arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.06322cs.RO
收藏

考虑附加肌肉的肌肉骨骼人形机器人自适应身体图式学习系统

Adaptive Body Schema Learning System Considering Additional Muscles for Musculoskeletal Humanoids

The University of Tokyo(东京大学)

Kento Kawaharazuka, Akihiro Miki, Yasunori Toshimitsu, Kei Okada, Masayuki Inaba

AI总结:

本研究提出一种考虑附加肌肉的肌肉骨骼人形机器人自适应身体图式学习系统,通过模块化硬件和少量数据学习,验证了添加肌肉可有效放松高负荷任务中的肌肉张力。

摘要:

肌肉骨骼人形机器人的一个重要优势在于,其肌肉排列可以轻松改变,并且可以根据情况增加肌肉数量。在本研究中,我们描述了肌肉骨骼人形机器人肌肉添加的整体系统,以及考虑附加肌肉的自适应身体图式学习。在硬件方面,我们描述了一种可安装附加肌肉的模块化身体设计;在软件方面,我们描述了一种能够从少量运动数据中学习与附加肌肉相关的身体图式变化的方法。我们将该方法应用于一个简单的1自由度腱驱动机器人仿真以及肌肉骨骼人形机器人Musashi的手臂,并展示了通过添加肌肉来放松高负荷任务中的肌肉张力的有效性。

英文摘要:

One of the important advantages of musculoskeletal humanoids is that the muscle arrangement can be easily changed and the number of muscles can be increased according to the situation. In this study, we describe an overall system of muscle addition for musculoskeletal humanoids and the adaptive body schema learning while taking into account the additional muscles. For hardware, we describe a modular body design that can be fitted with additional muscles, and for software, we describe a method that can learn the changes in body schema associated with additional muscles from a small amount of motion data. We apply our method to a simple 1-DOF tendon-driven robot simulation and the arm of the musculoskeletal humanoid Musashi, and show the effectiveness of muscle tension relaxation by adding muscles for a high-load task.

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。

↑