A Probabilistic Model for Driving-Style-Recognition-Enabled Driver Steering Behaviors

Deng, Zejian; Chu, Delin; Wu, Chaozhong; Liu, Shidong; Sun, Chen; Li, Teng; Cao, Dongpu

doi:10.1109/tsmc.2020.3037229

Cited by 41 publications

(14 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the statistical report, the average driving time per person in the world exceeds 1 hour per day 7,8 , which also is accompanied by serious injuries, fatalities and related costs caused by negative human emotions in driving tasks 9,10 . For a long time, how to reduce accidents risk caused by emotions through studying human emotions in driving tasks has been an important research topic in many fields such as psychology, physiology, engineering, and ergonomics, and has been extensively studied [11][12][13][14][15] .…”

Section: Background and Summarymentioning

confidence: 99%

A multimodal psychological, physiological and behavioural dataset for human emotions in driving tasks

Tan

Xing

et al. 2022

Sci Data

Self Cite

View full text Add to dashboard Cite

Human emotions are integral to daily tasks, and driving is now a typical daily task. Creating a multi-modal human emotion dataset in driving tasks is an essential step in human emotion studies. we conducted three experiments to collect multimodal psychological, physiological and behavioural dataset for human emotions (PPB-Emo). In Experiment I, 27 participants were recruited, the in-depth interview method was employed to explore the driver’s viewpoints on driving scenarios that induce different emotions. For Experiment II, 409 participants were recruited, a questionnaire survey was conducted to obtain driving scenarios information that induces human drivers to produce specific emotions, and the results were used as the basis for selecting video-audio stimulus materials. In Experiment III, 40 participants were recruited, and the psychological data and physiological data, as well as their behavioural data were collected of all participants in 280 times driving tasks. The PPB-Emo dataset will largely support the analysis of human emotion in driving tasks. Moreover, The PPB-Emo dataset will also benefit human emotion research in other daily tasks.

show abstract

Section: Background and Summarymentioning

confidence: 99%

A multimodal psychological, physiological and behavioural dataset for human emotions in driving tasks

Tan

Xing

et al. 2022

Sci Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, methods based on reinforcement learning like the Generative Adversarial Imitation Learning (GAIL) framework [22] were utilized to mimic drivers in a highway driving scenario [23], and were extended to imitate human behavior in a short-term race driving setting based on visual features [24]. Besides that, research on personalized driver modeling is available that targets specific human individuals [25], [26], [27]. However, these models do not consider human adaptability and are partially limited to only model steering as a car control input.…”

Section: B Related Workmentioning

confidence: 99%

An Adaptive Human Driver Model for Realistic Race Car Simulations

Löckel¹,

Ju²,

Schaller³

et al. 2022

Preprint

View full text Add to dashboard Cite

Engineering a high-performance race car requires a direct consideration of the human driver using real-world tests or Human-Driver-in-the-Loop simulations. Apart from that, offline simulations with human-like race driver models could make this vehicle development process more effective and efficient but are hard to obtain due to various challenges. With this work, we intend to provide a better understanding of race driver behavior and introduce an adaptive human race driver model based on imitation learning. Using existing findings and an interview with a professional race engineer, we identify fundamental adaptation mechanisms and how drivers learn to optimize lap time on a new track. Subsequently, we use these insights to develop generalization and adaptation techniques for a recently presented probabilistic driver modeling approach and evaluate it using data from professional race drivers and a state-of-the-art race car simulator. We show that our framework can create realistic driving line distributions on unseen race tracks with almost human-like performance. Moreover, our driver model optimizes its driving lap by lap, correcting driving errors from previous laps while achieving faster lap times. This work contributes to a better understanding and modeling of the human driver, aiming to expedite simulation methods in the modern vehicle development process and potentially supporting automated driving and racing technologies.

show abstract

“…Han W et al [21] extracted discriminative features using the conditional kernel density, and computed the posterior probability of each selected feature to classify driving styles into seven levels from normal to aggressive. Deng Z et al [22] extracted maximum lateral acceleration as a crucial indicator, and determined driving style using the point estimation model and interval estimation model.…”

Section: Driving Style Recognition Mehtodmentioning

confidence: 99%

“…In the above related works, in order to represent the driving styles, many researchers extracted statistical parameters, such as the maximum [22], and many researchers calculated the time gap (division of range and speed) and speed difference [17]. However, these parameters lost the detailed information of the driving behavior, and ignored the simultaneity and correlation between different data fields.…”

Section: Driving Style Recognition Mehtodmentioning

confidence: 99%

Driving Style Recognition Model Based on NEV High-Frequency Big Data and Joint Distribution Feature Parameters

Xia

Kang

2021

WEVJ

View full text Add to dashboard Cite

With the promotion and financial subsidies of the new energy vehicle (NEV), the NEV industry of China has developed rapidly in recent years. However, compared with traditional fuel vehicles, the technological maturity of the NEV is still insufficient, and there are still many problems that need to be solved in the R&D and operation stages. Among them, energy consumption and driving range are particularly concerning, and are closely related to the driving style of the driver. Therefore, the accurate identification of the driving style can provide support for the research of energy consumption. Based on the NEV high-frequency big data collected by the vehicle-mounted terminal, we extract the feature parameter set that can reflect the precise spatiotemporal changes in driving behavior, use the principal component analysis method (PCA) to optimize the feature parameter set, realize the automatic driving style classification using a K-means algorithm, and build a driving style recognition model through a neural network algorithm. The result of this paper shows that the model can automatically classify driving styles based on the actual driving data of NEV users, and that the recognition accuracy can reach 96.8%. The research on driving style recognition in this paper has a certain reference value for the development and upgrade of NEV products and the improvement of safety.

show abstract

A Probabilistic Model for Driving-Style-Recognition-Enabled Driver Steering Behaviors

Cited by 41 publications

References 62 publications

A multimodal psychological, physiological and behavioural dataset for human emotions in driving tasks

A multimodal psychological, physiological and behavioural dataset for human emotions in driving tasks

An Adaptive Human Driver Model for Realistic Race Car Simulations

Driving Style Recognition Model Based on NEV High-Frequency Big Data and Joint Distribution Feature Parameters

Contact Info

Product

Resources

About