Fuzzy control to drive car-like vehicles

The reactive component of a motion control architecture for a car-like vehi cle intended to move in dynamic and partially known environments is present ed in this paper. It is called the execution monitor (EM). The purpose of E M is to generate commands for the servo-systems of the vehicle so as to fol low a given nominal trajectory while reacting in real time to unexpected ev ents. EM is designed as a fuzzy controller. i.e. a control system based upo n fuzzy logic, whose main component is a set of fuzzy rules encoding the re active behaviour of the vehicle. A behaviour-based approach is used to set up the fuzzy rule base: the overall behaviour of the vehicle results from t he combination of several basic behaviours (trajectory following, obstacle avoidance, etc.), each of which is encoded by a specific set of rules. This approach permits an easy and incremental construction of the fuzzy rule ba se and also to develop and rest the basic behaviours separately. It is the fuzzy control mechanism that straightforwardly handles the problems of beha viour arbitration and command fusion. The basic behaviour rules are simply obtained through direct encoding of the human expertise about car driving. In addition, weighing coefficients are attached to the rules thus permittin g a fine tuning of the influence of each basic behaviour. EM has been imple mented and tested on a real computer-controlled car, equipped with sensors of limited precision and reliability. Experimental results obtained with th e prototype vehicle are presented. They demonstrate the capability of EM to actually control a real vehicle and to perform trajectory following and ob stacle avoidance in real outdoor environments by using simple fuzzy behavio urs relying upon low-resolution sensor data. (C) 2001 Elsevier Science B.V. All rights reserved.