An improved approach to beacons detection for a mobile robot using a neural network

In this paper we propose a neuro-mimetic technique relating to the detection of beacons in mobile robotics. The objective is to bring a robot moving i an unspecified environment to acquire attribute s for recognition. We develop a practical approach for t he segmentation of images of objects of a scene and evaluate the performances in real time of them. The neurona l classifier used is a window of a network MLP (9-6 -3-1) using the Algorithm of retro-propagation of the gra dient, where the distributed central pixel uses inf ormation in level of gray. The originality of the work lies in the use of the association of an enhanced neural n etwork configuration and Standard Hough Transform. The res ults obtained with a momentum of 0.03 and one coeff ici nt of training equal to 0.002 shows that our system is robust with an extremely appreciable computing tim e. ¶