AGV fuzzy control optimized by genetic algorithms

Abstract

Automated Guided Vehicles (AGV) are an essential element of transport in industry 4.0. Although they may seem simple systems in terms of their kinematics, their dynamics is very complex, and it requires robust and efficient controllers for their routes in the workspaces. In this paper, we present the design and implementation of an intelligent controller of a hybrid AGV based on fuzzy logic. In addition, genetic algorithms have been used to optimize the speed control strategy, aiming at improving efficiency and saving energy. The control architecture includes a fuzzy controller for trajectory tracking that has been enhanced with genetic algorithms. The cost function first maximizes the time in the circuit and then minimizes the guiding error. It has been validated on the mathematical model of a commercial hybrid AGV that merges tricycle and differential robot components. This model not only considers the kinematics and dynamics equations of the vehicle but also the impact of friction. The performance of the intelligent control strategy is compared with an optimized PID controller. Four paths were simulated to test the approach validity.