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

Sumin Zhang,Jianping Li,Rui He,Yongshuai Zhi

doi:10.1109/access.2020.2971705

Sumin Zhang, Jianping Li + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2971705

Copy DOI

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.

Highlights

The development of intelligent automobile technology has greatly improved traffic safety, social progress and the efficiency and quality of people’s daily travel
Vehicle is the main body of traffic behavior, and the motion prediction of traffic vehicle expresses the understanding of the future dynamic change of traffic environment, which is a necessary prerequisite for the behavior decision-making and trajectory planning of intelligent vehicles
Abstract the functions of these two modules, we can get the following definition: (1) vehicle behavior recognition module, the probability distribution of the observed vehicle is estimated by the data obtained from the on-board sensor, in this paper, a behavior recognition method based on Gaussian Mixture Hidden Markov Model (GMM-HMM) is used

Summary

INTRODUCTION

The development of intelligent automobile technology has greatly improved traffic safety, social progress and the efficiency and quality of people’s daily travel. S. Zhang et al.: Research on Traffic Vehicle Behavior Prediction Method Based on Game Theory and HMM and Hu et al represent this measure through the Euclidean distance between trajectory points [6]. Abstract the functions of these two modules, we can get the following definition: (1) vehicle behavior recognition module, the probability distribution of the observed vehicle is estimated by the data obtained from the on-board sensor, in this paper, a behavior recognition method based on Gaussian Mixture Hidden Markov Model (GMM-HMM) is used.

MODEL TRAINING

REVENUE FUNCTION DESIGN AND CALIBRATION

COLLISION RISK INDE

DESIGN AND VERIFICATION OF EXPERIMENTS

Findings

CONCLUSION