Driving risk assessment based on naturalistic driving study and driver attitude questionnaire analysis

Optimal Duration of In-Vehicle Data Recorder Monitoring to Assess Bus Driver Behavior

This study examined the optimal sampling durations for in-vehicle data recorder (IVDR) data analysis, focusing on professional bus drivers. Vision-based technology (VBT) from Mobileye Inc. is an emerging technology for monitoring driver behavior and enhancing safety in advanced driver assistance systems (ADASs) and autonomous driving. VBT detects hazardous driving events by assessing distances to vehicles. This naturalistic study of 77 male bus drivers aimed to determine the optimal duration for monitoring professional bus driving patterns and the stabilization point in risky driving events over time using VBT and G-sensor-equipped buses. Of the initial cohort, 61 drivers' VBT data and 66 drivers' G-sensor data were suitable for analysis. Findings indicated that achieving a stable driving pattern required approximately 130 h of VBT data and 170 h of G-sensor data with an expected 10% error rate. Deviating downward from these durations led to higher error rates or unreliable data. The study found that VBT and G-sensor data are both valuable tools for driving assessment. Moreover, it underscored the effective application of VBT technology in driving behavior analysis as a way of assessing interventions and refining autonomous vehicle algorithms. These results provide practical recommendations for IVDR researchers, stressing the importance of adequate monitoring durations for reliable and accurate outcomes.

Revision of the driver behavior questionnaire for Chinese drivers' aberrant driving behaviors using naturalistic driving data

The Manchester Driver Behavior Questionnaire (DBQ) is a widely used self-reported measure of aberrant driving behaviors. It provides a standardized way of evaluating drivers' safety awareness and motivation, but the effectiveness of the DBQ's application in different regions can be influenced by culture, social norms, and time period. Several studies have adjusted DBQ items to reflect driver behavior native to particular regions or times, but few have used objective measurements to make proper adjustments. A naturalistic driving study (NDS) provides vehicle kinematic data and in-vehicle videos that objectively capture actual driving behaviors. The gender, age, and driving experience characteristics of aberrant driving behaviors were analyzed, and, based on comparisons between the DBQ self-reported driving behaviors and those observed in the Shanghai, China, NDS, the existing items from the Manchester DBQ were subsequently adjusted. Sixty-two types of real-world aberrant driving behaviors were extracted from 490 valid crash and near crash events observed in the Shanghai NDS. Aberrant driving behavior rates were calculated for individual characteristics (gender, age, and driving experience), and factor rates were calculated based on the three DBQ factor types of violation, error, and lapse. Results revealed that (a) male drivers, drivers in their thirties, and those with three to five years of driving experience demonstrated higher rates of aberrant driving behaviors; and (b) there were weak correlations between observed NDS factor rates and self-reported DBQ scores, and only slight differences among drivers divided by factor rate level (e.g., high violation rate). The questionnaire calibrated for Chinese drivers includes 23 items. Five of the original 24 DBQ items were modified, eight were left unchanged, eleven were deleted, and ten field-observed combined behaviors were added. In addition to the importance of adjusting the DBQ for today's Chinese drivers, this study provides a method for objectively modifying DBQ items in the future in accord with observed driving behaviors in an NDS.

Collision-free emergency planning and control methods for CAVs considering intentions of surrounding vehicles

Autonomous emergency braking (AEB) systems are able to control vehicles as needed to avoid vehicle rear-end collisions. However, these systems are ineffective in scenarios with laterally cut-in vehicles and rapidly-changing dangerous scenes. This paper proposes a novel collision-free emergency braking system (CFEBS) that can enable intelligent connected vehicles (CAVs) to plan and execute a more conservative safety trajectory for the braking process in dangerous scenes by considering the longitudinal and lateral motion intentions of the surrounding vehicles. An intention identification model for surrounding vehicles is proposed based on long-short term memory (LSTM) networks and conditional random fields (CRFs). By considering the surrounding vehicles as risk sources and quantifying the risk with the speed of the risk flow, a potential risk flow model is built to calculate the potential risk map (PRM) around the ego vehicle. The global safest trajectory is generated via the PRM using the discrete method. The output trajectory profile is regarded as the reference for a model predictive controller (MPC). Simulation results show that the proposed CFEBS can predict vehicle intention with 91.6% accuracy and control the ego vehicle to perform effective collision-free braking operations in emergency traffic environments.

Review of Research on Road Traffic Operation Risk Prevention and Control

Road traffic safety can be ensured by preventing and controlling the potential risks in road traffic operations. The relevant literature was systematically reviewed to identify the research context and status quo in the road traffic operation risk prevention and control field and identify the key study contents needing further research. As research material, the related English and Chinese literature published between 1996 and 2021 (as of 31st December 2021) was obtained through the Web of Science Core Collection and Chinese Science Citation Database. These research materials include 22,403 English and 7876 Chinese papers. Based on the bibliometrics, this study used CiteSpace software to conduct keyword co-occurrence analysis in the field. The results show that the relevant research topics mainly covered the risks of drivers, vehicles, roads, and the traffic environment. In the aspect of driver risks, the studies focused on driving behavior characteristics. In terms of vehicle risks, the related studies were mainly about the vehicle control system, driving assistance system, hazardous material transportation, automated driving technology, safe driving speed, and vehicle collision prediction. For the road risks, the safe driving guarantee of high-risk road sections, driving risks at intersections, and safe road alignment design were the three study hotspots. In terms of traffic environment risks, identifying traffic risk locations and driving safety guarantees under adverse weather conditions were the two main research highlights. Moreover, mathematical modeling was the main method for studying road traffic operation risk. Furthermore, the impact of environmental factors on drivers, the emergency rescue system for road traffic accidents, the connection between automated driving technology and safe driving theory, and the man-machine hybrid traffic flow characteristics are the subjects needing further research.

Data-Driven Estimation of a Driving Safety Tolerance Zone Using Imbalanced Machine Learning

Predicting driving behavior and crash risk in real-time is a problem that has been heavily researched in the past years. Although in-vehicle interventions and gamification features in post-trip dashboards have emerged, the connection between real-time driving behavior prediction and the triggering of such interventions is yet to be realized. This is the focus of the European Horizon2020 project “i-DREAMS”, which aims at defining, developing, testing and validating a ‘Safety Tolerance Zone’ (STZ) in order to prevent drivers from risky driving behaviors using interventions both in real-time and post-trip. However, the data-driven conceptualization of STZ levels is a challenging task, and data class imbalance might hinder this process. Following the project principles and taking the aforementioned challenges into consideration, this paper proposes a framework to identify the level of risky driving behavior as well as the duration of the time spent in each risk level by private car drivers. This aim is accomplished by four classification algorithms, namely Support Vector Machines (SVMs), Random Forest (RFs), AdaBoost, and Multilayer Perceptron (MLP) Neural Networks and imbalanced learning using the Adaptive Synthetic technique (ADASYN) in order to deal with the unbalanced distribution of the dataset in the STZ levels. Moreover, as an alternative approach of risk prediction, three regression algorithms, namely Ridge, Lasso, and Elastic Net are used to predict time duration. The results showed that RF and MLP outperformed the rest of the classifiers with 84% and 82% overall accuracy, respectively, and that the maximum speed of the vehicle during a 30 s interval, is the most crucial predictor for identifying the driving time at each safety level.

Based on ISM—NK Tunnel Fire Multi-Factor Coupling Evolution Game Research

A tunnel is a complex network system with multiple risk factors interacting. At present, the cause analysis of tunnel fire accidents focuses on exploring risk sources and risk assessment, ignoring the interaction between risk factors. A single model has certain limitations. By proposing the concept of the multi-factor coupled evolutionary game of tunnel fire, integrating the natural killing model (NK) and the explanatory structure model (ISM), the evolutionary game of multi-factor coupling of tunnel fire is studied from the perspective of micro and macro analysis, qualitative and quantitative research, the coupling relationship and effect between risk factors are discussed, 100 tunnel fire accidents and 158 tunnel fire literature at home and abroad are analyzed, and 40 typical tunnel fire risk factors and 31 coupling types of fire cause factors are extracted. Using the combined ISM-NK model, a seven-level network model of tunnel fire accident risk coupling is constructed, and the degree of coupling of various types of risk factors is evaluated. The hierarchical network cascade model revealed that 4 of the 40 typical tunnel fire risk factors were the underlying risk factors, 23 shallow layers were the risk factors and direct influencing factors, and 13 were the middle-risk factors and indirect influencing factors. The NK model shows that with the increase of coupling nodes, the frequency of tunnel fire accidents also shows an upward trend, and the subjective risk factor coupled with tunnel fires have a higher frequency than the objective risk factors.

Road safety under the environment of intelligent connected vehicles

The emergence of Intelligent Connected Vehicles (ICVs) is expected to drastically change various fields in the transportation system-especially traffic safety of road users. Therefore, this special issue aims to facilitate a forum for transportation researchers fostering an exchange of research ideas and experience in traffic safety with a specific focus on operations, planning and management of ICVs. The issue contains thirty-six papers from seven different countries. Topics are classified into seven categories: (1) Driving behavior in the ICV environment; (2) Safety evaluation of ICVs; (3) ICV driving/management strategies; (4) New framework for ICV safety analysis; (5) ICV safety for vulnerable road users; (6) Perception towards ICVs; and (7) Security issues relating to ICVs. The papers are concisely introduced in this editorial. All the papers were invited to present at the International Symposium on Accident Analysis & Prevention in 2021 (ISAAP 2021) and the symposium was successfully held. The research conducted in these articles reveal challenges and future directions in the area of ICVs that include further developing novel methodologies and algorithms for collision-free trajectories of ICVs, testing diverse scenarios in complex environments with mixed traffic, and addressing inherent safety risks of specific vulnerable road users (e.g., older road users, bicyclists, riders of micro-mobility vehicles).

Exploring the associations between driving volatility and autonomous vehicle hazardous scenarios: Insights from field operational test data

With the promising development and deployment trends of autonomous vehicles (AVs), AVs' operation safety has become a key issue worldwide. Studies have been conducted to reveal the risk factors of AV operation safety based upon AV-involved crash reports. However, the crash data sample size was limited and the crash reports only recorded static information, thus it failed to identify crash contributing factors and further provide feedbacks to AV algorithm development. In this study, the risk factors were investigated based upon hazardous scenarios, which were claimed to possess consistent causal mechanisms with crash events. First, contributing factors were extracted from both vehicle kinematics and traffic environment aspects, and their volatility features were obtained. Then, path analysis models were developed to reveal the concurrent relationships between scenario volatility and hazardous scenario occurrence probability. Besides, to understand the varying risk factors for hazardous scenarios caused by human drivers and AVs, a logit regression model was further established. The modeling results showed that large volatility of space headway held direct impacts on increasing the AV driving risks. And the volatility of the drivable road area had no significant impacts on AV driving risks while it indirectly influenced human driving risks. Finally, result implications for AV driving behavior improvements have been discussed.

Driving Risk Assessment Using Near-Miss Events Based on Panel Poisson Regression and Panel Negative Binomial Regression

This study proposes a method for identifying and evaluating driving risk as a first step towards calculating premiums in the newly emerging context of usage-based insurance. Telematics data gathered by the Internet of Vehicles (IoV) contain a large number of near-miss events which can be regarded as an alternative for modeling claims or accidents for estimating a driving risk score for a particular vehicle and its driver. Poisson regression and negative binomial regression are applied to a summary data set of 182 vehicles with one record per vehicle and to a panel data set of daily vehicle data containing four near-miss events, i.e., counts of excess speed, high speed brake, harsh acceleration or deceleration and additional driving behavior parameters that do not result in accidents. Negative binomial regression (AICoverspeed = 997.0, BICoverspeed = 1022.7) is seen to perform better than Poisson regression (AICoverspeed = 7051.8, BICoverspeed = 7074.3). Vehicles are separately classified to five driving risk levels with a driving risk score computed from individual effects of the corresponding panel model. This study provides a research basis for actuarial insurance premium calculations, even if no accident information is available, and enables a precise supervision of dangerous driving behaviors based on driving risk scores.

An integrated methodology for real-time driving risk status prediction using naturalistic driving data

Real-time driving risk status prediction is critical for developing proactive traffic intervention strategies and enhance driving safety. However, the optimal observation time window length and prediction time window length, which should be the prerequisite for the timeliness and accuracy of real-time driving risk status prediction model, have been rarely explored in previous studies. In this study, a methodology which integrates driving risk status identification, rolling time window-based feature extraction, real-time driving risk status prediction and driving risk influencing factors analysis was proposed to accurately evaluate and predict real-time driving risk status. The methodology was tested based on 1,440 car-following events from Shanghai Naturalistic Driving Study. Results show that four driving risk statuses (safe, low-risk, median-risk and high-risk) are most appropriate to establish risk labelling criteria. In addition, results from driving risk status prediction show that when the observation time window length is 0.5 s, the accuracy rate of predicting medium-risk or high-risk status occurring in the next 0.7 s is higher than 85 % using multi-layer perceptron model. Meanwhile, the results from the analysis of influencing factors show that the input variables related to the risk status score higher in the ranking of feature importance. A part from that, speed difference, headway distance, speed and acceleration are still important in predicting driving risk status. The proposed methods in this paper can be applied in connected and autonomous vehicle (CAV) to reduce driver cognitive workload and hence improve driving safety fed with naturalistic driving data collected using in-vehicle systems.