A navigation system based on fuzzy logic control is developed for a mobile robot working in an unknown environment. The structure of this fuzzy navigation system features the combination of a sensor system, fuzzy logic controller and motion control system. Ten ultrasonic sensors on-board the vehicle are used for distance measurement to the immediate obstacles. Sensor data are fuzzified to be the input of the fuzzy logic controllers. Three states, each with five quantized levels, are used to define the fuzzy set. Two fuzzy logic controllers are designed to handle the navigation problem in a two-dimensional plane. The outputs are the commanding velocities sent to the lower level motion control system. The performance of the controller was tested firstly by computer simulation. It was found that the performance of the newly designed fuzzy logic controllers was not acceptable and some heuristic virtual concepts were added to enhance the navigation capability. Practical implementation on an experimental mobile robot has been carried out to demonstrate the navigation capability. Satisfactory results have been obtained and are presented in this article.
|Number of pages||12|
|Journal||Proceedings of the National Science Council, Republic of China, Part A: Physical Science and Engineering|
|State||Published - 1 Jul 1994|