Evolution of central pattern generators for the control of a five-link bipedal walking mechanism

TL;DR

This paper introduces an evolutionary algorithm to optimize central pattern generators for controlling a five-link bipedal robot, demonstrating successful transfer from simulation to real hardware and highlighting the potential of biologically inspired models for legged locomotion.

Contribution

It presents a novel evolutionary approach to design CPG networks for bipedal robots, addressing the lack of generic design principles in the field.

Findings

Evolved CPG networks successfully control the robot in simulation.

Transfer of evolved networks from simulation to real robot is feasible.

Diverse network configurations can achieve effective locomotion.

Abstract

Central pattern generators (CPGs), with a basis is neurophysiological studies, are a type of neural network for the generation of rhythmic motion. While CPGs are being increasingly used in robot control, most applications are hand-tuned for a specific task and it is acknowledged in the field that generic methods and design principles for creating individual networks for a given task are lacking. This study presents an approach where the connectivity and oscillatory parameters of a CPG network are determined by an evolutionary algorithm with fitness evaluations in a realistic simulation with accurate physics. We apply this technique to a five-link planar walking mechanism to demonstrate its feasibility and performance. In addition, to see whether results from simulation can be acceptably transferred to real robot hardware, the best evolved CPG network is also tested on a real mechanism. Our results also confirm that the biologically inspired CPG model is well suited for legged locomotion, since a diverse manifestation of networks have been observed to succeed in fitness simulations during evolution.