Adaptive Body Schema Learning System Considering Additional Muscles for Musculoskeletal Humanoids

TL;DR

This paper presents a system for adaptive body schema learning in musculoskeletal humanoids that incorporates additional muscles, enabling improved performance in high-load tasks through modular hardware and efficient software learning methods.

Contribution

It introduces a modular hardware design and a novel software learning method for adapting body schema with extra muscles in musculoskeletal humanoids.

Findings

Effective muscle tension relaxation with added muscles for high-load tasks

Successful application to a 1-DOF robot simulation and humanoid arm

Adaptive learning from small motion datasets

Abstract

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.