Driving Style Recognition under Connected Circumstance Using a Supervised Hierarchical Bayesian Model

Depeng Chen,Mingyang Zhang,Yishi Zhang,Xu Qu,Chaozhong Wu,Zhijun Chen,Tomio Miwa

doi:10.1155/2021/6687378

Abstract

In recent years, the automated driving system has been known to be one of the most popular research topics of artificial intelligence (AI) and intelligent transportation system (ITS). The journey experience on automated vehicles and the intelligent automated driving system could be improved by individualization driving understanding. Although previous studies have proposed methods for driving styles understanding, the individualization driving classification has not been addressed thoroughly. Therefore, in this study, a supervised method is proposed to understand driving behavioral structure and the latent driving styles by incorporating the prior knowledge. Firstly, a novel method is established for driving behavioral encoding and raw driving data mining. Then, the Labeled Latent Dirichlet Allocation (LLDA) is proposed to understand the latent driving styles from individual driving with driving behaviors. Finally, the Safety Pilot Model Deployment (SPMD) data are used to validate the performance of the proposed model. Experimental results show that the proposed model uncovers latent driving styles effectively and shows good agreement to real situations, which provides theoretical guidance on driving behavior recognition for better individual experience on automated driving vehicles.

Highlights

Automated vehicle technology has been developing rapidly and has been applied in public life in some cities
Methodology e Latent Dirichlet Allocation (LDA) model is a successful topic discovery model to analyze the text in words, which is good at uncovering the latent topics under documents, consisted of words [7]
En, the driving styles of drivers are described as a mixture driving style distribution for individualization driving of drivers, which are based on the supervised labeled LDA model and given prior knowledge

Summary

Introduction

Automated vehicle technology has been developing rapidly and has been applied in public life in some cities. Automated vehicles, such as automated taxis and automated shared cars, can offer services for people’s daily commute. When approaching a slow-speed car (i.e., the red one), a driver with the moderate driving style (i.e., the blue one in the right-hand side of Figure 1, hereafter called the moderate driver) often tends to follow the front car instead of changing lane and overtaking. Analyzing and understanding the different driving styles of heterogeneous drivers automatically can help reduce the mismatch ratio for the passenger-driver pairs, in such a way as to enhance passenger satisfaction

Methods

Results

Conclusion