Suet Lee and Sabine Hauert, Heterogeneity of Faults in a Robot Swarm: Identifying Discriminatory Metrics, in ICRA 2023 - Heterogeneity in Multi-Robot Systems Workshop
Abstract: Robot swarms operating in real-world conditions will experience a variety of faults, essentially making the swarm heterogeneous over the lifetime of its operations. Our previous work presented a method to identify metrics which can discriminate effectively between normal and faulty states of a robot in the swarm. Here we present our approach to faulty state discrimination through the lens of measuring diversity: can diversity be evaluated through discrimination of states of a system, and can we identify discriminatory metrics to apply to real-time diversity evaluation?
Download Document-
Next Publication
Towards Fault Mitigation in a Robot Swarm Using Neuroevolution -
Previous Publication
Gaussian Belief Propagation for Distributed Swarm Sensing - View All Publications
