arXiv cs.AI· Zimo Wen, Yijin Chen, Yuxuan Cao, Wendi Chen, Yanwen Zou, Wenye Yu, Fuhang Kuang, Han Xue, Jun Lv, Chuan Wen, Cewu Lu·· 9 天前AI 评分30
RoboRSI：复杂真实环境中的稳定、高效、可复用机器人自我进化
RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
AI 导读
RoboRSI 是一个基于自顶向下技能精炼（TSR）的机器人自我改进系统，将任务分解为复合、原子和基础技能并明确输入输出契约，由 Manager、Planner、Engineer、Reviewer 协同完成规划、执行、诊断与技能验证发布。
正文 · 原文
Authors:Zimo Wen, Yijin Chen, Yuxuan Cao, Wendi Chen, Yanwen Zou, Wenye Yu, Fuhang Kuang, Han Xue, Jun Lv, Chuan Wen, Cewu Lu
Abstract:A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot agents that act through code can already repair programs from execution feedback, yet it remains a central challenge to organize this experience around the task structure that gives it meaning, so that each repair is attributed to the responsible capability, supported by execution evidence, and validated before it is reused. We introduce RoboRSI, a robot self-improvement system built on Top-Down Skill Refinement (TSR). TSR decomposes tasks into compound, atomic, and base skills with scoped responsibilities and explicit input--output contracts, attributes each execution outcome to the responsible branch, and confines revision to that branch. Building upon this structure, a Manager, Planner, Engineer, and Reviewer coordinate planning, execution, diagnosis, and the validated release of new skills, while people steer the process through objectives and corrections; stable skill sequences are further consolidated into reusable compound skills. On a mobile manipulator, RoboRSI develops multi-object household cleanup over 104 rounds. In simulation, it achieves the highest success rate on LIBERO, LIBERO-PRO, LIBERO-Plus, and RoboTwin, exceeding the strongest baseline by 2.7 to 11.0 percentage points.
| Comments: | project page:this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12424 [cs.RO] |
| (or arXiv:2610.12424v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12424 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zimo Wen [view email]
[v1]
Thu, 8 Oct 2026 17:55:12 UTC (14,340 KB)
来源：arXiv cs.AI · arxiv.org