A FUZZY SYSTEM TO CONTROL MULTI-ROBOT FORMATIONS USING COMPUTER VISION

L. Payá, O. Reinoso, M. Ballesta, A. Gil, M.A. Vicente
Departamento de Ingeniería de Sistemas Industriales
Miguel Hernández University
Ed. Torreblanca 03202 Elche (Alicante) Spain
E-mail {lpaya, o.reinoso, arturo.gil, suni}@umh.es

Keywords:Multi-robot systems, computer vision, formations behaviours, control schemas, fuzzy logic

Abstract: The necessity of carrying out complex tasks in variable environments has promoted the development of new robotics approaches, such as collaborative robotics. This way, multi-robot systems have become a very attractive field of research. This paper presents a behaviour-based method for multi-robot formations, using computer vision. A team of robots must follow a leader one, keeping a relative distance and orientation, and avoiding the possible collision with the obstacles. A very robust computer vision technique has been used for the localization of the leader robot using the images of the camera that each robot carries on its top. The final control has been built through the combination of several single behaviours using fuzzy locig. These algorithms have been tested over a team of WiFiBot robots with excellent results