arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02608cs.ROcs.AIcs.CVcs.LGcs.MA
收藏

学习分散式多臂运动规划器

Learning a Decentralized Multi-arm Motion Planner

Columbia University(哥伦比亚大学)

Huy Ha, Jingxi Xu, Shuran Song

摘要:

我们提出了一个闭环多臂运动规划,是可扩展的和灵活的团队规模。传统的多臂机器人系统依赖于集中式运动规划器,其运行时间通常随团队规模呈指数级增长,因此无法用开环控制来处理动态环境。在本文中,我们解决这个问题与多智能体强化学习,其中分散的政策是训练控制一个机器人手臂在多臂系统中,以达到其目标末端执行器姿态给定的观察其工作空间状态和目标末端执行器姿态。该策略使用具有来自基于采样的运动规划算法(即,BiRRT)。通过利用经典的规划算法,我们可以提高强化学习算法的学习效率,同时保持神经网络的快速推理时间。由此产生的政策规模次线性,可以部署在多臂系统与可变的团队规模。由于闭环和分散的公式化,我们的方法可以推广到5-10个多臂系统和动态移动目标(10臂系统的成功率>90%),尽管我们只训练了1-4个静态目标的臂规划任务。代码和数据链路可在https://multiarm.cs.columbia.edu上找到。

英文摘要:

We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robot systems have relied on centralized motion planners, whose runtimes often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a decentralized policy is trained to control one robot arm in the multi-arm system to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is trained using Soft Actor-Critic with expert demonstrations from a sampling-based motion planning algorithm (i.e., BiRRT). By leveraging classical planning algorithms, we can improve the learning efficiency of the reinforcement learning algorithm while retaining the fast inference time of neural networks. The resulting policy scales sub-linearly and can be deployed on multi-arm systems with variable team sizes. Thanks to the closed-loop and decentralized formulation, our approach generalizes to 5-10 multi-arm systems and dynamic moving targets (>90% success rate for a 10-arm system), despite being trained on only 1-4 arm planning tasks with static targets. Code and data links can be found at https://multiarm.cs.columbia.edu.

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。

↑