arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.23408cs.ROcs.CV
收藏

解开机器人操作策略中动作空间设计的谜团

Demystifying Action Space Design for Robotic Manipulation Policies

Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学);Shanghai AI Lab(上海人工智能实验室);Peking University(北京大学)

Yuchun Feng, Jinliang Zheng, Zhihao Wang, Dongxiu Liu, Jianxiong Li, Jiangmiao Pang, Tai Wang, Xianyuan Zhan

AI总结:

本文通过大规模实验研究,揭示动作空间设计对机器人策略学习的显著影响,分析了时间与空间轴上的动作设计对策略可学习性和控制稳定性的影响。

摘要:

动作空间的定义在基于模仿的机器人操作策略学习中起着关键作用,深刻影响着策略学习的优化景观。尽管近期进展主要集中在扩大训练数据和模型容量上,但动作空间的选择仍依赖于随意的启发式方法或遗留设计,导致对机器人策略设计哲学的理解模糊。为了解决这种模糊性,我们进行了大规模和系统的经验研究,证实动作空间对机器人策略学习有显著而复杂的影响。我们沿着时间和空间轴解剖动作设计空间,从而对这些选择如何指导策略的可学习性和控制稳定性进行结构化分析。基于13000多个真实世界滚动和在四个场景中500多个训练模型的评估,我们研究了绝对与delta表示以及关节空间与任务空间参数化之间的权衡。我们的大规模结果表明,适当设计策略以预测delta动作能一致提高性能,而关节空间和任务空间表示分别提供了互补的优势,分别有利于控制稳定性和泛化能力。

英文摘要:

The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling training data and model capacity, the choice of action space remains guided by ad-hoc heuristics or legacy designs, leading to an ambiguous understanding of robotic policy design philosophies. To address this ambiguity, we conducted a large-scale and systematic empirical study, confirming that the action space does have significant and complex impacts on robotic policy learning. We dissect the action design space along temporal and spatial axes, facilitating a structured analysis of how these choices govern both policy learnability and control stability. Based on 13,000+ real-world rollouts on a bimanual robot and evaluation on 500+ trained models over four scenarios, we examine the trade-offs between absolute vs. delta representations, and joint-space vs. task-space parameterizations. Our large-scale results suggest that properly designing the policy to predict delta actions consistently improves performance, while joint-space and task-space representations offer complementary strengths, favoring control stability and generalization, respectively.

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。

↑