A NEURAL MACHINE VISION MODEL FOR ROAD DETECTION IN AUTONOMOUS NAVIGATION

This paper presents an original approach for visual identification of road direction in autonomous vehicle navigation using a neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author. For comparison, we also evaluate the performances of three other usual classifiers. The path to be identified has been quantized in three output directions: straight ahead, left and right. We present the experimental results obtained by computer simulation (using a data set of 210 road images from the CMU VASC Image Database), as well as a real-time neural path follower based on CSOM model, implemented on a mobile robot (car toy).