Evolving Multi-Objective Neural Network Controllers for Robot Swarms

TL;DR

This paper introduces a multi-objective evolutionary neural network method for developing scalable robot swarm controllers, successfully transferring from low to high-fidelity simulations and adjusting behaviors via objective weighting.

Contribution

It presents a novel approach combining multi-objective evolution and neural networks for scalable, transferable robot swarm control in high-fidelity environments.

Findings

Controllers effectively manage robot behaviors

Controllers transfer from low to high-fidelity simulations

Scalable to larger robot swarms without retraining

Abstract

Many swarm robotics tasks consist of multiple conflicting objectives. This research proposes a multi-objective evolutionary neural network approach to developing controllers for swarms of robots. The swarm robot controllers are trained in a low-fidelity Python simulator and then tested in a high-fidelity simulated environment using Webots. Simulations are then conducted to test the scalability of the evolved multi-objective robot controllers to environments with a larger number of robots. The results presented demonstrate that the proposed approach can effectively control each of the robots. The robot swarm exhibits different behaviours as the weighting for each objective is adjusted. The results also confirm that multi-objective neural network controllers evolved in a low-fidelity simulator can be transferred to high-fidelity simulated environments and that the controllers can scale to environments with a larger number of robots without further retraining needed.