Deep Learning Based Model Identification System Exploits the Modular Structure of a Bio-Inspired Posture Control Model for Humans and Humanoids
This work addresses the problem of identifying parameters for human posture control models, which is relevant for researchers in biomechanics and robotics, but the abstract does not provide specific quantitative gains.
This paper introduces a system identification procedure utilizing Convolutional Neural Networks (CNNs) to identify parameters for the DEC parametric model of human posture control. The modular design of the control model allowed for a modular identification procedure, where a single neural network identified parameters across different degrees of freedom.
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