发表机构
National Institute of Advanced Industrial Science and Technology (AIST); Institute of Science Tokyo; The University of Tokyo（国立产业技术综合研究所（AIST）; 东京科学大学; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究探索利用单机器人遥操作数据实现大规模多机器人协调推箱，发现被动观察难以获取有效协调，并揭示了多机器人研究的瓶颈。
AI 中文摘要
多机器人模仿学习，特别是在无通信、机载分布式的视觉运动策略部署场景中，代表了一种有吸引力的范式。然而，其实现仍未被充分理解，主要原因是收集集体示范的困难，因为单个操作员无法同时控制多个机器人。与此同时，与耦合的协作操作不同，许多协调任务主要通过最小化机器人间的干扰来实现系统级效率。这种结构促使我们研究由遥操作的单机器人收集的数据是否可用于大规模协调推箱任务作为测试平台。我们系统地研究了数据集创建策略和轻量级策略架构。特别是，多达40个机器人的实验突显了仅通过被动观察其他运行中的机器人来获取有效协调的困难，揭示了多机器人研究的一个具体瓶颈。
英文摘要
Multi-robot imitation learning, particularly in settings where visuomotor policies are deployed in a communication-free, onboard decentralised style, represents an attractive paradigm. However, its realisation remains insufficiently understood, largely due to the difficulty of collecting collective demonstrations, since a single operator cannot control many robots simultaneously. Meanwhile, unlike coupled collaborative manipulation, many coordinated tasks achieve system-wide efficiency primarily through minimising inter-robot interference. This structure motivates us to study whether data collected by a teleoperated single-robot can be leveraged for large-scale coordinated box-pushing as a testbed. We systematically investigate dataset creation strategies and lightweight policy architectures. In particular, experiments with up to 40 robots highlight the difficulty of acquiring effective coordination solely through passive observation of other operating robots, revealing a concrete bottleneck for multi-robot research.
Comments15 pages, 8 figures. Accepted for presentation at the 2026 Conference on Robot Learning (CoRL 2026)
