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 2302.09450cs.ROcs.AIcs.SYeess.SY
收藏

通过强化学习实现稳健且多功能的双足跳跃控制

Robust and Versatile Bipedal Jumping Control through Reinforcement Learning

University of California, Berkeley(加州大学伯克利分校);Simon Fraser University(西蒙弗雷泽大学);Université de Montréal(蒙特利尔大学);Mila(米拉人工智能研究所)

Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath

AI总结:

本文提出一种强化学习框架与多阶段训练方案,结合长短期I/O历史策略结构,使双足Cassie机器人能够在现实世界中稳健完成立定跳远、跳上高台及多轴跳跃等多种动态跳跃任务。

摘要:

本工作旨在通过使力矩控制的双足机器人在现实世界中执行稳健且多功能的动态跳跃,推动双足机器人敏捷性的极限。我们提出了一种强化学习框架,用于训练机器人完成多种跳跃任务,例如跳向不同位置和方向。为了提高这些具有挑战性任务的表现,我们开发了一种新的策略结构,该结构编码机器人的长期输入/输出(I/O)历史,同时提供对短期I/O历史的直接访问。为了训练多功能的跳跃策略,我们采用了一种多阶段训练方案,该方案包含针对不同目标的不同训练阶段。经过多阶段训练后,该策略可以直接迁移到真实的双足Cassie机器人上。在不同任务上训练并探索更多样化的场景,可以产生高度稳健的策略,这些策略能够利用所学的多样化动作库,在现实世界部署期间从扰动或不良着陆中恢复。所提策略中的这种稳健性使Cassie能够在现实世界中成功完成各种具有挑战性的跳跃任务,例如立定跳远、跳上高台以及多轴跳跃。

英文摘要:

This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a robot to accomplish a large variety of jumping tasks, such as jumping to different locations and directions. To improve performance on these challenging tasks, we develop a new policy structure that encodes the robot's long-term input/output (I/O) history while also providing direct access to a short-term I/O history. In order to train a versatile jumping policy, we utilize a multi-stage training scheme that includes different training stages for different objectives. After multi-stage training, the policy can be directly transferred to a real bipedal Cassie robot. Training on different tasks and exploring more diverse scenarios lead to highly robust policies that can exploit the diverse set of learned maneuvers to recover from perturbations or poor landings during real-world deployment. Such robustness in the proposed policy enables Cassie to succeed in completing a variety of challenging jump tasks in the real world, such as standing long jumps, jumping onto elevated platforms, and multi-axes jumps.

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。

↑