Neural Networks Based on Information Fusion Using for Avoiding Obstacle Robot

Abstract

The paper describes an indoor autonomous wheel robot which could move safely in an obstacle environment. The environment may involve any number of arbitrary shape and size obstacles, and the path may be very complex. We describe an approach to solving the motion-planning for mobile robot control by using neural networks based on information fusion technique. In the article, the physics model of the mobile robot was set up, and the sensors used in the avoiding obstacle of the mobile robot were selected. As the indoor environment information couldn’t be exact by single sensor, we proposed that using a multi-sensor system for the mobile robot avoiding obstacle. At last, we selected multiple ultrasonic sensors and infrared sensors. In order to predigest the calculation, the measurement data are to be classified and selected. The fuzzy neuron network information fusion based on the T-S model is used to avoid obstacle for the mobile robot, which fully utilized the information coming from the sensors. Finally, the experiment with the autonomous robot proved that the method is really feasible and efficient.