The Effect of Changing-Lane Prediction Algorithms on the Performance of ACC System Model in Matlab/Simulink

Self-driving vehicles are capturing the attention of numerous researchers, companies, and car enthusiasts. The automation of vehicles varies across multiple levels, depending on the tasks they perform and the techniques they employ. The Adaptive Cruise Control (ACC) system is an automated vehicle at the first level. It checks the presence of other vehicles in its lane to adapt its velocity accordingly or maintain a constant speed. However, it does not include lane-changing capabilities. Nevertheless, the presence of other neighboring vehicles can affect the performance of the ACC based Model Predictive Controller (MPC) system, leading to discomfort or collisions. In this paper, we will provide a brief description of the ACC system and the MPC controller. Subsequently, we will discuss the challenges that affect the performance of the ACC based MPC system and propose potential solutions using the Variable Time Headway (VTH) strategy or changing-lane prediction algorithms, such as Random Forest (RF), K- Nearest Neighbor (KNN) and Support Vector Machine (SVM). Simulation results of applying these methods to a sufficiently dangerous driving scenario will be illustrated, followed by a brief conclusion.