Adaptive Event-Trigged Control for Intelligent Connected Vehicles Systems with Collision Avoidance

This study proposes a robust adaptive neural network asymptotic tracking control for a third-order heterogeneous vehicle platoon system with input saturation. In order to reduce the waste of communication resources and unnecessary data transmission, an event triggering mechanism is constructed. An auxiliary design system-integrated control scheme is devised to tackle the input saturation issue, and utilizing the radial basis function neural network (RBFNN) to approximate the unspecified nonlinear function. Combining the auxiliary system and triggering mechanism, an adaptive NN asymptotic tracking control scheme is developed. Through the barrier Lyapunov functions, the developed control scheme ensures the spacing error asymptotically converges to zero, and both string and individual stabilities can be proved. In addition, the collisions can be avoided. Comprehensive numerical simulations validate the efficacy of the proposed control approach. Finally, numerical simulations validate the effectiveness of our control approach.