Beyond Point-Attached Semantics: Stable Object-Centric Semantic Fields for Robust Manipulation
cs.RO
Submitted: 2026-07-03
Updated: 2026-09-21
Project page: https://zainzh.github.io/beyond-point-attached-semantics
Terminology
Sources
- FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation
- 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
- 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
- Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulation
- Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
- O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation
- DINOv2: Learning Robust Visual Features without Supervision
- Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
- VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
- Utonia: Toward One Encoder for All Point Clouds
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- SAM 2: Segment Anything in Images and Videos
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving