发表机构
The Hong Kong University of Science and Technology; The Chinese University of Hong Kong; SmartMore; Harbin Institute of Technology, Shenzhen; Shenzhen Loop Area Institute（香港科技大学; 香港中文大学; 思谋科技; 哈尔滨工业大学（深圳）; 深圳河套学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RESETTLE是一种模型无关的机器人恢复框架，通过分歧触发检索与高效校正控制，在仿真和真实任务中提升机器人操作成功率，且计算延迟显著低于对比方法，兼容高层智能体规划。
AI 中文摘要
可靠的机器人操作需要及时干预以纠正执行错误后出现的偏差并恢复进度。然而，基于重复视觉-语言推理或迭代在线优化的恢复方法会产生大量延迟，延误干预时机。为应对这些挑战，我们提出RESETTLE（Robotic rEcovery through diSagrEement-Triggered reTrievaL and Efficient Corrective Control），这是一种模型无关框架，可在冻结机器人策略的动作执行接口处提供计算高效的恢复能力。RESETTLE在相同条件下独立采样的两个动作提议持续存在分歧时触发恢复；它使用适配的V-JEPA编码器检索相同任务的演示参考，结合状态伺服先验与受保护的视觉残差执行一次校正动作，无需在线轨迹优化或额外视觉-语言推理，随后将控制权交还给基础策略。在仿真环境中针对6种基础策略，RESETTLE在LIBERO-Plus、Meta-World和RoboCasa Tabletop上分别实现了高达8.70%、6.28%和6.83%的绝对成功率提升，在使用两种策略的4项真实世界任务上也有进一步改进。在基于QwenPI的对比中，其监测与恢复的计算延迟比VoLoAgent的监测与规划延迟低74.04%至93.57%，针对抓取和放置工具调用；它还将Harness VLA的LIBERO-Pro Swap任务成功率从42%提升至50%，证明其与高层智能体规划的兼容性。代码可在以下网址获取：this https URL
英文摘要
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
