RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
RESETTLE is a model-agnostic framework for robotic recovery that uses disagreement between action proposals to trigger correction, combining a state-servo prior with a guarded visual residual to execute corrective actions efficiently. It achieves success-rate gains in simulated and real-world tasks and reduces monitoring-and-recovery latency compared to existing methods.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- code: Available Artifact link Open source S5
- code: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
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
Open source S4
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
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org