Motion planning in unknown environment using an interval fuzzy type-2 and neural network classifier

This paper describes environmental recognition and motion control using weightless neural network classifier and interval type-2 fuzzy logic controller. The weightless neural network classifies geometric feature such as U-shape, corridor and left or right corner using ultrasonic sensors. The neural network utilizes previous sensor data and analyzes the situation of the current environment. The behavior of mobile robot is implemented by means of fuzzy control rules. Based on the performance criteria the quality of controller is evaluated to make navigation decisions. This functionality is demonstrated on a mobile robot using modular platform and containing several microcontrollers implies the implementation of a robust architecture. The proposed architecture implemented using low cost range sensor and low cost microprocessor. The experiment results show that the mobile robot can recognize the current environment and was able to successfully avoid obstacle in real time.