arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.23288cs.RO
收藏

CoEvolve:面向人形机器人的从技能到策略的自演化代码策略

CoEvolve: Self-Evolving Code Policies from Skills to Strategies for Humanoid Robots

Peking University(北京大学);Renmin University of China(中国人民大学);Beijing XYZ Embodied AI Co., Ltd.(北京XYZ具身人工智能有限公司);Beijing Academy of Artificial Intelligence (BAAI)(北京人工智能研究院)

Zicheng Liu, Haochen Wu, Jiawei He, Suyun Zhao, Huan Yang, Cheng Chi, Hao Tang

AI总结:

本文提出CoEvolve框架,将团队协调表示为基于机器人运动技能的可执行代码,通过验证器引导的协调演化机制提升多机器人协作能力,在人形机器人运输载荷任务中取得良好效果,同时也暴露了部分局限。

摘要:

视觉-语言-动作(VLA)模型和世界动作模型(WAMs)的最新进展拓展了单个机器人的操作能力与全身运动能力,但单个机器人仍受限于自身的实体形态,而许多现实世界任务需要仅通过协作才能实现的能力。现有多机器人框架大多侧重任务分解、分配与重规划,却在物理执行偏离预期行为时,对可执行协调的自适应支持有限。本文提出CoEvolve框架,该框架将团队协调表示为基于固定机器人运动技能的可执行代码。CoEvolve引入了验证器引导的协调演化机制:多模态基础模型通过运动原语、语义目标、临时机器人角色及有界执行参数实例化协调策略;物理验证器评估每一次执行的状态转移,被拒绝的行为会从已接受的检查点触发结构化协调修订,经验证的经验会被保留以指导后续决策。我们使用两个仿真Unitree G1人形机器人在受限走廊中运输自由支撑的刚性载荷来评估CoEvolve,在针对三类多模态主干模型的15次基础任务运行中,CoEvolve完成了8项任务,且所有主干模型均实现了端到端成功。额外评估验证了其在两种额外走廊布局下的适用性,以及在同主干模型和跨主干模型经验初始化后的表现,同时也揭示了其在运动精度和接触稳定性方面的持续局限。这些结果表明,可执行协调是在共享物理约束下适配长时多机器人协作的实用接口。

英文摘要:

Recent advances in Vision-Language-Action (VLA) models and World Action Models (WAMs) have expanded the manipulation and whole body capabilities of individual robots. Yet a single robot remains limited by its embodiment, and many real world tasks require capabilities that can only emerge through cooperation. Existing multi robot frameworks largely emphasize task decomposition, allocation, and replanning, while providing limited support for adapting executable coordination when physical execution deviates from the intended behavior. We present CoEvolve, a framework that represents team coordination as executable code over fixed robot motor skills. CoEvolve introduces Verifier Guided Coordination Evolution, where a multimodal foundation model instantiates coordination strategies through motion primitives, semantic objectives, temporary robot roles, and bounded execution parameters. Physical verification evaluates each executed transition, rejected behaviors trigger structured coordination revision from an accepted checkpoint, and verified experience is retained to guide subsequent decisions. We evaluate CoEvolve with two simulated Unitree G1 humanoids transporting a freely supported rigid payload through constrained corridors. Across 15 base task runs with three multimodal backbone families, CoEvolve completes 8 tasks, with every backbone achieving end to end success. Additional evaluations yield verified placement on two additional corridor layouts and after both same-backbone and cross-backbone experience initialization, while exposing persistent limitations in motion precision and contact stability. These results support executable coordination as a practical interface for adapting long horizon multi robot collaboration under shared physical constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑