Anticipation-Based Autonomous Platoon Control Strategy with Minimum Parameter Learning Adaptive Radial Basis Function Neural Network Sliding Mode Control

This article investigates the headway and optimal velocity tracking of autonomous vehicles (AVs), considering their predictive driving for the stability and integrity of spatial vehicle formation in the platoon. First, the human-like anticipation car-following model is used for modeling the autonomous system. Second, an adaptive radial basis function neural network (ARBF-NN)-based sliding mode control (SMC) is proposed for the control purpose. The control objective is to regulate traffic perturbation during entire road operations. To enable the controller to experience less computational burden and adaptation complexity, a minimum parameter learning (MPL) has also been integrated with ARBF-NN-based SMC. Third, an illustrative simulation example has been performed for two scenarios, i.e., constant headway and time-varying headway of vehicles. A performance comparison between the proposed controller and the conventional SMC was conducted, and controller parameter sensitivity was also carried out. The simulation results show that the proposed controller is an effective and ingenious method for platoon system control compared to the conventional sliding mode controller. Parameter sensitivity analysis shows that only three parameters need greater attention for maximum convergence rate and disturbance attenuation. The parameters c, ƞ, and k can alter the responses of the vehicles.