arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.22355cs.ROcs.AI
收藏

基于人类演示的动态异构图学习面向目标的双手揉面操作

Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration

The Chinese University of Hong Kong(香港中文大学);T-Stone Robotics Institute(T-Stone机器人研究所);Idiap Research Institute(伊迪亚普研究所)

Junjia Liu, Chenzui Li, Shixiong Wang, Zhipeng Dong, Sylvain Calinon, Miao Li, Fei Chen

AI总结:

针对机器人软物体操作的状态表征与策略学习难题,提出基于动态异构图的目标导向软物体操作策略学习模型,结合人类演示引导学习,经揉面任务仿真与真机实验及消融验证,实现更优的类人操作效果。

摘要:

软物体操作为机器人带来了重大挑战,需要有效的状态表征与操作策略学习技术。状态表征涉及捕捉环境中的动态变化,而操作策略学习侧重于建立机器人动作与状态转换之间的关联,以实现特定目标。为应对这些挑战,本研究提出了一种新方法:基于动态异构图的模型,用于学习面向目标的软物体操作策略。该模型将图作为状态表征与策略学习的统一形式,借助动态图可提取关于物体动力学与操作策略的关键信息,此外该模型还支持整合演示数据,实现有引导的策略学习。为评估方法的有效性,我们设计了揉面任务,分别在可微模拟器与真实人形机器人上开展实验,并通过多项消融实验分析了方法的作用,证明其在实现类人行为方面的优越性。

英文摘要:

Soft object manipulation poses significant challenges for robots, requiring effective techniques for state representation and manipulation policy learning. State representation involves capturing the dynamic changes in the environment, while manipulation policy learning focuses on establishing the relationship between robot actions and state transformations to achieve specific goals. To address these challenges, this research paper introduces a novel approach: a dynamic heterogeneous graph-based model for learning goal-oriented soft object manipulation policies. The proposed model utilizes graphs as a unified representation for both states and policy learning. By leveraging the dynamic graph, we can extract crucial information regarding object dynamics and manipulation policies. Furthermore, the model facilitates the integration of demonstrations, enabling guided policy learning. To evaluate the efficacy of our approach, we designed a dough rolling task and conducted experiments using both a differentiable simulator and a real-world humanoid robot. Additionally, several ablation studies were performed to analyze the effect of our method, demonstrating its superiority in achieving human-like behavior.

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。

↑