Abstract—Automatic Vehicle Driving (known as AVD) involves several issues, such as the capability to follow the road and keep the right lane, to maintain the distance between vehicles, to regulate vehicle speed or to find the shortest route to a destination. In this paper a real-time automatic lane-keeper is proposed. The main features of the system are the lane markers location process as well as the computation of the vehicle steering lock. A Multilayer Perceptron is designed for this purpose which has been implemented using the Xilinx Spartan 3. For real-time processing of road scenes, an open source software for car racing games is used. The required processing time is 0.33ms per frame; so that the system can process 3 frames/sec. steering angle accuracy is computed with an average error of 1.2 degree which shows an acceptable result.

Index Terms—FPGA, neural networks, automatic vehicle DRIVING

Aida Farahani is with Department of Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran (e-mail: hex41434@ieee.org).
Behnam Ghiaseddin is with the K. N. Toosi University of Tech, Department of Mechanical Engineering, Tehran, Iran (e-mail: behnam@ghiaseddin.com).

Cite: A. Farahani and B. Ghiaseddin, "Implementation of an Automatic Vehicle Driving System on a Single FPGA Chip," International Journal of Computer and Electrical Engineering vol. 4, no. 6, pp. 875-877, 2012.