arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.15262cs.ROcs.AI
收藏

基于学习的对称双臂操作自适应柔顺方法

A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation

Beijing Institute of Control Engineering(北京控制工程研究所);Tsinghua University(清华大学);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);City University of Hong Kong(香港城市大学);Qian Xuesen Laboratory of Space Technology(钱学森空间技术实验室);Beijing Aerospace Automatic Control Institute(北京航天自动控制研究所)

Yuxue Cao, Wenbo Zhao, Shengjie Wang, Xiang Zheng, Wenke Ma, Zhaolei Wang, Tao Zhang

AI总结:

针对对称双臂操作中运动规划与柔顺控制分离导致效率低、适应性差的问题,提出基于学习的自适应柔顺算法(LAC),统一轨迹生成与阻抗调整,并用集中式Actor-Critic与LSTM增强同步性,在插孔装配实验中优于基线。

摘要:

对称双臂操作因其强大的负载能力,是在轨操作中的一项基本技能。以往的工作应用柔顺控制来维持操作的稳定性。然而,传统方法将运动规划和柔顺控制视为两个独立的模块,这可能导致在存在外力和干扰时,期望轨迹和阻抗参数的同时变化产生冲突。此外,这两个模块的联合使用需要专家手动调整参数。为了在提高适应性的同时实现高效率,我们提出了一种新颖的基于学习的自适应柔顺算法(LAC),该算法提高了对称双臂操作的效率和鲁棒性。具体而言,该算法框架将期望轨迹生成和阻抗参数调整集成在一个统一框架下,以缓解矛盾并提高效率。其次,我们引入了一个集中式Actor-Critic框架,其中LSTM网络预处理力状态,增强了双臂操作的同步性。在双臂插孔装配实验中评估时,我们的方法在最优性和鲁棒性方面优于基线算法。

英文摘要:

Symmetric bi-manual manipulation is an essential skill in on-orbit operations due to its potent load capacity. Previous works have applied compliant control to maintain the stability of manipulations. However, traditional methods have viewed motion planning and compliant control as two separate modules, which can lead to conflicts with the simultaneous change of the desired trajectory and impedance parameters in the presence of external forces and disturbances. Additionally, the joint usage of these two modules requires experts to manually adjust parameters. To achieve high efficiency while enhancing adaptability, we propose a novel Learning-based Adaptive Compliance algorithm (LAC) that improves the efficiency and robustness of symmetric bi-manual manipulation. Specifically, the algorithm framework integrates desired trajectory generation and impedance-parameter adjustment under a unified framework to mitigate contradictions and improve efficiency. Second, we introduce a centralized Actor-Critic framework with LSTM networks preprocessing the force states, enhancing the synchronization of bi-manual manipulation. When evaluated in dual-arm peg-in-hole assembly experiments, our method outperforms baseline algorithms in terms of optimality and robustness.

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。

↑