Visual trajectory control of a mobile robot using FPGA implemented neural network

Abstract

In the paper hardware implemented artificial neural network used for trajectory control of a mobile robot is presented. As a controller RBF (Radial Basis Function) type hardware implemented artificial neural network has been used. There are presented the structure of the neural network implemented on an FPGA system, the main modules of the system, the on chip training.As a robot, a mobile robot with three wheels has been chosen. The left and right side wheels are driven by DC motors and the third one is a free-wheel. The robot position is determined from the image sequence captured by a camera. Finally, measurement results based on the robot model and on the real system will be presented.