1 Fuzzy Parking Manoeuvres of Wheeled Mobile Robots Amar KHOUKHI, Luc BARON and Marek BALAZINSKI Department of Mechanical Engineering, École Polytechnique of Montreal P. O. box. 6079, Succ. CV, Montreal, Quebec, Canada H3C 3A7 amar.khoukhi@polymtl.ca , luc.baron@polymtl.ca , marek.balazinski@polymtl.ca Abstract - This work deals with the parking manoeuvres problem for a wheeled mobile robot (WMR). The robot has the same non-holonomic kinematic constraint that has a car vehicle. This constraint makes the robot having its direction always tangent to the trajectory. Two sub-cases of parking problems are considered. These are forward and backward maneuvers, aiming to stabilize the robot at a pre-specified pose. The environment is assumed to be known, obstacle-free and a local map of the area is already done by prior processing the information obtained from ultrasonic sensors mounted on the robot. A linguistic fuzzy model to represent the robot and its environment is developed. From this model, the parking manoeuvres are carried out by mimicking a human car driver using a fuzzy control system. Upon simulation tests this approach has been proved efficient giving very encouraging results. Index Terms - Mobile Robot, Non-Holonomy, Parking Manoeuvres, Fuzzy Planning I. INTRODUCTION In recent years, autonomous parking problems of wheeled mobile robots (WMR) have attracted a great deal of attention from robotics research community and automobile industry [1- 3]. In robotics literature, a tremendous amount of research has been published in the last decade on the topic [4, 5]. In the automotive industry, an intensive research is carried out for the development of intelligent automobiles that can make the driving procedure easier and more secure [6, 7]. Many government organizations and laboratories pursue advanced researches on this topic [8-10]. Indeed, the parking problem has a wider range of applications. It is used to automate service procedures like the loading and unloading of warehouses, or the transfer of disabled persons, and can also be used to assist the mooring of ships to docks. Basically, the parking problem consists of placing the vehicle in parallel to its moving direction in a confined space that is very little wider than the vehicle's dimensions. Many researchers have examined the garage parking and parallel-parking schemes. Most of these researches have been concentrated on tracking and pose stabilization methods. The Manuscript received May 5, 2007. This work was supported by the Natural Science and Engineering Research Council of Canada (NSERC), under grants ES D3-317622, RGPIN-203618, RGPIN-105518 and STPGP-269579. tracking method is to design a control algorithm that makes a wheeled mobile robot (WMR) follow a reference trajectory. The pose stabilization method is to stabilize the WMR to a desired final pose, while starting from a given initial pose [5- 8]. From kinematics point of view, parking is merely a path- planning problem, in which a collision-free path between initial and final poses should be found, while meeting the non- holonomic constraint. Hence, many continues-curvature path planners using geometric methods have been proposed, which generate feasible paths that are followed by implementing a path tracking technique. In these methods, the trajectory planner should be combined with a controller capable of tracking the nominal trajectory. For instance, in [12] an optimal open-loop steering approach had been considered using sinusoidal trajectory parameterization. Generally speaking, the kinematics equations of a car with non-holonomic constraints are nonlinear and time-varying differential equations. It is almost impossible to find an auto- driver, who uses a traditional control method to manoeuvre the car to perform parking. Nonetheless, a human driver can smoothly and even perfectly park a car into a garage or parking zone by some simple rules without the knowledge of the motion kinematics of the automobile. Indeed, consider the behaviour of a human driver; according to available space, one of the following cases may occur: If the parking spot is not enough; the driver cannot park and decides for no parking. If the space is just sufficient, the driver decides to make a couple of back-drive or head-in manoeuvres. If there is a large enough space; he decides for a forward parking. Therefore, beside geometric based path planners, several soft-computing [7, 11, 13], especially fuzzy logic based- approaches were proposed to solve the parking problem by emulating experience of human drivers. As a matter of fact, most advanced control algorithms in autonomous mobile robots can benefit from fuzzy logic control. Among these works [7, 11], one can find that about half the parking problems are solved using fuzzy control (FC) systems In this framework, an intelligent parking using vision is proposed in [14], where a color segmentation method is developed based on neural networks. They apply quintic polynomials and symmetric pose to provide good results in local path planning for automatic parking behaviours. Another parking motion planning architecture based on a radial basis