Deep Learning Based Model Identification System Exploits the Modular Structure of a Bio-Inspired Posture Control Model for Humans and Humanoids

TL;DR

This paper introduces a CNN-based system identification method for human posture control that leverages the modular structure of a bio-inspired model, enabling efficient parameter estimation across multiple degrees of freedom.

Contribution

It proposes a novel modular neural network approach for identifying parameters of a bio-inspired posture control model, improving efficiency and scalability.

Findings

Effective identification of control parameters from body sway data

Utilization of modular CNN architecture for multi-DOF systems

Demonstrated applicability to external stimulus-induced sway

Abstract

This work presents a system identification procedure based on Convolutional Neural Networks (CNN) for human posture control using the DEC (Disturbance Estimation and Compensation) parametric model. The modular structure of the proposed control model inspired the design of a modular identification procedure, in the sense that the same neural network is used to identify the parameters of the modules controlling different degrees of freedom. In this way the presented examples of body sway induced by external stimuli provide several training samples at once