A throttle and brake fuzzy controller: Towards the automatic car

Trabajo presentado en la International Conference on Computer Aided Systems Theory (EUROCAST 2003), celebrada en Las Palmas de Gran Canaria (España), del 24 al 28 de febrero de 2003It is known that the techniques under the topic of Soft Computing have a strong capability of learning and cognition, as well as a good tolerance to uncertainty and imprecision. Due to these properties they can be applied successfully to Intelligent Vehicle Systems. In particular Fuzzy Logic is very adequate to build qualitative (or linguistic) models, of many kinds of systems without an extensive knowledge of their mathematical models. The throttle and brake pedal and steering wheel, are the most important actuators for driving. The aim of this paper is to integrate in a qualitative model the vehicle operation and the driver behavior in such a way that an unmanned guiding system can be developed around it [1] [2]. The automation of both pedals permits to direct the speed control from a computer and so, to automate several driving functions such as speed adaption, emergency brake, optimum speed selection, safe headway maintenance, etc. The building and design of fuzzy controllers for automatic driving is based on the drivers' know-how and experience and the study of their behavior in maneuvers. The use of fuzzy controllers allows achieving a human like vehicle operation. The results of this research show a good performance of fuzzy controllers that behave in a very human way, adding the precision data from a DGPS source, and the safety of a driver without human lacks such as tiredness, sensorial defects or aggressive standings