Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation
Neural and Evolutionary Computing
2020-11-04 v2 Artificial Intelligence
Robotics
Abstract
In this paper, we propose SwarmNet -- a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Tested on artificially generated swarm motion data, the network achieves high levels of prediction accuracy and imitation authenticity. We compare our model to previous approaches for modelling interaction systems and show how modifying components of other models gradually approaches the performance of ours. Finally, we also discuss an extension of SwarmNet that can deal with nondeterministic, noisy, and uncertain environments, as often found in robotics applications.
Cite
@article{arxiv.1912.02811,
title = {Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation},
author = {Siyu Zhou and Mariano Phielipp and Jorge A. Sefair and Sara I. Walker and Heni Ben Amor},
journal= {arXiv preprint arXiv:1912.02811},
year = {2020}
}