Backpropagation through Soft Body: Investigating Information Processing in Brain-Body Coupling Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tomioka, Hiroki, Inoue, Katsuma, Kuniyoshi, Yasuo, Nakajima, Kohei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916646535299072
author Tomioka, Hiroki
Inoue, Katsuma
Kuniyoshi, Yasuo
Nakajima, Kohei
author_facet Tomioka, Hiroki
Inoue, Katsuma
Kuniyoshi, Yasuo
Nakajima, Kohei
contents Animals achieve sophisticated behavioral control through dynamic coupling of the brain, body, and environment. Accordingly, the co-design approach, in which both the controllers and the physical properties are optimized simultaneously, has been suggested for generating refined agents without designing each component separately. In this study, we aim to reveal how the function of the information processing is distributed between brains and bodies while applying the co-design approach. Using a framework called ``backpropagation through soft body," we developed agents to perform specified tasks and analyzed their mechanisms. The tasks included classification and corresponding behavioral association, nonlinear dynamical system emulation, and autonomous behavioral generation. In each case, our analyses revealed reciprocal relationships between the brains and bodies. In addition, we show that optimized brain functionalities can be embedded into bodies using physical reservoir computing techniques. Our results pave the way for efficient designs of brain--body coupling systems.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05601
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Backpropagation through Soft Body: Investigating Information Processing in Brain-Body Coupling Systems
Tomioka, Hiroki
Inoue, Katsuma
Kuniyoshi, Yasuo
Nakajima, Kohei
Neural and Evolutionary Computing
Animals achieve sophisticated behavioral control through dynamic coupling of the brain, body, and environment. Accordingly, the co-design approach, in which both the controllers and the physical properties are optimized simultaneously, has been suggested for generating refined agents without designing each component separately. In this study, we aim to reveal how the function of the information processing is distributed between brains and bodies while applying the co-design approach. Using a framework called ``backpropagation through soft body," we developed agents to perform specified tasks and analyzed their mechanisms. The tasks included classification and corresponding behavioral association, nonlinear dynamical system emulation, and autonomous behavioral generation. In each case, our analyses revealed reciprocal relationships between the brains and bodies. In addition, we show that optimized brain functionalities can be embedded into bodies using physical reservoir computing techniques. Our results pave the way for efficient designs of brain--body coupling systems.
title Backpropagation through Soft Body: Investigating Information Processing in Brain-Body Coupling Systems
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2503.05601