ReAP: From Visual Failure Recognition to Action-Conditioned Risk Prediction for Runtime Failure Monitoring
cs.RO
Submitted: 2026-10-12
Updated: 2026-10-12
Code: https://github.com/MINT-SJTU/Evo-RL
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Exploration by Random Network Distillation
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model
- ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation
- RoboReward: General-Purpose Vision-Language Reward Models for Robotics
- FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
- Cosmos 3: Omnimodal World Models for Physical AI
- DINOv2: Learning Robust Visual Features without Supervision
- Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- The Geometry of Flow-Matching Uncertainty: A Cost-free Uncertainty Proxy and Its Application in Flow-based VLA Failure Detection
- Robot Critics that Sweat the Small Stuff
- Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
- Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies