• Estimation of Unknown Parameters in Presence of Perturbations and Noises with Application to GPEBO Design —
• Semi-discrete Optimal Transport for Time-Varying Multi-Agent Coverage Control —
• Decentralized Continuification Control of Multi-Agent Systems via Distributed Density Estimation —
• A Closed-Loop Model of an Anion Exchange Membrane Electrolyser Based on Operational Data —
• A general representation form of system data with feedback control and fundamental lemma as examples —
• Quantum Computing in Next-Gen Smart Grid Operations: A Comprehensive Review —
• Rao-Blackwellized Stein Gradient Descent for Joint State-Parameter Estimation —
• Bifurcation Beyond Surface-Tangential Asymptotic Convergence in Continuous Sliding Mode Control —
• LMP-GNN: Probabilistic Reconstruction of Missing Lane Counts for Signed Max-Pressure Traffic Signal Control —
• Data-Driven Unknown Input Reconstruction for MIMO Systems with Convergence Guarantees —
• Bridging RL and MPC for mixed-integer optimal control with application to Formula 1 race strategies —
• Nonlinear Predictive Cost Adaptive Control of Pseudo-Linear Input-Output Models Using Polynomial, Fourier, and Cubic Spline Observables —
• Safety Under State Uncertainty: Robustifying Control Barrier Functions —
• An Exact Componentwise Voltage-Monotonicity Threshold for Radial Distribution Networks —
• Adaptive sliding mode formation control for space interferometer missions —
• Multi-Period Repetitive Control Design in a Time Delay Framework with Application to an Active Vibration Isolation System —
• Data-Driven Synthesis of Robust Positively Invariant Sets from Noisy Data —
• Entropy-Regularized Optimal Transport for Time-Varying Multi-Agent Coverage Control —
• Set-Based Value Function Characterization and Neural Approximation of Stabilization Domains for Input-Constrained Discrete-Time Systems —
• Constrained Feedback Control of Nonlinear Systems via Approximate HJB and Control Barrier Functions —
• Reachability Guarantees for Energy Arbitrage —
• Koopman-Based Linear MPC for Safe Control using Control Barrier Functions —
• A Marginal Cost Consensus Scheme with Reset Mechanism for Distributed Economic Dispatch in BESSs —
• Time-Optimal Operation of a Load-Hoisting Gantry Crane —
• GNN-Accelerated Mixed-Integer Dual MPC for Interactive Driving —
• Machine Learning-Based State Estimation for an Actual Transmission System Using Field PMU Data —
• Reactive Power Beyond Sinusoids: Scalar Measurement Readouts and Information Limits —
• Consensus and Synchronization of Multi-agent Systems over Finite Fields - Graph Topologies —
• Designing a Pseudo-Random Bit Generator with a Novel 5D-Hyperchaotic System —
• Sufficient and Necessary Smooth Barrier-like Conditions for Continuous-Time Stochastic Reach-Avoid Verification —
• Local Input-to-State Stability for Consensus in the Presence of Intermittent Communication and Input Saturation —
• Optimization-Based Formation Flight on Libration Point Orbits —
• Real-Time Prediction of Lower Limb Joint Kinematics, Kinetics, and Ground Reaction Force using Wearable Sensors and Machine Learning —
• Wildfire Resilient Unit Commitment under Uncertain Demand —
• Collective Tube Model Predictive Control With Distribution-Free Joint Safety Certificates —
• Sufficient and Necessary Continuous Barrier-like Conditions for Discrete-Time Stochastic Reach-Avoid Verification —
• Minimax-Optimal Robust Identification of Continuous-Time Systems: Handling Narrow-Band Disturbances in the Frequency Domain —
• Quantifying Trade-Offs Between Stability and Goal-Obfuscation —
• On the dynamic behavior of the network SIRS epidemic model —
• Data center cooling choices shift water impacts across the grid: An integrated water-energy model for sustainable data center development —
• Extracting Exact Lie Derivatives Without Backpropagation: A Dual Compiler for Neural Control Barrier Functions —
• Control Synthesis against LTL Specifications with Long-Run Visit Proportion Objectives —
• Making Every Bit Count for A-Optimal State Estimation —
• Boundary adaptive observer design for semilinear hyperbolic rolling contact ODE-PDE systems with uncertain friction —
• Microwave-acoustic-based isolated gate driver for power electronics —
• Co-Investment with Payoff-Sharing Mechanism for Cooperative Decision-Making in Network Design Games —
• An Algebraic Observer for State-Affine Systems —
• Remote State Estimation with Unreliable Communication: Information Asymmetry and Belief Structure —
• Quasi-Static Fault-Tolerant Feedback Control of a Quadrotor under Rotor Failure with Provable Safety Guarantees —
• Stability of Slow-Fast Nonlinear Dynamics: Moving Equilibrium Case —
• Benefits of Linear Dynamic State Feedback in Co-stabilization —
• Contract-Based Decomposition of Temporal Logic Specifications for Networked Systems under Arbitrary Partitions —
• Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure —
• Plug-and-Play Stability Certificates Compliant with Black-Box Models of Devices —
• Privacy-Preserving Coordinated Operation of Power Grids and AI Data Centers: A Checkpoint-Aware Three-Phase Scheme —
• On stability of a distributed observer over switching networks: The case of commutative coupling —
• Energy-optimal predictive control of discrete-time port-Hamiltonian systems: Closed-loop practical stability —
• Three High Performance Global Tracking Composite Adaptive Controllers for Fully Actuated Euler-Lagrange Systems: Experimental Validation —
• Receding Horizon Multi-Agent Deceptive Path Planner —
• Remote Magnetic Levitation Using Reduced Attitude Control and Parametric Field Models —
• Decentralized Guidance and Control for Rendezvous and Docking with a Tumbling Target using Multiple Servicers —
• New perspectives for the fitness fatigue model: how to revisit questions about the science of sports training from the perspective of systems control theory —
• Leader-follower Attitude Synchronization of Rigid-body Systems on SO(3) —
• Finite-Horizon Robustness Analysis under Mixed Disturbances using Signal-IQCs —
• Online Learning-Based Adaptive Hybrid Benders Decomposition for Risk-Averse Optimal Sizing —
• Two-impulse Rendezvous Planning about Thrusting Spacecraft on SE 2(3) —
• Tractable Reinforcement Learning for Full Class of Signal Temporal Logic Specifications Using Spatiotemporal Tube Reward —
• Optimal Guidance with Terminal Intercept-Angle Constraints and Acceleration Bounds —
• A partitioned fluid-structure interaction solver for two-phase sloshing and flexible spacecraft dynamics —
• Reward-Rate Congestion Games and Replicator--Dinkelbach Dynamics —
• Exact Average Consensus under Noisy Communication Links: A Decentralized Gradient Perspective —
• GA-Agent: Large Language Models as Hyperparameter Optimizers for Evolutionary Controller Synthesis —
• Reshaping Converter-Network Interactions in Microgrids: From Virtual Impedance to Virtual Two-Port Control —
• Evaluating Grid Strength with Rising Penetration of Inverter Based Resources —
• How Sensor Attacks Transfer Across Lie Groups —
• Salted Fisher Information for Hybrid Systems —
• Reduced Order Observers for Monocular Visual Inertial Odometry —
• Robust Mode Transition for Spacecraft Attitude Control —
• QMSR: Query-Conditioned Mask-wise Expert Routing for Robust Open-Vocabulary Underwater Object Retrieval —
• Real-Time Bounded Catenary Solver for UAV Tether Modeling —
• Stochastic Neural Signed Swept Volume for Real-time Chance-Constrained Trajectory Optimization —
• Barrier Certificate Synthesis for Non-Polynomial Robotic Dynamics via Polynomial Lifting —
• SafeStage: Evaluating Safety Before, During, and After Vision-Language-Conditioned Robot Manipulation —
• Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs —
• AeRSoM: An Aerial Rigid-Soft Integrated Manipulator for Contact-Rich Manipulation —
• Versatile Exoskeleton Control Supports Elderly Joint Energetics During Hip-Intensive Tasks —
• Incremental Stability and Convergence Properties of Discrete-Time Projected Control Systems —
• Suboptimal Formation Reconfiguration of Satellites Under Input Directional Constraints —
• HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models —
• SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs —
• How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation —
• HEROIC: Heterogeneous Evidential Reasoning for Open-Vocabulary Identification and Cross-Robot Collaboration —
• RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision —
• Resilient Design and Optimal Operation of Battery Energy Storage Systems for Behind-the-Meter Data Center Microgrids —
• Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies —
• Min-Max Grassmannian Optimization for Online Subspace Tracking —
• TRACS: A Geometry-Aware Framework for Scalable Multi-Agent Path Finding in Warehouses —
• Constraint-Unified MPC for Over-Actuated Surface Vehicles with Post-Detection Fault Reconfiguration —
• SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists —
• Task-Oriented Co-Design and Optimization of Geared Actuators for Robotic Applications —
• AirSplan: Risk-Aware Motion Planning for Quadrotors in Cluttered 3D Gaussian Splats —
• AeRove: A Compact Bimodal Aerial-Terrestrial Drone with Rapid Bistable Reconfiguration for Close-Range Pipeline Inspection —
• ProTracer: Proprioception-Guided Failure Diagnosis in Robot Manipulation —
• Robust Structureless Monocular Visual Inertial Initialization Exploiting Line Features and Vanishing Points —
• PopNavShift: Stress-Testing Social Navigation under Behavioral Population Shift —
• A Monolithic Force-Proprioception Soft Acutuator Enabled by Single-Material 3D printing —
• CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies —
• Becoming a Fruit Ninja: Real-Time Probabilistic Kinodynamic Planning for Manipulator Projectile Interception —
• Resilient Monitoring of Social Dynamical Systems through Collaborative Multi-Agent Networks under Latency —
• Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation —
• Manipulation with Stability Guarantees: Linear Deformable Objects with Non-negligible Physical Response Grasped at Multiple Location —
• Optimal Day-Ahead Scheduling of Fast EV Charging Station With Multi-Stage Battery Degradation Model —
• Reproducible Dynamic Parameter Identification for a Low-Cost Robot Arm: A Positive-Definiteness Audit for Model Acceptance —
• ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling —
• A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies —
• DR-DAQP: A Hybrid Operator Splitting and Active-Set Solver for Affine Variational Inequalities —
• WOLF: World Model Guided LiDAR Exploration with Predictive Frontiers —
• BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models —
• Metallic Ultrasound Waveguides as a Distributed Tactile Sensing Platform —
• VT-Bridge: Bridging Pretrained Foundation VLAs to VTLAs via Lightweight Residual Adaptation —
• FinsSim: A Reality-Aligned Integrated Simulation Platform for Underwater Robot Learning —
• Optimal Control and Closed-Loop Stability of Droplet Transport in a Microchannel —
• Collocated Shape Regulation for Soft Robots —
• Active Spatial Inspection for Effective and Efficient Embodied Exploration —
• Leader-Follower Density Control of Multi-Agent Systems with Interacting Followers: Feasibility and Convergence Analysis —
• Multi-Axis Selective Decoupling Framework for Free-Floating Space Manipulators —
• DEAL-Grasp: Decoupled Alignment Representation for Geometry-Aware Dexterous Grasp Generation —
• Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions —
• The Minkowski Wrap: A Relativistic Speed Limiter —
• A Unified Control Theory Derivation of Discrete-Time Linear Ensemble Kalman Filters —
• VIRGA: Virtual-Agent-Intermediated Riemannian Geometry for Active-Sensing Air-Ground Coordination —
• An Adaptive-Sampling Control Framework for Constrained Linear Systems with Robust Safety Guarantees —
• GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation —
• Design and Experimental Validation of a 3D Printed Torsional Series Elastic Actuator for Safe Human Robot Interaction —
• ForwardDLO: Model-Based Bimanual Shape Matching of Unconstrained Deformable Linear Objects —
• Examining the Difference in Human Behavior Between Virtual and Real-World Human-Robot Teaming —
• Body-Motion Control of a Simulated Aerial Swarm from a First-Person View —
• A3P5 NEMESIS Integrated Rover Design for Environmental Reconnaissance and Robotic Sampling with Reproducible Mobility Analysis and an External Data Machine Learning Calibration Benchmark —
• PESTO: Formally Correct Registration of LiDAR Point Clouds with Limited Overlap —
• An Efficient Algorithm for Minimum-Pressure Growth Planning of Vine Robots —
• Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs —
• HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments —
• Wheel-loader V-Cycle Automation with Deep Koopman MPC —
• Selective Commitment for Language-Guided Object Retrieval under Partial Observability —
• On the Control of Mobile Ad-Hoc Agent Deployments in Partially Observed Space —
• DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies —
• Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection —
• Intelligence Across Embodiments —
• The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models —
• Evolving Inspectable O-RAN Slicing xApps with LLMs —
• InternW0: A Foundational Physical World Model for Efficient Real-World Interactions —
• Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation —
• Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction —
• LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials —
• Generalizable Robotic Insertion with World Models —
• EvEMTBench: An Open Benchmark for Machine Learning in Power System Protection —
• A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models —
• Safety-Critical Control under Uncertainty via Adaptive Conformal Quantile Prediction Intervals —
• Risk-Aware Motion Planning and Control under Unknown Dynamics with Hybrid Observations —
• LunaDrive: A Delay-Compensated High-Voltage GaN FET-Based Motor Driver for Dynamic Robots with Flat BLDC Motors —
• Scaling Vision-Language Reward Learning for Robot Manipulation in Parallel Simulation —
• CARF: Contrastive Attraction-Repulsion of Failure-Guided Flow Matching —
• MAPLE-RF: Efficient Probabilistic RF Source Localization in Partially Explored Environments —
• MA-LIPP: Cooperative Multi-Agent Load-Aware Informative Path Planning for Heterogeneous Robot Teams —
• PowerModels-ACOPF-AI: On-the-Fly Machine Learning Approach for Solving AC Optimal Power Flow Integrating Renewable Energy Sources —
• PIVOT: Perception-aware Independent Viewpoint Online Optimization —
• Enhancing the Perception of Safety and Comfort during Physical Human-Robot Handshake Interactions by Integrating Flexible Elements into a Robotic Arm —
• Benchmarking Visual-Inertial Odometry in Subterranean Environments Under Sensor Degradation, Miscalibration, and Dynamic Occlusion —
• Response Time Stochastic Analysis for Fixed-Priority Stable Real-Time Systems —
• TACO: TActile World Model as a Self-COrrector for Scalable Robot Policy Post-Training —
• Relationship between Loss of Load Expectation and Frequency of Load Loss Events —
• Design and Control of a Cable-Driven Switchable Actuator with Torque/Tension Dual Modes for Exoskeletons —
• Macro-Scale Electrostatic Origami Motor —
• ARCGym: Benchmarking Deep Reinforcement Learning in Autonomous Robotic Colonoscopy —
• AoI-Driven Hierarchical Learning for Cooperative Resource Sharing in Multi-Operator UAV Networks —
• Layered Control of Partially Observed Stochastic Systems —
• Demonstration Synthesis from a Single Scan via Gaussian Splatting for Visuomotor Policy Learning —
• Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation —
• Adapting Rigid-Body Dynamics Derivatives for Constraint Embedding Closed-Chain Models —
• SPARROW: Survival-POMCP for Adaptive Robot Routing, Observation, and Waiting —
• Performance-Preserving Online Adaptation in Social Navigation via Diffusion Steering —
• Compressed delayed-information projection for six-degree-of-freedom underwater vehicle navigation under delayed acoustic positioning —
• DUGM-R: Uncertainty-Aware Dynamic Grid Mapping and Risk-Triggered Recovery for Learned Local Navigation —
• Banana Kick: Response-Informed Skill Evolution for Humanoid Soccer —
• Learning Dissipative Dynamics with Dissipativity-by-Construction Discrete-Time Neural Networks —
• SABER: Learning Attention-based Semantic Affordance for Legged Locomotion —
• Algorithmic Energy Management in Constrained Railway Traction Networks: A Systematic Review —
• RAYA: Learning Where and When to Intervene for Robot Recovery —
• Towards Fine-Grained Object Manipulation: SAM3-Guided Visuomotor Policy with Persistent Memory Learning and Focused Visual Conditioning —
• DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments —
• GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments —
• Structured Learning for Electromagnetic Field Modeling and Real-Time Inversion —
• Towards Effective Visual-Inertial SLAM with Passive-Only Sensors for Low-Cost Autonomous Underwater Vehicles —
• Robot Programming with Augmented Reality: The Role of Spatial Ability —
• Energy Management Strategies for Electric Aircraft Charging Leveraging Active Landside Vehicle-to-Grid —
• Comparing Commercial Depth Sensor Accuracy for Medical Applications —
• A Robot Among People:From Social Imitation to the Social Becoming of Human Groups —
• Feasibility Distance Fields for Heterogeneous Constraints in Robot Configuration Space —
• Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training —
• Visual Proactivity: Enhancing Human-Robot Collaboration Through Intent Communication —
• PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing —
• Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation —
• The Small-Talk Effect in Practical Synchronization of Heterogeneous Oscillating Dynamics —
• Multi-Scale Datacenter Power Modulation —
• A Mean-Field Approach for Safe Routing of Multi-Destination Urban Air Mobility Networks —
• Design of Economic Dispatch Schemes of An Isolated BESS Network Based on Distributed Discrete-time PI+Rest Consensus —
• Acoustic Ellipses: Bio-Inspired Omnidirectional Echolocation in Cooperative Multi-Agent Systems using Frequency Sweeps —
• Closed-Loop Motion Planning for Differentially Flat Systems: A Time-Varying Optimization Framework —
• Agentic AI Enabling Autonomous, Self-Organizing, and Evolving UAV Networks —
• WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning —
• 4D Radar Perception Algorithms for Autonomous Driving: A Review —
• DEXTERA: From a Single Image to Deployable Dexterous Manipulation via Real-to-Sim-to-Real —
• Ordinal Neural Collapse as a Representation Prior for Visual Navigation —
• Navi-Agent: Unlocalized Monocular Navigation Agent —
• Learning Foresight without Explicit Trajectories for 3D Diffusion Policies —
• Towards Scaling Marine Perception with Synthetic Data —
• LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation —
• Underwater Visual Target Tracking with Target-Specific Depth Estimation and Adaptive Model-Fusion Predictive Control —
• Resilient Motion Planning for Free-Flying Space Robots under Actuator Failures —
• StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation —
• Winning a Won Game: Strict Reach-Avoid-Stay Control Barrier Functions for High-Dimensional Black-Box Systems —
• EMoG: Emotion-Modulated Gait Generation for Expressive Humanoid Locomotion —
• ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph —
• Does Online Gravity Estimation Matter? Revisiting a Silent Design Split in LiDAR-Inertial Odometry —
• M3-Tele: A Unified Multimodal Teleoperational Framework for Compliant Whole-Body Mobile Manipulation —
• BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation —
• Observation Design for Certified Control Authority: Projection--Estimability Separation and Active-Face Equivalence —
• DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation —
• Closed-Loop Object-Informed Control for Non-Prehensile Robot Manipulation —
• See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation —
• RoverDevKit: An open, physics-grounded tradespace toolkit for conceptual design of lunar micro-rovers —
• Robust multi-scale leader-follower control of large multi-agent systems —
• Spiderbot: An Open-Source Energy-Efficient Hexapod with Passive Gravity Compensation —
• MPC-Based Trajectory Tracking for a Quadrotor UAV with Uniform Semi-Global Asymptotic Stability Guarantees —
• Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation —
• LapaTrack-3D: 6 DoF pre-operative shape tracking for laparoscopic surgery —
• Feeling Terrain Before Crossing: World Models for Off-Road Navigation —
• OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion —
• DexPIE: Stable Dexterous Policy Improvement from Real-World Experience —
• PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration —
• Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies —
• CoRelNav: Collaborative Relational Navigation for Multi-Robot Spatially Constrained Semantic Navigation —
• LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion —
• Learning a Speed-adaptive Hip Exoskeleton Control Policy Via Sim-to-real Reinforcement Learning —
• A Modular Dual-Arm Robotic Cell for Disassembly and Repair of Industrial Control Electronics —
• Recording Hand-Held Laparoscopic Instrument Motion in the Operating Room: Magnetometer-Free Fusion of Inertial, Range and Visual Sensing —
• Advancing Minimally Invasive Precision Surgery in Large Open Cavities with Robotic Flexible Endoscopy —
• LEAP: Learning Emergent Active Perception for Quadruped Navigation —
• Fault-Tolerant, Rigidity-Preserving Control of Inflatable Truss Robots —
• DR-MPC: Fast and Feasible Dynamics-Relaxed Model-Predictive Control for Legged Locomotion —
• ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation —
• CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding —
• AC-DC: Adaptive Communication for Scalable Dynamic Average Consensus in Multi-Robot Ergodic Search —
• RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents —
• Distribution Network Reconfiguration: A Reproducible Benchmark of Heuristic, Metaheuristic and Mathematical Methods —
• ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control —
• HydroMap: Probabilistic Water Surface Elevation Mapping for Semantic Scene Representation in Inland Waterways —
• Design and Implementation of an Ultra-Low-Cost Wall-Climbing Robot for Infrastructure Crack Detection —
• LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction —
• Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers —
• Dr-LiSA: Direct Radar-Lidar Scan Alignment for SE(3) Localization —
• Forced Oscillations in Power Systems Induced by Data Centers Hosting AI Workloads —
• SOL-SLAM: Inverse Compositional Gauss-Newton Direct Registration for Fast Sonar-Only Local SLAM —
• PSR: Predictive Sensorimotor Representation Learning for Contact-Rich Manipulation —
• Digital Twin-Driven VR Teleoperation with Multi-View Spatial Perception for Surgical Robots —
• DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation —
• Rectify, Don't Regret: On-Policy Closed-Loop Training for Multimodal Trajectory Prediction —
• From Reach to Insert: Tactile-Augmented Precision Assembly under Sub-Millimeter Tolerances —
• Dynamic Modeling and LQR Control of a Single Coaxial Drone with 2DOF Thrust Vectoring Mechanism —
• Lies We Can Trust: Quantifying Action Uncertainty with Inaccurate Stochastic Dynamics through Conformalized Nonholonomic Lie groups —
• P squared Calib: Utilizing Pattern Priors for LiDAR-Camera Extrinsic Calibration —
• Universal Navigation Interface: Robot-Free Data for Wheeled Robot Navigation —
• Ask Before It Tells: Benchmark-to-Robot Body-Cue Transfer for a Question-First Bedside Robot —
• VLM-MPPI: Grounding Natural Language in Behaviorally Diverse Trajectories for Aerial Navigation —
• Ensuring Stability of Non-Minimal Modes in Input-Output Data-Driven Representation —
• Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control —
• Underwater Navigation in Unsteady Flows Using Measurement Histories from a Single Sensing Unit —
• NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping —
• Beyond Object Selection:Markerless Gaze-based Robot Placement at Arbitrary Positions —
• Feasibility and Singularity in High-Order Safety-Critical Control for Quadrotor UAVs —
• From Instrument-Mounted Demonstrations to In-Vivo Execution: Learning Bimanual Laparoscopic Appendectomy Without Robot-Collected Demonstrations —
• Transferring the Intelligence of VLMs to Robotic Control —
• Task-Oriented Active Learning of Residual Dynamics for Model Predictive Path Integral Control —
• Efficient physiological control of an integrated system architecture for continuous-flow ventricular assist devices: in-silico study —
• Omnidirectional Amphibious Locomotion via Internal Mass Actuation —
• InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies —
• Sampling-based Model Predictive Control Using Trust Regions —
• Real-Time Service Robot Replanning via Simple Button Interaction for Improved Task Success and User Experience —
• A Candidate Counterexample to a Conjecture on ISS for Time-Delay Systems —
• H2RBench: A Real-to-Sim Benchmark for Evaluating Human-to-Robot Transfer —
• CANTABILE: Learning Expressive Dynamics for Robotic Piano Performance —
• Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short-Term Memory Learning —
• Flexible-body Modeling, Kinematic Identification, and Assembly Accuracy of Overconstrained Spatial Linkages —
• RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement —
• A review of imbalance price forecasting in Europe: algorithms, metrics and the way forward —
• ULOHA: An Underwater Bimanual Robot System for Robot Learning —
• When Gigawatts of Computational Load Disappear: Cycle-Space Certificates for Grid Synchronization and Transient Stability —
• MedVLA: A Hierarchical Vision-Language-Action Framework for Closed-Loop Precision Medical Robot Manipulation —
• Predictive Varanus: Combining CSP Conformance Monitoring with Predictive LTL Runtime Verification —
• Beyond Point-Attached Semantics: Stable Object-Centric Semantic Fields for Robust Manipulation —
• GeomVLA: Unifying Scene, Motion, and Action in 3D —
• Distributed Secondary Frequency Control and SoC Balance for Droop-Controlled BESSs with A Unified SoC Relative Variation Rate —
• Phrase-Level Robotic Guqin Performance: Bimanual Motion Planning and Audio-Tactile Interaction Monitoring —
• Multi-Agent Transportation of Free-Flyers in Microgravity Via Pushing Interaction Under Human-in-the-Loop Control —
• EgoWild2Dex: Learning Dexterous Robotic Manipulation from In-the-Wild Human Experience —
• Learning Slope-Adaptive Whole-Body Locomotion for Humanoid Robots in Roofing Construction —
• Motoneuron-Inspired Sampling for Model Predictive Path Integral Control —
• Modelling and Model-Checking a ROS2 Multi-Robot System using Timed Rebeca —
• Atomic Motion Coordinate for Language-Steerable and Force-Responsive Manipulation —
• FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback —
• CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing —
• Learning to Solve Two-Stage Stochastic Unit Commitment Problems with Quality Guarantees —
• Gray-Box Model Predictive Control for Articulated Dump Trucks via Gaussian Process Learning of Sideslip —
• TADreamer: Zero-Shot Language-Guided 3D Navigation for Terrestrial-Aerial Bimodal Robots via Video Imagination —
• Grasping by interconnection: robust closing motions from coarse object templates —
• Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation —
• You Should Be Properly Scoring Your Odometry —
• Navigate or Relocate? Planning Among Movable Obstacles in Unknown Environments —
• Effects of Assistance Delay on Joint Mechanics and Energetics in Biological Torque Control of a Hip Exoskeleton —
• CoRe-WAM: Correspondence-Aligned Temporal Residuals for World Action Models —
• Asymptotically Optimal Multi-Robot Task and Motion Planning —
• Foldable Antenna Array in Space-Air-Ground Integrated Networks: Architectures and Applications —
• SemSafe-3DGS: Semantic Risk-Aware Active Navigation in Uncertain 3D Gaussian Splatting Maps —
• NavSafe- infinity: Benchmarking Closed-Loop Driving Safety in Photorealistic Environments —
• OpenDexGrasp: Open-vocabulary Task-Oriented Dexterous Grasping —
• Bayesian Safety Guarantees for Port-Hamiltonian Systems with Learned Energy Functions —
• Safety-Filtered Distributed Koopman-MPC —
• Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs —
• Object-Centric Conditioning for Visuomotor Flow Matching —
• A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics —
• DAVIS: A Depth-Only End-to-End Active-Vision Framework for Humanoid Soccer Skills —
• TACIT: Tactile Contact Supervision for Spatial Attention in Dexterous Manipulation —
• DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo —
• Estimation and Control of Tensegrity Manipulator Kinematics based on Strut Inclination Angles —
• Control Barrier Functions for Safe Free-Flying Robotic Spacecraft Operations in Tumbling Target Capture —
• PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation —
• Beyond RSRP Coverage: UAV Serviceability in Interference-Limited Urban 5G NR Networks —
• Range-Aided SLAM Initialization Exploiting Accurate Heading Information —
• Minimum Time Trajectories for a Car-Like Mobile Robot Moving with Rigid Wheels Under Non-Sliding Constraints —
• MOLA LiDAR-Inertial Odometry (MOLA-LIO) on the COMFORT Localization Benchmark —
• Modularity is Not Enough: Demonstration of a Solderless 400 V DC, 2.5 kW Three-Phase Inverter —
• WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning —
• High-Performance Sensorless Control for High-Speed PMSM with Current Source Inverters —
• D3DWA: Adaptive Weight and Prediction-Horizon for Dynamic Window Approach via Dueling Double Deep Q-Network —
• DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mapping —
• Barrier Functions Against Safety Drift in Shared Control —
• Wave-Robust Passive AUV Localization Using FP-MUSIC —
• MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts —
• Learning to Plan in Human-Robot Collaboration: Multimodal Reinforcement Learning for Adaptive Interaction —
• MAGNETAR: Multipath-Guided Spatial Posteriors for Transmitter Pose Inference in the Upper Mid-Band —
• Model-Free Current Control of Permanent Magnet Synchronous Motors via ESO-Based Disturbance Feedforward and Data-Driven H-infinity Residual Feedback —
• A bioinspired internal model-based online estimator for planar pursuit —
• Communication Architecture Co-Design for Distributed Control via System Level Synthesis —
• Path Integral Control in Gaussian Belief Space for Partially Observed Systems —
• EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics —
• Multi-Agent Event-Triggered LQG Control under Shared Communication Constraints —
• Simultaneous Arrival Control for Distributed Multi-Robot Systems with Curvature and Constant-Speed Constraints —
• RoboMP-DINOv2: Prompts, Not Filters for Robust Robot Manipulation —
• Optimal Regret for Online Storage Control via Cumulative Policies —
• Learning Beyond What Humans Can Demonstrate —
• ForceDelta-VLA: Distilling Force-Conditioned ActionCorrections for Contact-Rich Manipulation —
• RotateIt! Fast and Reliable Single-Arm Garment Unfolding via Online-Adaptive Dynamic Rotation —
• Predicted-Flow Control Barrier Functions for Real-Time Safe Optimal Control —
• DRT&R: Direct Radar Teach & Repeat —
• A Switched Adaptive Control Framework for Aerial Manipulators Under Dynamic Transitions —
• TAO-Force: Unifying Force-Aware Perception and Fast-Slow Control for Contact-Rich Manipulation —
• Communication Delay Robust Control of BESS for AI Training Load Smoothing —
• Timely Activation of Safety Filters via One-Step Reachability Expansion —
• Multi-Session Multimodal Underwater Mapping with Acoustic and Optical Imaging —
• LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models —
• Skill Sequence Planning for Collaborative Multi-Robot Construction —
• UWA360CAM: A 360 24/7 Real-Time Streaming Camera System for Underwater Applications —
• Quantifying Mechanical Intelligence in Legged Robots with Information Theory —
• Future-Aware Flow Planning for Safe UAV Target Following —
• VisForce: Visual Grounding of Current and Desired Forces for Goal-Conditioned Dexterous Manipulation —
• Behavior-Aligned Action Tokenization for Robot Policy Learning —
• From LiDAR Maps to Visual Localization: Unified Visual Association for Robust Point-Line-Plane Pose Estimation —
• CIRO7.2: A Material Network with Circularity of-7.2 and Reinforcement-Learning-Controlled Robotic Disassembler —
• GLoTouch: Global-to-Local Haptic Perception Using a Parallel Gripper for Object Search, Recognition, and Grasping Without External Vision —
• Map2Route: Benchmarking Compositional Language-Grounded Route Planning over Semantic Maps —
• NaViRrator: Robot Navigation from Human-Readable Maps through a Learned Visual Route —
• NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation —
• Tip Manipulation in Soft Everting Robots via Wall Retraction and Deployable Fingers —
• Humanoid Locomotion with a Fly-Inspired Recurrent Controller —
• Learning Safe Humanoid Navigation from Reduced Order Models —
• Optimal Trajectory Generation for Improved Magnetic Navigation —
• ElastiQP: An Always-Feasible QP Solver for Constrained Robot Control —
• MatcherCompass: A Deployment-Aware Benchmark to Guide Image Matcher Selection in the Wild —
• Minimizing Bid Cost Recovery for Energy Storage with Uniform Pricing —
• PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation —
• Water Surface Swimming in a Centipede and its Robophysical Model —

Important terms

DreamAvoid

A testing approach used during training to proactively prevent failures by allowing vision-language models to reason about reachability, ensuring safer robot policies.

BEE

Intervention-adaptive reinforcement learning that incorporates vision and language into action models, making autonomous systems more robust when facing situations outside their training data.

InternW0

A foundational physical world model designed for efficient real-world interactions between agents, providing a structured understanding of how physical objects behave in space.

HEROIC

Addresses the need for open-vocabulary identification and cross-robot collaboration, allowing different robots to share knowledge to recognize novel objects or situations.

Energy-Regularized Imitation Learning

A method that trains robotic systems to understand physical effort by regularizing the learning process with energy terms, guiding robots toward physically plausible actions.