Robotic system fixes errors quickly by spotting conflicting actions
RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
Robotics
Summary
Robots sometimes make mistakes when trying to do tasks, and fixing these mistakes quickly is important for success. The authors created RESETTLE, a system that watches for conflicting robot action suggestions to detect problems early. It then finds an example of how to fix the error and quickly performs a corrective movement without complex new reasoning. This approach improves task success rates across many robot tasks and works faster than some other recovery methods.
What this means in practice
- •For robotics engineers: Improve robot task reliability by adding quick recovery triggered by conflicting action outputs to frozen control policies.
- •For automation integrators: Lower recovery latency in automated handling systems by integrating retrieval-guided corrective actions into existing robot controllers.
Authors
Yuxin Chen, Senqiao Yang, Zixuan Wang, Jinhui Ye, Changsheng Lu, Pengguang Chen, Shu Liu, Zhuotao Tian, Jiaya Jia
Abstract
Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery methods based on repeated vision-language reasoning or iterative online optimization can incur substantial latency, delaying intervention. To address these challenges, we introduce RESETTLE(Robotic rEcovery through diSagrEement-Triggered reTrievaL and Efficient Corrective Control), a model-agnostic framework that provides computationally efficient recovery at the action-execution interface of frozen robot policies. RESETTLE triggers recovery when two action proposals independently sampled under identical conditioning persistently disagree. It retrieves a same-task demonstration reference using an adapted V-JEPA encoder and combines a state-servo prior with a guarded visual residual to execute one corrective action without online trajectory optimization or additional vision-language reasoning, then returns control to the base policy. Across six base policies in simulation, RESETTLE achieves up to 8.70%, 6.28%, and 6.83% absolute success-rate gains on LIBERO-Plus, Meta-World, and RoboCasa Tabletop, respectively, with further improvements on four real-world tasks using two policies. In QwenPI-based comparisons, its monitoring-and-recovery computation latency is 74.04%--93.57% lower than VoLoAgent's monitoring-and-planning latency for grasp and place tool calls. It also raises Harness VLA's LIBERO-Pro Swap success from 42% to 50%, demonstrating compatibility with high-level agentic planning. Code available at: https://github.com/JIA-Lab-research/RESETTLE