Adaptive Body Schema Learning System Considering Additional Muscles for Musculoskeletal Humanoids

TL;DR

An overall system of muscle addition for musculoskeletal humanoids and the adaptive body schema learning while taking into account the additional muscles is described and a method that can learn the changes in body schema associated with additional muscles from a small amount of motion data is described.

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.

Figures (11)

• Figure 1: The concept of the entire system of adaptive body schema learning considering muscle addition.
• Figure 2: The basic musculoskeletal structure.
• Figure 3: The hardware design considering muscle addition.
• Figure 4: The adaptive body schema learning system considering additional muscles.
• Figure 5: The old and new designs of muscle arrangement for the experiment of a simple 1-DOF tendon-driven robot simulation.