Research On Automatic Car Backing Controller Based On The Fuzzy Theory

With the development of automobile industry and the improvement of people's living standards, the number of car has increased year by year; the problem of car backing has got widespread attention. In order to solve this problem fundamentally, the only way is to realize automatic car backing system which makes the entire car backing process complete automatically and intelligently. In order to achieve this goal, this paper has studied the automatic car backing controller which is the most crucial part of the automatic car backing system.The paper, firstly, has conducted the research to the automatic car backing control algorithm. On the basis of studing and researching on the theory of fuzzy control, we have designed multi-dimensional fuzzy controller which can avoid the problem of "dead zone" in the process of car backing when the car controlled by the traditional two-dimensional fuzzy controller. Simultaneously, we have programmed the simulation program with VC++ to carry the simulation on the designed multi-dimensional fuzzy controller. In order to improve the control precision of the multi-demensional fuzzy controller, we have designed trimming controller based on the theory of variable universe fuzzy control, and embedded it in multi-dimensional fuzzy controller, the resoult of simulation show that control precision can be improved largely. Furthermore, the paper has integrated fuzzy control theory with artificial potential field theory, and designed an obstacle avoidance controller which is embedded in the designed multi-dimensional fuzzy controller, then to avoid obstacle in real-time during car backing has been realized.On the basis of the research of automatic control algorithm, the paper also studied how to realize the automatic car backing controller on ARM+μC/OS- II platform and the method to realize the controller in the form of IC, We have designed the general structure of the control chip and defined the interface of each component module, we studied the implementation method for the main component module simultaneously. Additionally, the paper built an experimental platform to test control effcet of the designed controller. In order to solve the positioning problem of experimental car, we proposed an positioning method which is based on infrared, this method has many advantages, such as high positioning accuracy, low cost, easy to realize etc., and can solve positioning problem of all kind of mobile robots and intelligent vehicles in the experimental stage.Finally, the paper summarized the achievement through analyzing the result of experiment, and proposed some problems that remaining to be solved, which pointed out the direction for future research.