arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01434cs.ROcs.AI
收藏

基于先验策略指导的双臂漂浮基空间机器人运动规划强化学习

Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot

Beijing Institute of Control Engineering(北京控制工程研究所);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);Tsinghua University(清华大学)

Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Xinru Xie, Lei Liu

摘要:

强化学习方法作为一种很有前途的技术,在自由漂浮空间机器人的运动规划中取得了很好的效果。然而,由于规划维数的增加和系统动力学耦合的加剧,双臂漂浮基空间机器人的运动规划仍然是一个公开的挑战。特别是,目前的研究不能处理的任务,捕获一个非合作的对象,由于缺乏姿态约束的末端执行器。为了解决这个问题,我们提出了一种新的算法,高效LPT,以方便基于RL的方法,以有效地提高规划精度。我们的核心贡献是构造了一个具有先验知识指导的混合策略,并引入了无穷范数来构造一个更合理的奖励函数。此外,我们的方法成功地捕捉到一个旋转的物体具有不同的旋转速度。

英文摘要:

Reinforcement learning methods as a promising technique have achieved superior results in the motion planning of free-floating space robots. However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge. In particular, the current study cannot handle the task of capturing a non-cooperative object due to the lack of the pose constraint of the end-effectors. To address the problem, we propose a novel algorithm, EfficientLPT, to facilitate RL-based methods to improve planning accuracy efficiently. Our core contributions are constructing a mixed policy with prior knowledge guidance and introducing infinite norm to build a more reasonable reward function. Furthermore, our method successfully captures a rotating object with different spinning speeds.

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。

↑