Lane-Changing Strategy Based on a Novel Sliding Mode Control Approach for Connected Automated Vehicles

Safe and efficient autonomous lane changing is a key step of connected automated vehicles (CAVs), which can greatly reduce the traffic accident rate relieve pressure. Aiming at requirements smoothness efficiency lane-changing trajectory CAVs, it necessary to design controller integrate sensing, decision-making, control tasks in driving process. Firstly, based on vehicle dynamics model, this paper proposes strategy NNTSMC method (neural network enhanced non-singular fast terminal sliding mode control). The designed well realize path tracking, both lateral position yaw angle track expected value. This enables front wheel steering intelligently, acceleration during changes small scope, ensures stability vehicle. In study, an improved adaptive RBF neural with bounded mapping estimate upper bound total disturbance system, effectively reduces chattering phenomenon force. Lyapunov function constructed study proves that ensure controlled system. Finally, comparative experiment performed by MATLAB/Simulink-CarSim co-simulation. Compared SMC TSMC (non-singular control), proposed has performance improvement least 58.0% 34.1%, respectively. effectiveness superiority were confirmed experiments co-simulation platform.