A Review of Research on Driving Styles and Road Safety

Sagberg, Fridulv; Selpi,; Piccinini, Giulio Bianchi; Engström, Johan

doi:10.1177/0018720815591313

Cited by 328 publications

(182 citation statements)

References 106 publications

Supporting

Mentioning

147

Contrasting

Unclassified

Order By: Relevance

“…With the earliest driving style research occurred in 1949 [6], most of these studies were primarily focusing on improving driving safety, and various self-report instrument questionnaires had been adopted for data collection [7]. However, owing to the overwhelming energy crisis and the advent of vehicular sensing technologies, another trend emerged in the last decade, which utilized recorded vehicle information to analyze driving styles and their relations to fuel consumption.…”

Section: Introductionmentioning

confidence: 99%

A Support Vector Clustering Based Approach for Driving Style Classification

Feng

Pickering²,

Chappell³

et al. 2019

IJMLC

View full text Add to dashboard Cite

All drivers have their own habitual choice of driving behavior, causing variations in fuel consumption. It would be beneficial to classify these driving styles and extract the most economical and ecological driving patterns. However, driving style of each driver is not consistent and may vary within a single trip. Therefore, this paper proposes a novel technique to robustly classify driving style using the Support Vector Clustering approach, which attempts to differentiate the variations in individual's driving pattern and provides an objective driver classification. It is part of a research program aiming to replicate some humans' driving behaviors on chassis dynamometer using a robot driver. Moreover, it can potentially be used in developing more economical and personalized advanced driver assistance systems (ADAS) and humanized autonomous driving strategies. With the easily accessible on-board diagnostics (OBD) data on modern vehicles, both vehicle state and traffic information of three drivers were collected using an instrumented vehicle, which had external forward-looking radar and a monocular dashcam. For data processing, each trip data was first segmented into separate event groups. Prominent factors were then extracted by applying Principal Component Analysis (PCA) on both statistical and spectral features of all signals. Afterwards, Support Vector Clustering (SVC) was performed to classify driving style during the trip. The trained classifier was used to indicate the driving pattern variations in percentage. The validity of the proposed method was evaluated using the jerk profile, where a high correlation was found between the classification results and jerk distributions. Moreover, a positive relation between fuel consumption and driving aggressivity was also confirmed. Furthermore, it was found that weather condition, time of the day and ultimately, the driver's eagerness, can cause significant variations in driving style.

show abstract

Section: Introductionmentioning

confidence: 99%

A Support Vector Clustering Based Approach for Driving Style Classification

Feng

Pickering²,

Chappell³

et al. 2019

IJMLC

View full text Add to dashboard Cite

show abstract

“…One may question if the differences could be explained by the fact that there are both male and female drivers in the Sweden dataset while there are only male drivers in the China dataset. However, previous research reviewed in [31] gives mixed results on whether there is a relationship between gender and driving behaviour. Further, previous research comparing male and female driver behaviours in Sweden suggest that there are only marginal difference between the two groups, e.g.…”

Section: Comparison Of Ttc and Time Gap In Various Relative Speed mentioning

confidence: 96%

Comparison of Car-Following Behavior in Terms of Safety Indicators Between China and Sweden

Tong

Selpi

2020

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Understanding car-following behaviour in different countries is essential for the design and development of autonomous driving and further development of active safety systems that can function well worldwide, in particular in mixed traffic conditions. However, very few studies exist that compare car-following behaviours in different countries based on real driving data. This paper analyses the similarities and differences of drivers' car-following behaviour, in terms of time gap, gap distance, and time to collision, using both China and Sweden datasets from real road driving studies, in a bid to identify how these indicators affect drivers' speed control in car-following situations. Results indicate that the highest frequency of gap distance is observed in the same value-range in both datasets, while the highest frequency of time gap in the Sweden dataset is found at a lower value-range than the corresponding value-range in the China dataset. For both datasets, time gap is observed to be a more reliable indicator for car-following analysis than gap distance, since it is less sensitive to speed variations. Furthermore, time to collision (TTC) in the low travel speed ranges (v<50 km/h) tends to be steady in comparison with TTC at other speed ranges, so is the time gap in the high speed ranges (v>90 km/h). Therefore, time gap is recommended as the safety indicator for car-following analysis in high speed conditions, while a combination of time gap and TTC is recommended for low speed conditions, especially on urban roads.

show abstract

“…Driving behavior analysis is an interdisciplinary field and has drawn increasing attention in the recent decade, specifically in the context of vehicle automation [23]. An in-depth recent review of the literature on driving style analysis frameworks is given in [27]. Traditionally, the main source of the data for the driving behavior analysis are naturalistic driving studies (NDS).…”

Section: Related Workmentioning

confidence: 99%

Clusters of Driving Behavior From Observational Smartphone Data

Warren

Lipkowitz

Sokolov

2019

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Understanding driving behaviors is essential for improving safety and mobility of our transportation systems. Data is usually collected via simulator-based studies or naturalistic driving studies. Those techniques allow for understanding relations between demographics, road conditions and safety. On the other hand, they are very costly and time consuming. Thanks to the ubiquity of smartphones, we have an opportunity to substantially complement more traditional data collection techniques with data extracted from phone sensors, such as GPS, accelerometer gyroscope and camera. We developed statistical models that provided insight into driver behavior in the San Francisco metro area based on tens of thousands of driver logs. We used novel data sources to support our work. We used cell phone sensor data drawn from five hundred drivers in San Francisco to understand the speed of traffic across the city as well as the maneuvers of drivers in different areas. Specifically, we clustered drivers based on their driving behavior. We looked at driver norms by street and flagged driving behaviors that deviated from the norm.

show abstract

A Review of Research on Driving Styles and Road Safety

Cited by 328 publications

References 106 publications

A Support Vector Clustering Based Approach for Driving Style Classification

A Support Vector Clustering Based Approach for Driving Style Classification

Comparison of Car-Following Behavior in Terms of Safety Indicators Between China and Sweden

Clusters of Driving Behavior From Observational Smartphone Data

Contact Info

Product

Resources

About