In the paper, a new control algorithm called human simulating control algorithm (HS) is presented. Unlike the traditional methods, the algorithm uses sigmoid function to describe the steering operations of human drivers. Based on this function, HS algorithm is presented. In order to improve the adaptability to different environments, a parameter adaptive adjustment algorithm is presented. This algorithm can adjust the values of the key parameters real time. HS controller is used on a vehicle equipped with a computer vision system and a computer controlled steering actuator system. The results from the experiments show that the vehicle prototype with HS algorithm processed good tracking performance at different vehicle speeds, even up to the speed of 172 km/h.