Real time implementation of CTRNN and BPTT algorithm to learn on-line biped robot balance: Experiments on the standing posture

TL;DR

This paper presents a real-time neural network control system using CTRNN and BPTT for balancing a biped robot, demonstrating effective on-line learning and disturbance compensation in standing posture.

Contribution

It introduces a real-time implementation of CTRNN and BPTT algorithms for on-line control of a biped robot, which is a novel application in robot balance management.

Findings

Effective disturbance compensation achieved

Real-time learning demonstrated on embedded hardware

Improved balance control performance

Abstract

This paper describes experimental results regarding the real time implementation of continuous time recurrent neural networks (CTRNN) and the dynamic back-propagation through time (BPTT) algorithm for the on-line learning control laws. Experiments are carried out to control the balance of a biped robot prototype in its standing posture. The neural controller is trained to compensate for external perturbations by controlling the torso's joint motions. Algorithms are embedded in the real time electronic unit of the robot. On-line learning implementations are presented in detail. The results on learning behavior and control performance demonstrate the strength and the efficiency of the proposed approach.