Environment induced emergence of collective behaviour in evolving swarms with limited sensing

TL;DR

This paper demonstrates that evolutionary algorithms can develop effective controllers for robot swarms with limited sensing, leading to emergent collective behaviors that adapt to environmental challenges.

Contribution

It introduces an evolutionary approach to design controllers for swarms with limited sensing, showing emergent behaviors and scalability across different environments.

Findings

Evolved controllers successfully guided swarm to follow environmental gradients.

Solutions from harsh conditions exhibited higher flexibility.

Emergent collective motion was observed without explicit programming.

Abstract

Designing controllers for robot swarms is challenging, because human developers have typically no good understanding of the link between the details of a controller that governs individual robots and the swarm behavior that is an indirect result of the interactions between swarm members and the environment. In this paper we investigate whether an evolutionary approach can mitigate this problem. We consider a very challenging task where robots with limited sensing and communication abilities must follow the gradient of an environmental feature and use Differential Evolution to evolve a neural network controller for simulated robots. We conduct a systematic study to measure the flexibility and scalability of the method by varying the size of the arena and number of robots in the swarm. The experiments confirm the feasibility of our approach, the evolved robot controllers induced swarm behavior that solved the task. We found that solutions evolved under the harshest conditions (where the environmental clues were the weakest) were the most flexible and that there is a sweet spot regarding the swarm size. Furthermore, we observed collective motion of the swarm, showcasing truly emergent behavior that was not represented in- and selected for during evolution.