具有隐式动作的跨形态机器人基础世界模型

中文摘要 AI 辅助

机器人形态与动作空间的多样性，使得构建能跨不同形态泛化的机器人世界模型颇具挑战。我们提出了隐式动作条件机器人世界模型（LAC-WM），该模型在跨不同形态学习得到的统一隐式动作空间中运行。这种统一动作空间提升了世界模型适配此前未见过的机器人形态时的性能。我们将LAC-WM与显式动作条件世界模型（EAC-WM，以显式运动标签为条件）进行对比。结果显示，显式动作条件会导致不同形态间的动作表征不相交，限制了其适配新机器人时的下游性能。我们在灵巧操作任务及修改后的LIBERO基准上评估了两种模型。LAC-WM在灵巧操作任务上的下游性能较EAC-WM提升最高达46.7%，在LIBERO基准上提升11.7%。关键的是，统一隐式动作空间使LAC-WM的下游性能随预训练所用形态数量增加而正向扩展；相比之下，EAC-WM的不相交动作空间会导致其性能随预训练形态数量增加而下降。这些结果凸显了统一动作空间对高效跨形态学习的重要性，解决了机器人领域的一项关键挑战。项目网站：this https URL

英文摘要

The diversity of robot embodiments and action spaces makes it challenging to build robot world models that generalize across different embodiments. We introduce the Latent Action-Conditioned Robot World Model (LAC-WM), which operates within a learned unified latent action space shared across diverse embodiments. This unified action space improves the world model's performance when adapted to previously unseen robot embodiments. We compare LAC-WM with an Explicit Action-Conditioned World Model (EAC-WM), which conditions on explicit motion labels. Our results show that explicit action conditioning leads to disjoint action representations across embodiments, limiting downstream performance when adapting to new robots. We evaluate both models on dexterous manipulation tasks and a modified LIBERO benchmark. LAC-WM improves downstream performance over EAC-WM by up to 46.7% on dexterous manipulation and 11.7% on LIBERO. Crucially, the unified latent action space allows LAC-WM's downstream performance to scale positively with the number of embodiments used during pretraining. In contrast, the disjoint action space in EAC-WM leads to decreased performance as the number of pretraining embodiments increases. These results highlight the importance of a unified action space for efficient cross-embodiment learning, addressing a key challenge in robotics. Project website: https://lacwm.github.io/

发表机构

• Stanford University（斯坦福大学）
• Meta FAIR Robotics（Meta FAIR 机器人学部门）

机构由 AI 辅助整理，请以论文原文为准。