Research on Traffic Vehicle Behavior Prediction Method Based on Game Theory and HMM

Abstract

Traffic vehicle behavior prediction is a necessary prerequisite for intelligent vehicle behavior decision and trajectory planning. The behaviors of vehicles are deeply interactive. In order to reasonably predict the future behavior of traffic vehicles, based on the Game theory, this paper designs the behavior prediction framework of traffic vehicles, and establishes the GMM(Gaussian Mixture Model)-HMM(Hidden Markov Model) behavior recognition model. Then, the revenue function is designed to model the driver's intent by calculating the vehicle's front running space, collision risk and comfort loss under each scenario. And the NGSIM dataset is used to train the parameters in the GMM-HMM model and those in the revenue function. Finally, two groups of experiments are designed to compare this method with the traditional method. The experimental results show that the proposed method can predict the future behavior of traffic vehicles earlier, and can also well reflect the interaction process of vehicle behavior, and has better robustness.