Intent Recognition Based on Gaussian Mixture and Lane Change Decision Control for Intelligent Vehicles

The accurate recognition and prediction of the surrounding vehicles’ driving intentions play a critical role in enabling intelligent vehicles to make informed decisions, thereby providing passengers with a safer and more comfortable ride. Therefore, it is essential to propose a method for intent recognition that can determine the driving intent of surrounding vehicles, serving as a key reference for decision-making and controlling the host vehicle’s driving behavior. In this paper, a driving simulator platform is used to replicate real-world driving behavior, capturing vehicle trajectories and dynamic parameters, and generating experimental datasets. An intent detection module, based on a Gaussian Mixture Model (GMM), is proposed to detect the driving intent of surrounding vehicles. Additionally, a finite state machine is introduced to facilitate decision-making in intelligent vehicles based on the current driving state and recognized driving intent. A fifth-degree polynomial-based trajectory planning method is then proposed for lane changing, aiming to select the optimal trajectory. Finally, Model Predictive Control (MPC) and PID control are employed to manage the host vehicle’s motion in the lateral and longitudinal directions, respectively. The effectiveness of the proposed system is demonstrated through simulation results, which show its capability in recognizing surrounding vehicles’ driving intentions and enabling decision-making and control based on both vehicle state and driving intent. The research findings offer valuable insights and practical guidance for intent recognition and decision control in real-world traffic environments.