Environment induced emergence of collective behaviour in evolving swarms with limited sensing
Fuda van Diggelen (1), Jie Luo (1), Tugay Alperen Karag\"uzel (1),, Nicolas Cambier, Eliseo Ferrante, A.E. Eiben

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDistributed Control Multi-Agent Systems · Modular Robots and Swarm Intelligence · Reinforcement Learning in Robotics
