Event-triggered adaptive neural network asymptotic tracking control of intelligent vehicles with composite learning

Benefitted from composite learning, the proposed scheme takes on the better neural learning and less control conservativeness than the existing adaptive asymptotic control approaches. This paper opens the avenue to address the high-precision tracking of nonlinear intelligent vehicles by guaranteeing the asymptotic stability. Taking the advantage of ETC, the proposed scheme separately reduces the communication burden in the different controller-to-actuator channels compared with the continuous control work.