Coevolutionary Optimization of a Fuzzy Logic Controller for Antilock Braking Systems Under Changing Road Conditions

An anti-lock brake system based on fuzzy logic has been developed and optimized to cope with changes in adherence road conditions. Conventional control systems have to be tuned by conducting simulations and tests on different surfaces before putting them into use. This way, large amounts of computational and testing times are required. The main objective of this work is to propose a methodology to simplify the process of obtaining a controller for antilock brake systems through a combination of optimization and simulation. To this end, an evolutionary algorithm based on the coevolution of two species has been used to tune the proposed fuzzy logic controller. The controller evolves competitively with the environment to optimize its response to different adherence conditions. Finally, the optimized controller has been implemented in a real motorcycle to compare its performance with a conventional system.