Utilisation des réseaux de neurones artificiels pour la commande d'un véhicule autonome. (Artificial Neural Networks for Automatic Vehicle Control)

The subject of this thesis covers both mobile robotic and arti cial neural networks(ANN) elds. Our aim is to study solutions that connectionist techniques can bring to particularproblems raised by the automatic control of a car-like vehicle. This report is composed of two mainparts. The rst of them processes fundamental aspects of mobile robot control and of the use ofarti cial neural networks for control of complex systems. This rst study allows us to underline thedi erent points where ANN can contribute in a control architecture providing a real autonomy to thevehicle while respecting the robustness and rapidity constraints induced by the utilisation of a robot ofthe size and the speed of a car. We propose in the second part of this report several controllers allowinggradual increase of the robot autonomy. First of all, we are interested in a simple task consisting onlyin enslaving the robot on a reference path given by a planner. Our approach enables a continuousadaptation of the system facing possible changes of the parameters of the robot or its environment.So as to allow the execution of manoeuvres without external orders, we also propose a methodologyfor the realisation of controllers based on external sensors of the vehicle. Our approach uses a modelallying characteristics from both fuzzy logic and ANN. Finally we show how complex tasks can berealised using a sequence of several simple controllers. Our realisation of the selection system for thesecontrollers, which uses a recurrent ANN, exhibits some characteristics of robustness and very fastreactions when faced to the external events that must be taken into account.