UAV-UGV-UMV Multi-Swarms for Cooperative Surveillance

Daniel H Stolfi; Matthias R Brust; Grégoire Danoy; Pascal Bouvry

doi:10.3389/frobt.2021.616950

UAV-UGV-UMV Multi-Swarms for Cooperative Surveillance

Front Robot AI. 2021 Feb 19:8:616950. doi: 10.3389/frobt.2021.616950. eCollection 2021.

Authors

Daniel H Stolfi¹, Matthias R Brust¹, Grégoire Danoy^{1

2}, Pascal Bouvry^{1

2}

Affiliations

¹ Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg.
² FSTM/DCS, University of Luxembourg, Esch-sur-Alzette, Luxembourg.

Abstract

In this paper we present a surveillance system for early detection of escapers from a restricted area based on a new swarming mobility model called CROMM-MS (Chaotic Rössler Mobility Model for Multi-Swarms). CROMM-MS is designed for controlling the trajectories of heterogeneous multi-swarms of aerial, ground and marine unmanned vehicles with important features such as prioritising early detections and success rate. A new Competitive Coevolutionary Genetic Algorithm (CompCGA) is proposed to optimise the vehicles' parameters and escapers' evasion ability using a predator-prey approach. Our results show that CROMM-MS is not only viable for surveillance tasks but also that its results are competitive in regard to the state-of-the-art approaches.

Keywords: UAV; UGV; UMV; competitive coevolutionary genetic algorithm; mobility model; parameter optimisation; surveillance system; swarm robotics.