Adaptive Speed Control of Autonomous Vehicle under Changing Operation Conditions

The common PID controller with fixed parameters is difficult to control the speed of autonomous vehicle under changing operation conditions, thus a indirect single neuron adaptive PID controller based on quadratic criterion is put forward in this paper. The output error and control increment are assigned to be performance indexs in the learning algorithm. In order to further restrain the control increment and reduce the influence of measurement error, the controller proposed in this paper is changed into indirect structure. A method, which is based on identification model of vehicle and simulation experiment, to obtain the initial parameters of the controller, is presented in this paper. Furthermore, this paper uses a miniature autonomous vehicle to test the performance of the controller.