Learning of Balance Controller Considering Changes in Body State for Musculoskeletal Humanoids

TL;DR

This paper introduces an online adaptive learning method for balance control in musculoskeletal humanoids, modeling joint-muscle dynamics and adapting to body state changes for improved stability.

Contribution

It proposes a novel correlation model with parametric bias for online adaptation to body state variations in musculoskeletal humanoids.

Findings

Model successfully adapts to changes in footwear and joint calibration.

Simulation and real humanoid experiments validate the effectiveness.

Enhanced balance stability compared to traditional PID control.

Abstract

The musculoskeletal humanoid is difficult to modelize due to the flexibility and redundancy of its body, whose state can change over time, and so balance control of its legs is challenging. There are some cases where ordinary PID controls may cause instability. In this study, to solve these problems, we propose a method of learning a correlation model among the joint angle, muscle tension, and muscle length of the ankle and the zero moment point to perform balance control. In addition, information on the changing body state is embedded in the model using parametric bias, and the model estimates and adapts to the current body state by learning this information online. This makes it possible to adapt to changes in upper body posture that are not directly taken into account in the model, since it is difficult to learn the complete dynamics of the whole body considering the amount of data and computation. The model can also adapt to changes in body state, such as the change in footwear and change in the joint origin due to recalibration. The effectiveness of this method is verified by a simulation and by using an actual musculoskeletal humanoid, Musashi.