tailieunhanh - A Fuzzy Motion Controller for a Car-Like Vehicle

This explains why we would see large e ects of gasoline price changes on the prices of used cars. What market share e ects should we expect to nd? In used cars, we might expect to see rather small market share e ects for the following reason. An owner of a low fuel e ciency car may wish to respond to an increased gasoline price by selling her current car and replacing it with a high fuel e ciency car. Alas, the price that the owner can obtain for the low fuel e ciency car will have fallen just at the time that she wishes to sell the car or trade. | IN KI A INSTITUT NATIONAL DE RECHERCHE ENINFORMATIQUE ET EN AUTOMATIQUE A Fuzzy Motion Controller for a Car-Like Vehicle Philippe Garnier and Thierry Fraichard N 3200 June 25 1997 __ THEME 3 _ ISSN 0249-6399 Ỉ NR. IẠ RHÒNE-ALPES A Fuzzy Motion Controller for a Car-Like Vehicle Philippe Garnier and Thierry Fraichard Theme 3 Interaction homme-machine images données connaissances Projet Sharp Rapport de recherche n 3200 June 25 1997 32 pages Abstract this paper describes an execution monitor EM it is the key component of a motion control architecture for a vehicle moving in a dynamic and partially known environment. EM endows the vehicle with the reactive capabilities required in an uncertain environment. Its purpose is to generate the commands for the servo-systems of the vehicle so as to follow a given nominal trajectory while reacting in real-time to unexpected events. EM is designed as a fuzzy controller . a control system based upon fuzzy logic thus permitting approximate reasoning and a human-like description of the vehicle s reactive behaviour. The main components of EM are an inference engine and a set of linguistic rules . The global behaviour of the vehicle results from the combination of several basic behaviours trajectory following obstacle avoidance etc. each of which is encoded by a specific set of rules. EM differs from classical fuzzy controllers in two novel ways first it introduces a new defuzzification technique the Barycentre of the Centres Of Area that permits to better take into account the influence of each and every rule. Second weighing coefficients are attached to the rules thus permitting a fine tuning of the influence of each basic behaviour. Furthermore it is shown how supervised learning . learning through samples can be used to automate the determination of these weights thus suppressing the ever delicate problem of finding such coefficients the identification problem . EM has been implemented and tested on an electric