COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS

As a result of terrorist attacks in the last years; new efforts have raised trying to solve challenges related to security task automation using robotic platforms. In this paper we present the results of a cooperative multi-robot approach for infrastructure security applications at critical facilities. We formulate our problem using a M. Pac-Mac like environment. In this implementation, multiple robotic agents define policies with the objective to increase the number of explored states in a grid world. This is through the application of the off-policy learning algorithm from reinforcement learning area, known as Q-learning. We validate experimentally our approach with a group of agents learning a patrol task and we present results obtained in simulated environments.