用统一抓取工具让不同机器人共享操作技能，实现跨机体模仿学习。
LEGATO: Cross-Embodiment Imitation Using a Grasping Tool
- 设计手持抓取器统一线性动作与观测空间，使任务定义一致。
- 在模拟和真实机器人上成功实现多种机器人间的视觉运动技能迁移。
- 适合研究跨机器人泛化、低成本机器人技能复用的团队使用。
跨机体模仿学习使在特定机器人上训练的策略能够迁移到不同机器人上，从而实现大规模、低成本且高可复用的模仿学习。本文提出LEGATO框架，实现不同运动学形态机器人之间的视觉运动技能迁移。引入一种手持抓取器，统一动作与观测空间，使任务在不同机器人间保持一致。通过模仿学习，在该抓取器上对任务示范进行训练，并将动作映射到运动不变空间以计算训练损失。策略生成的抓取器运动通过逆运动学重定向为高自由度全身动作，部署于多样化的机器人平台上。仿真和真实机器人实验均验证了该框架在跨机器人学习与迁移视觉运动技能方面的有效性。更多信息请见项目页面：https://ut-hcrl.github.io/LEGATO。
原文摘要 · Abstract (English)
Cross-embodiment imitation learning enables policies trained on specific embodiments to transfer across different robots, unlocking the potential for large-scale imitation learning that is both cost-effective and highly reusable. This paper presents LEGATO, a cross-embodiment imitation learning framework for visuomotor skill transfer across varied kinematic morphologies. We introduce a handheld gripper that unifies action and observation spaces, allowing tasks to be defined consistently across robots. We train visuomotor policies on task demonstrations using this gripper through imitation learning, applying transformation to a motion-invariant space for computing the training loss. Gripper motions generated by the policies are retargeted into high-degree-of-freedom whole-body motions using inverse kinematics for deployment across diverse embodiments. Our evaluations in simulation and real-robot experiments highlight the framework's effectiveness in learning and transferring visuomotor skills across various robots. More information can be found on the project page: https://ut-hcrl.github.io/LEGATO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。