# Evolving Multi-Objective Neural Network Controllers for Robot Swarms

arXiv: https://arxiv.org/abs/2307.14237 · HTML: https://mlsanity.com/paper/2307.14237/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 39 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 5 of 5)

- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks](https://mlsanity.com/paper/1903.10527/) (2019)
- [Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges](https://mlsanity.com/paper/2006.05415/) (2020)
- [Importance mixing: Improving sample reuse in evolutionary policy search methods](https://mlsanity.com/paper/1808.05832/) (2018)
- [DOTS: An Open Testbed for Industrial Swarm Robotic Solutions](https://mlsanity.com/paper/2203.13809/) (2022)

## Built on by (most cited first, 1 of 1)

- [Robust Quadruped Locomotion via Evolutionary Reinforcement Learning](https://mlsanity.com/paper/2604.07224/) (2026)

## Abstract (arXiv)

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.