arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.02407cs.RO
收藏

基于强化学习的可推动物体间局部路径规划

Local Path Planning among Pushable Objects based on Reinforcement Learning

University College London(伦敦大学学院)

Linghong Yao, Valerio Modugno, Andromachi Maria Delfaki, Yuanchang Liu, Danail Stoyanov, Dimitrios Kanoulas

AI总结:

本文提出基于强化学习的局部路径规划方法,通过多智能体训练和优势演员-评论家算法,实现可推动物体间的灵活避障,并在仿真和四足机器人上验证了其适应性。

摘要:

本文提出了一种方法来解决机器人在可推动物体间的局部路径规划问题——这是机器人学中的一个开放性问题。具体而言,我们通过在基于物理的仿真环境中同时训练多个智能体来实现这一目标,并采用了优势演员-评论家算法结合深度神经网络。所开发的在线策略使这些智能体能够以不限于轴向对齐的方式推动障碍物,即时适应障碍物动态中的意外变化,并有效应对狭窄区域内的局部路径规划。我们在多种仿真环境中测试了该方法,以证明其在陌生环境中对各种未见场景的适应有效性。此外,我们已成功将该策略应用于实际的四足机器人,证实了其处理真实世界传感器相关的不确定性和噪声,以及未探索物体推动任务中固有不确定性的能力。

英文摘要:

In this paper, we introduce a method to deal with the problem of robot local path planning among pushable objects -- an open problem in robotics. In particular, we achieve that by training multiple agents simultaneously in a physics-based simulation environment, utilizing an Advantage Actor-Critic algorithm coupled with a deep neural network. The developed online policy enables these agents to push obstacles in ways that are not limited to axial alignments, adapt to unforeseen changes in obstacle dynamics instantaneously, and effectively tackle local path planning in confined areas. We tested the method in various simulated environments to prove the adaptation effectiveness to various unseen scenarios in unfamiliar settings. Moreover, we have successfully applied this policy on an actual quadruped robot, confirming its capability to handle the unpredictability and noise associated with real-world sensors and the inherent uncertainties present in unexplored object pushing tasks.

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。

↑