A Multi-robot System for Patrolling Task via Stochastic Fictitious Play

Abstract: A great deal of work has been done in recent years on the multi-robot patrolling problem. In such problem a team of robots is engaged to supervise an infrastructure. Commonly, the patrolling tasks are performed with the objective of visiting a set of points of interest. This problem has been solved in the literature by developing deterministic and centralized solutions, which perform better than decentralized and non-deterministic approaches in almost all cases. However, deterministic methods are not suitable for security purpose due to their predictability. This work provides a new decentralized and non-deterministic approach based on the model of Game Theory called Stochastic Fictitious Play (SFP) to perform security tasks at critical facilities. Moreover, a detailed study aims at providing additional insight of this learning model into the multi-robot patrolling context is presented. Finally, the approach developed in this work is analyzed and compared with other methods proposed in the literature by utilizing a patrolling simulator.