Visual navigation of a vehicle along roads: the algorithm and experiments

This paper is concerned with preview lateral control of an automated vehicle with a machine vision system. The lateral control is found with road edges captured by the machine vision so as to drive a vehicle along a road. The road edges are expressed in the machine vision system as two series of sampled points, and the optimal path is designed with the series of the sampled points, which enables the vehicle to drive safely and comfortably. Experiments with an automated guided vehicle (AGV) have been conducted, where the control period is about 0.5 sec and the vehicle drives at 0.3 m/sec. The results show the feasibility of the algorithm