Generating Oscillation Activity with Echo State Network to Mimic the Behavior of a Simple Central Pattern Generator

TL;DR

This paper demonstrates that a modified Echo State Network can autonomously generate oscillatory activity mimicking biological central pattern generators, with potential applications in bio-inspired robotics.

Contribution

It introduces a novel method for using ESNs to produce autonomous oscillations without external input, enhancing bio-inspired control strategies.

Findings

ESN can generate stable oscillations autonomously

Adjustments to network parameters increase oscillation likelihood

The approach enables bio-inspired robotic control

Abstract

This paper presents a method for reproducing a simple central pattern generator (CPG) using a modified Echo State Network (ESN). Conventionally, the dynamical reservoir needs to be damped to stabilize and preserve memory. However, we find that a reservoir that develops oscillatory activity without any external excitation can mimic the behaviour of a simple CPG in biological systems. We define the specific neuron ensemble required for generating oscillations in the reservoir and demonstrate how adjustments to the leaking rate, spectral radius, topology, and population size can increase the probability of reproducing these oscillations. The results of the experiments, conducted on the time series simulation tasks, demonstrate that the ESN is able to generate the desired waveform without any input. This approach offers a promising solution for the development of bio-inspired controllers for robotic systems.