Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
cs.RO, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Interactive Imitation Learning in Robotics: A Survey
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching
- VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
- HG-DAgger: Interactive Imitation Learning with Human Experts
- OpenVLA: An Open-Source Vision-Language-Action Model
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
- Evaluating Real-World Robot Manipulation Policies in Simulation
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Model-Based Runtime Monitoring with Interactive Imitation Learning
- RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
- Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction
- ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
- Human-in-the-Loop Imitation Learning using Remote Teleoperation
- CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
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