arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.19795cs.RO
收藏

Duke Humanoid:利用被动动力学实现节能双足运动的设计与控制

The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive Dynamics

Duke University(杜克大学)

Boxi Xia, Bokuan Li, Jacob Lee, Michael Scutari, Boyuan Chen

AI总结:

本文介绍开源10自由度人形机器人 Duke Humanoid,并通过利用被动动力学的端到端强化学习实现可零样本部署的节能行走,真实世界运输成本降低31%。

摘要:

我们提出了 Duke Humanoid,这是一个具有10个自由度的开源人形机器人,作为运动研究的可扩展平台。其设计模仿人类生理结构,在额状面采用对称身体对齐方式,以在膝盖伸直时保持静态平衡。我们开发了一种强化学习策略,可零样本部署到硬件上,用于速度跟踪行走任务。此外,为提高运动中的能效,我们提出了一种端到端强化学习算法,鼓励机器人利用被动动力学。实验结果表明,我们的被动策略在仿真中将运输成本降低了最高50%,在真实世界测试中降低了31%。我们的网站是 http://generalroboticslab.com/DukeHumanoidv1/ 。

英文摘要:

We present the Duke Humanoid, an open-source 10-degrees-of-freedom humanoid, as an extensible platform for locomotion research. The design mimics human physiology, with symmetrical body alignment in the frontal plane to maintain static balance with straight knees. We develop a reinforcement learning policy that can be deployed zero-shot on the hardware for velocity-tracking walking tasks. Additionally, to enhance energy efficiency in locomotion, we propose an end-to-end reinforcement learning algorithm that encourages the robot to leverage passive dynamics. Our experimental results show that our passive policy reduces the cost of transport by up to $50\%$ in simulation and $31\%$ in real-world tests. Our website is http://generalroboticslab.com/DukeHumanoidv1/ .

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。

↑