Characterization of the Driving Style by State–Action Semantic Plane Based on the Bayesian Nonparametric Approach

Xuqiang Qiao,Yuqing Ren,Zhida Zhang,Lihong Qiu,Ling Zheng,Yinong Li,Ziwei Zhang

doi:10.3390/app11177857

Abstract

The quantification and estimation of the driving style are crucial to improve the safety on the road and the acceptance of drivers with level2–level3(L2–L3) intelligent vehicles. Previous studies have focused on identifying the difference in driving style between categories, without further consideration of the driving behavior frequency, duration proportion properties, and the transition properties between driving style and behaviors. In this paper, a novel methodology to characterize the driving style is proposed by using the State–Action semantic plane based on the Bayesian nonparametric approach, i.e., hierarchical Dirichlet process–hidden semi–Markov model (HDP–HSMM). This method segments the time series driving data into fragment clusters with similar characteristics and construct the State–Action semantic plane based on the statistical characteristics of the state and action layer to label and interpret the fragment clusters. This intuitively and simply visualizes the driving performance of individual drivers, while the risk index of the individual drivers can also be obtained through semantic plane. In addition, according to the joint mutual information maximization (JIMI) approach, seven transition probabilities of driving behaviors are extracted from the semantic plane and applied to identify driving styles of drivers. We found that the aggressive drivers prefer high–risk driving behaviors, and the total duration and frequency of high–risk behaviors are greater than those of cautious and normal drivers. The transition probabilities among high–risk driving behaviors are also greater compared with low–risk behaviors. Moreover, the transition probabilities can provide rich information about driving styles and can improve the classification accuracy of driving styles effectively. Our study has practical significance for the regulation of driving behavior and improvement of road safety and the development of advanced driver assistance systems (ADAS).

Highlights

Better understanding of the variability in individual driving styles would be especially useful for understanding driver preferences, mechanisms for vehicle control, path planning, and for developing more realistic traffic simulations [1,2] to improve road safety and driver’s acceptance of L2–L3 level intelligent vehicles [3,4]
The driving data were used to train HDP–HSMM to obtain model parameters based on WLGS
DiTschuesasbioonve analysis shows that HDP–HSMM can provide reasonable segmentation for drTivhienagbdoavtea ainnatilmyseissesrhioesw, santhdatthHe SDtPat–eH–ASMctiMoncsaenmparnotvicidpelarneeasaollnoawbsleussetgominentetraptiroent ffroargdmrievnint cgludsattearsinintitmuietisveerliyesa,nadndtotheveaSltuaatete–Athcetiironrisskemcoaenftfiiccipelnatneeaasillloy.wIns uthsetofoilnltoewrpinregt sfreacgtimone,ntthceludsrtievrins ginsttuyilteivweliyll abnedqutoanetviafileudataentdhediirscruissksecdoeufsfiicnigentht eeasseimlya. nInticthpelafnolel.owing 5s.e1c.tiDorni,vtihnge dStryivleinDgissctuyslseiownill be quantified and discussed using the semantic plane

Summary

Introduction

Better understanding of the variability in individual driving styles would be especially useful for understanding driver preferences, mechanisms for vehicle control, path planning, and for developing more realistic traffic simulations [1,2] to improve road safety and driver’s acceptance of L2–L3 level intelligent vehicles [3,4]. Previous studies have shown that drivers with an aggressive style are prone to bad behavior such as rapid acceleration, rapid deceleration, near following, and frequent lane changing in the process of driving. Drivers have personalized requirements for the advanced driver assistance system (ADAS) due to different driving styles. A personalized adaptive cruise control (PACC) was designed to satisfy the personalized needs of drivers with different driving styles [6]. Yang et al [7] collected various styles of lane changing characteristics and designed

Methods

Results

Discussion

Conclusion