arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.13457cs.ROcs.LG
收藏

面向协调机器人运动:转换树上运动策略的端到端学习

Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees

Georgia Institute of Technology(佐治亚理工学院);University of Washington(华盛顿大学);NVIDIA Research(英伟达研究院)

M. Asif Rana, Anqi Li, Dieter Fox, Sonia Chernova, Byron Boots, Nathan Ratliff

摘要:

由于机器人所施加的几何约束,生成同时完成多个任务的机器人运动是具有挑战性的。在本文中,我们提出了解决多任务问题,通过学习结构化的政策,从人类的示范。我们的结构化策略受到RMPflow的启发,RMPflow是一个用于在不同空间上组合子任务策略的框架。策略结构为用户提供了一个界面,用于1)指定与任务完成直接相关的空间,以及2)为不需要学习的某些任务设计策略。我们推导出一个适合于多任务问题的端到端学习目标函数,强调任务空间上的运动偏差。此外,从学习的策略类生成的运动被保证是稳定的。我们验证了我们提出的学习框架的有效性,通过定性和定量评估三个机器人任务上的7自由度Rethink Sawyer机器人。

英文摘要:

Generating robot motion that fulfills multiple tasks simultaneously is challenging due to the geometric constraints imposed by the robot. In this paper, we propose to solve multi-task problems through learning structured policies from human demonstrations. Our structured policy is inspired by RMPflow, a framework for combining subtask policies on different spaces. The policy structure provides the user an interface to 1) specifying the spaces that are directly relevant to the completion of the tasks, and 2) designing policies for certain tasks that do not need to be learned. We derive an end-to-end learning objective function that is suitable for the multi-task problem, emphasizing the deviation of motions on task spaces. Furthermore, the motion generated from the learned policy class is guaranteed to be stable. We validate the effectiveness of our proposed learning framework through qualitative and quantitative evaluations on three robotic tasks on a 7-DOF Rethink Sawyer robot.

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。

↑