A TRANSPORTABLE NEURAL-NETWORK APPROACH TO AUTONOMOUS VEHICLE FOLLOWING

This paper presents the development and testing of a neural-network mo dule for autonomous vehicle following. Autonomous vehicle following is defined as a vehicle changing its own steering and speed while follow ing a lead vehicle. The strength of the developed controller is that n o characterization of the vehicle dynamics is needed to achieve autono mous operation. As a result, it can be transported to any vehicle rega rdless of the nonlinear and often unobservable dynamics. Data for the range and heading angle of the lead vehicle were collected for various paths while a human driver performed the vehicle following control fu nction. The data was collected for different driving maneuvers includi ng straight paths, lane changing, and right/left turns. Two time-delay backpropagation neural networks were then trained based on the data c ollected under manual control-one network for speed control and the ot her for steering control, After training, live vehicle following runs were done under the neural-network control. The results obtained indic ate that it is feasible to employ neural networks to perform autonomou s vehicle following.