Concurrent Bayesian Learners for Multi-Robot Patrolling Missions

Distributed robot systems have been adopted lately for security purposes, such as in automatic multirobot patrolling of infra-structures. Research has shown that deterministic patrol routes can lead to effective performance. However, they can potentially be predicted by intelligent intruders. This work presents a probabilistic multi-robot patrolling strategy, where each autonomous agent uses Bayesian reasoning to decide its moves in the environment. Each member of the team is a learning agent that collects information and assesses the state of the system, using concurrent reinforcement learning to influence future moves. This way, effective coordination in collective patrol is achieved, as shown by preliminary simulation experiments.