Design of a Cross-obstacle Neural Network Controller using Running Error Calibration

An obstacle avoidance method for a mobile robot is proposed in this paper. Our research was focused on the obstacles that can be found indoors since a robot is usually used within a building. It is necessary that the robot maintain the desired direction after successfully avoiding the obstacles to achieve a good autonomous navigation performance for the specified project mission. Sensors such as laser, ultrasound, and PSD (Position Sensitive Detector) can be used to detect and analyze the obstacles. A PSD sensor was used to detect and measure the height and width of the obstacles on the floor. The PSD sensor was carefully calibrated before measuring the obstacles to achieve better accuracy. Data obtained from the repeated experiments were used to plot an error graph which was fitted to a polynomial curve. The polynomial equation was used to navigate the robot. We also obtained a direction-error model of the robot after avoiding the obstacles. The prototypes for the obstacle and direction-error were modeled using a neural network whose inputs are the obstacle height, robot speed, direction of the wheels, and the error in direction. A mobile robot operated by a notebook computer was setup and the proposed algorithm was used to navigate the robot and avoid the obstacles. The results showed that our algorithm performed very well during the experiments.