Suet Lee and Sabine Hauert, Towards Fault Mitigation in a Robot Swarm Using Neuroevolution, in ICRA 2023 - Workshop on Robot Execution Failures and Failure Management Strategies
Abstract: As robot swarms are increasingly deployed in the real-world, making them safe will be critical for improving adoption and trust. A robot swarm is composed of many individual robots each susceptible to failure at any given time, which may decrease the performance of the swarm as a whole. The ability to mitigate such faults is therefore necessary. The difficulty with designing a good mitigation strategy lies in the complexity of the swarm as a system, where individual interactions give rise to emergent behaviour. In this paper, we aim to learn a mitigation strategy using neuroevolution in a fault-discriminatory metric space. We demonstrate the strategy in a realistic intralogistics use-case.
More Information
