Machine Learning applied to the Patrol Route Planning for Autonomous Robots
Applied Computational Intelligence, Patrol Robots, Intelligent Robots, Intelligent Control, Reinforcement Learning
Research on intelligent and autonomous mobile robots has grown significantly due to its military, civil and industrial applications, such as the monitoring of agricultural plantations, the use in actions to support environmental disasters, the border patrol, the mapping of submarine territories or even the study of animal behavior. In this context, many researchers and designers characterize their robots as intelligent or autonomous systems uncritically without the theoretical commitment that justifies such qualities. This work rescues the artificial intelligence multi and interdisciplinary motivation, starting from philosophical questions to the intelligent and autonomous systems characterization. Thus, only after building the theoretical bases for these agents conception, a bioinspired approach is proposed for the patrol trajectory elaboration of an intelligent robot. For this purpose, reinforcement learning algorithms are introduced that determine the route to be followed by the feedback linearization control strategy combined with artificial neural networks.