Crash comparison of autonomous and conventional vehicles using pre-crash scenario typology

A matched case-control analysis of autonomous vs human-driven vehicle accidents

Despite the recent advancements that Autonomous Vehicles have shown in their potential to improve safety and operation, considering differences between Autonomous Vehicles and Human-Driven Vehicles in accidents remain unidentified due to the scarcity of real-world Autonomous Vehicles accident data. We investigated the difference in accident occurrence between Autonomous Vehicles' levels and Human-Driven Vehicles by utilizing 2100 Advanced Driving Systems and Advanced Driver Assistance Systems and 35,113 Human-Driven Vehicles accident data. A matched case-control design was conducted to investigate the differential characteristics involving Autonomous' versus Human-Driven Vehicles' accidents. The analysis suggests that accidents of vehicles equipped with Advanced Driving Systems generally have a lower chance of occurring than Human-Driven Vehicles in most of the similar accident scenarios. However, accidents involving Advanced Driving Systems occur more frequently than Human-Driven Vehicle accidents under dawn/dusk or turning conditions, which is 5.25 and 1.98 times higher, respectively. Our research reveals the accident risk disparities between Autonomous Vehicles and Human-Driven Vehicles, informing future development in Autonomous technology and safety enhancements.

What can we learn from the AV crashes? - An association rule analysis for identifying the contributing risky factors

The objective of this study is to explore the contributing risky factors to Autonomous Vehicle (AV) crashes and their interdependencies. AV crash data between 2015 and 2023 were collected from the autonomous vehicle collision report published by California Department of Motor Vehicles (DMV). AV crashes were categorized into four types based on vehicle damage. AV crashes features including crash location and time, driving mode, vehicle movements, crash type and vehicle damage, traffic conditions, and among others were used as potential risk factors. Association Rule Mining methods (ARM) were utilized to identify sets of contributing risky factors that often occur together in AV crashes. Several association rules suggest that AV crashes result from complex interactions between road factors, vehicle factors, and environmental conditions. No damage and minor crashes are more likely affected by the road features and traffic conditions. In contrast, the movements of vehicles are more sensitive to severe AV crashes. Improper vehicle operations could increase the probability of severe AV crashes. In addition, results suggest that adverse weather conditions could increase the damage of AV crashes. AV interactions with roadside infrastructure or vulnerable road users on wet road surfaces during the night could potentially lead to significant loss of life and property. Furthermore, the safety effects of vehicle mode on the different AV crash damage are revealed. In some contexts, the autonomous driving mode can mitigate the risk of crash damages compared with conventional driving mode. The findings of this study should be indicative of policy measures and engineering countermeasures that improve the safety and efficiency of AV on the road, ultimately improving road transportation's overall safety and reliability.

Unveiling pre-crash driving behavior common features based upon behavior entropy

Driving behavior is considered as the primary crash influencing factor, whereas studies claimed that over 90% crashes were attributed by behavior features. Therefore, unveil pre-crash driving behavior features is of great importance for crash prevention. Previous studies have established the correlations between features such as vehicle speed, speed variability, and the probability of crash occurrences, but these analyses have concluded inconsistent results. This is due to the varying operating characteristics among roadway facilities, where given the same driving behavior statistical features, the corresponding traffic states are not identical. In this study, a behavioral entropy index was proposed to address the abovementioned issue. First, through comparing the individual driving behavior with the group distribution, behavioral entropy index was calculated to quantify the abnormality of driving behavior. Then, crash classification models were established by comparing the behavioral entropy prior to crash events and normal driving conditions. The empirical analyses have been conducted based on 1,634,770 naturalistic driving trajectories and 1027 crash events. And models have been carried out for urban roadway sections, urban intersections, and highway sections separately. The results showed that utilizing the behavior entropy instead of the statistical features could enhance the crash classification accuracy by 11.3%. And common pre-crash features of increased behavioral entropy were identified. Moreover, the speed coefficient of variation (QCV) entropy was concluded as the most influencing factor, which can be used for real-time driving risk monitoring and enables individual-level hazard mitigation.

The typical AV accident scenarios in the urban area obtained by clustering and association rule mining of real-world accident reports

Automated Vehicles (AVs) based on a collection of advanced technologies such as big data and artificial intelligence have opened an opportunity to reduce traffic accidents caused by human drivers. Nevertheless, traffic accidents of AVs continue to occur, which raises safety and reliability concerns about AVs. AVs are particularly vulnerable to accidents on urban roads than on highways due to various dynamic objects and more complex infrastructure. Several studies proposed a scenario-based approach of experimenting with the response of AVs to specific situations as a way to test their safety. Reliable and concrete scenarios are necessary to test AV safety under critical conditions accurately. This study aims to derive a typical accident scenario for evaluating the safety of AVs, specifically in urban areas, by analysing collisions reported by the DMV of California, USA. We applied a hierarchical clustering method to find groups of similar reports and then executed association rule mining on each cluster to correlate between accident factors and collision types. We combined statistically significant association rules to constitute a total of 14 scenarios that are described according to an adapted PEGASUS framework. The newly obtained scenarios exhibit significantly different accident patterns than the typical Human-driven Vehicles (HVs) in urban areas reported by National Highway Traffic Safety Administration. Our discovery urges AV safety to be tested reliably under scenarios more relevant than the existing HV accident scenarios.

Critical voxel learning with vision transformer and derivation of logical AV safety assessment scenarios

Safety assessment is an active research subject for autonomous vehicles (AVs) that have emerged as a new mode of mobility. In particular, scenario-based safety assessments have garnered significant attention. AVs can be tested on how they safely avoid hypothetical situations leading to accidents. However, scenarios written by humans based on their expert knowledge and experience may only partially reflect real-world situations. Instead, we are keen on a different technique of extracting statistically significant and more detailed scenarios from sensor data captured during the critical moments when AVs become vulnerable to potential accidents. Specifically, we first render the three-dimensional space around an AV with fixed-sized voxels. Then, we modeled the aggregate kinetics of the objects in each voxel detected by 3D-LiDAR sensors mounted on real test AVs. The Vision Transformer we used to model the kinetics helped us quickly pinpoint critical voxels containing objects that threatened the AV's safety. We traced the trajectory of the critical voxels on a visual attention map to describe in detail how AVs become vulnerable to accidents according to the logical scenario format defined by the PEGASUS Project. We tested our novel method with 250 h of 3D-LiDAR recordings capturing critical moments. We devised an inference model that detected critical situations with an F1-score of 98.26%. For each type of scenario, our model consistently identified the critical objects and their tendency to influence AVs. Given the evaluation results, we can ensure that our data-driven approach yields an AV safety assessment scenario with high representativeness, coverage, expansion, and computational feasibility.

Analysis of pre-crash scenarios and contributing factors for autonomous vehicle crashes at intersections

Intersections are high-risk locations for autonomous vehicles (AVs). Crash causation analysis based on pre-crash scenarios can provide new insight into these crashes that can lead to effective countermeasures, but there are significant differences in pre-crash scenarios between autonomous and conventional vehicles, and inadequate AV data has put limits on research. The association rule method, however, can yield useful results despite these limits. This study therefore aims to use the method with pre-crash scenarios to understand the characteristics and contributing factors of AV crashes at intersections from the latest 5-year AV crash data. Analysis of 197 AV crashes at intersections revealed 30 types of pre-crash scenarios. The rear-end crash (58.88%) and lane change crash (16.24%) were the most frequently occurring scenarios for AVs. The proportion of AVs being rear-ended by conventional vehicles was 58.38%. The main contributing factors of these two most common AV scenarios were identified by association rules and crash causes were analyzed from the perspective of AV decision-making. The main factors contributing to the AV rear-end scenario were location outside the intersection in the intersection-related area, traffic signal control, autonomous engaged mode, mixed-use or public land, and weekdays, while those for lane change scenarios were on-street parking and the time of 8:00 a.m. Important causes of rear-end crashes attributable to the AV were inadequate stop and deceleration decisions by the AV's automated driving system (ADS) and insufficient collision avoidance decisions in lane change crashes. Identification of the pre-crash characteristics and contributing factors provide new insight into AV crash causation and can be used in the determination of the AV's operational design domain and the development and optimization of the AV's ADS at intersections. These findings can also play a role in guiding traffic safety agencies to discover AV hotspots and propose AV management regulations.

Machines meet humans on the social road: Risk implications

Human drivers and machine drivers (i.e., automated vehicles or AVs) will share roads and interact with each other, creating mixed traffic. In this perspective, we develop two mental models about them and their social interactions, aiming to understand the risk implications of AVs and mixed traffic. Based on Mental Model I (i.e., machine drivers are superior drivers without human weaknesses), many simulation-based safety assessments, which often overlook or oversimplify human-AV social interactions, have predicted significant safety benefits when machine drivers interact with or replace human drivers. In contrast, Mental Model II considers human and machine drivers as heterogeneous and incompatible, suggesting that their interactions may lead to unexpected and occasionally negative outcomes, particularly in imminent mixed traffic. This perspective gains support from recent comparative empirical studies that employ various methods such as survey experiments, driving simulators, test-tracks, on-road observations, and AV accident analysis. These studies provide initial evidence of emerging traffic risks arising from human-AV social interactions, including human drivers' aggression and road rage toward AVs, human drivers exploiting AVs, AVs exerting negative peer influences on human drivers, and their incompatibility increasing human drivers' challenges in joining mixed traffic and thus risky behaviors. We propose specific suggestions to mitigate problematic human-AV social interactions and the associated emerging risks.

Application of naturalistic driving data: A systematic review and bibliometric analysis

The application of naturalistic driving data (NDD) has the potential to answer critical research questions in the area of driving behavior assessment, as well as the impact of exogenous and endogenous factors on driver safety. However, the presence of a large number of research domains and analysis foci makes a systematic review of NDD applications challenging in terms of information density and complexity. While previous research has focused on the execution of naturalistic driving studies and on specific analysis techniques, a multifaceted aggregation of NDD applications in Intelligent Transportation System (ITS) research is still unavailable. In spite of the current body of work being regularly updated with new findings, evolutionary nuances in this field remain relatively unknown. To address these deficits, the evolutionary trend of NDD applications was assessed using research performance analysis and science mapping. Subsequently, a systematic review was conducted using the keywords "naturalistic driving data" and "naturalistic driving study data". As a result, a set of 393 papers, Published between January 2002-March 2022, was thematically clustered based on the most common application areas utilizing NDD. the results highlighted the relationship between the most crucial research domains in ITS, where NDD had been incorporated, and application areas, modeling objectives, and analysis techniques involving naturalistic databases.

Vehicle crash simulations for safety: Introduction of connected and automated vehicles on the roadways

Traffic accidents are one main cause of human fatalities in modern society. With the fast development of connected and autonomous vehicles (CAVs), there comes both challenges and opportunities in improving traffic safety on the roads. While on-road tests are limited due to their high cost and hardware requirements, simulation has been widely used to study traffic safety. To make the simulation as realistic as possible, real-world crash data such as crash reports could be leveraged in the creation of the simulation. In addition, to enable such simulations to capture the complexity of traffic, especially when both CAVs and human-driven vehicles co-exist on the road, careful consideration needs to be given to the depiction of human behaviors and control algorithms of CAVs and their interactions. In this paper, the authors reviewed literature that is closely related to crash analysis based on crash reports and to simulation of mixed traffic when CAVs and human-driven vehicles co-exist, for studying traffic safety. Three main aspects are examined based on our literature review: data source, simulation methods, and human factors. It was found that there is an abundance of research in the respective areas, namely, crash report analysis, crash simulation studies (including vehicle simulation, traffic simulation, and driving simulation), and human factors. However, there is a lack of integration between them. Future research is recommended to integrate and leverage different state-of-the-art transportation-related technologies to contribute to road safety by developing an all-in-one-step crash analysis system.

Developing an improved automatic preventive braking system based on safety-critical car-following events from naturalistic driving study data

In public road tests of autonomous vehicles in California, rear-end crashes have been the most common type of crash. Collision avoidance systems, such as autonomous emergency braking (AEB), have provided an effective way for autonomous vehicles to avoid collisions with the lead vehicle, but to avert false alarms, AEB tends to apply late and hard brake only if a collision becomes unavoidable. Automatic preventive braking (APB) is a new collision avoidance method used in Mobileye's Responsibility-Sensitive Safety (RSS) model that aims to reduce crashes with a milder brake and decreased impact on traffic flow, but APB's safety performance is inferior to that of AEB. This study therefore proposes three safety improvement strategies for APB, the addition of response time, safety buffer, and minimum following distance; and combines them in different ways into four improved APB systems, IP1-IP4. Simulating car-following safety-critical events (SCEs) extracted from the Shanghai Naturalistic Driving Study in MATLAB's Simulink, the safety performance, conservativeness, and driving comfort of the four systems were evaluated and compared with the original APB system, two AEB systems, and human drivers. The results show that 1) IP4, the system that integrated all three strategies, outperformed the baseline APB and IP1-IP3 and prevented all SCEs from becoming crashes; 2) IP4 was slightly more conservative than AEB, but less conservative than RSS; 3) APB's jerk-bounded braking profile improved driving comfort; and 4) higher deceleration was found in the two AEB systems (both 8.1 m/s²) than in IP4 (6.7 m/s²), but they failed to prevent all crashes. Our proposed APB system, IP4, can provide safe, efficient, and comfortable braking for AVs in car-following SCEs, and has the potential to be practically applied in vehicle collision avoidance systems.

Causation analysis of crashes and near crashes using naturalistic driving data

Understanding crash causation to the extent needed for applying countermeasures has always been a focus as well as a difficulty in the field of traffic safety. Previous research has been limited by insufficient crash data and analysis methods more suitable to single crashes. The use of crashes and near crashes (CNCs) and naturalistic driving studies can help solve the data problem, and use of pre-crash scenarios can identify the high-prevalence causes across multiple crashes of a given scenario. This study therefore proposes a two-stage crash causation analysis method based on pre-crash scenarios and a crash causation derivation framework that systematically categorizes and analyzes contributing factors. From the Shanghai Naturalistic Driving Study (SH-NDS), 536 CNCs were extracted, and were grouped into 23 different pre-crash scenarios based on the National Highway Traffic Safety Administration (NHTSA) pre-crash scenario typology. In-depth investigations were conducted, and CNCs sharing the same scenario were analyzed using the proposed framework, which identifies causation patterns based on the interaction of the framework's road user, vehicle, roadway infrastructure, and roadway environment subsystems. Through statistical analysis, the causation patterns and their contributing factors were compared for three common pre-crash scenarios of highest incidence: rear-end, lane change, and vehicle-pedalcyclist. Braking error in low-speed car following, following too closely, and non-driving-related distraction were important causes of rear-end scenarios. In lane change scenarios, the main causation patterns included illegal use of turn signals and dangerous lane changes as critical factors. Pedalcyclist scenarios were particularly impacted by visual obstructions, inadequate lanes for non-motorized vehicles, and pedalcyclists violating traffic regulations. Based on the identified causation patterns and their contributing factors, countermeasures for the three common scenarios are suggested, which provide support for safety improvement projects and the development of advanced driver assistance systems.

Divergent Effects of Factors on Crash Severity under Autonomous and Conventional Driving Modes Using a Hierarchical Bayesian Approach

Influencing factors on crash severity involved with autonomous vehicles (AVs) have been paid increasing attention. However, there is a lack of comparative analyses of those factors between AVs and human-driven vehicles. To fill this research gap, the study aims to explore the divergent effects of factors on crash severity under autonomous and conventional (i.e., human-driven) driving modes. This study obtained 180 publicly available autonomous vehicle crash data, and 39 explanatory variables were extracted from three categories, including environment, roads, and vehicles. Then, a hierarchical Bayesian approach was applied to analyze the impacting factors on crash severity (i.e., injury or no injury) under both driving modes with considering unobserved heterogeneities. The results showed that some influencing factors affected both driving modes, but their degrees were different. For example, daily visitors' flowrate had a greater impact on the crash severity under the conventional driving mode. More influencing factors only had significant impacts on one of the driving modes. For example, in the autonomous driving mode, mixed land use increased the severity of crashes, while daytime had the opposite effects. This study could contribute to specifying more appropriate policies to reduce the crash severity of both autonomous and human-driven vehicles especially in mixed traffic conditions.

Operational design domain of automated vehicles for crossing maneuvers at two-way stop-controlled intersections

The departure sight triangle provides the view for the vehicle waiting to cross at the two-way stop-controlled intersection. The factors influencing the sight triangle for human drivers are considered in the 2018 AASHTO Green Book, but the Green Book lacks quantitative estimations for automated vehicles (AVs). Therefore, to guarantee the AV's operational safety, this study investigated the impact of intersection angle, speed, and crossing distance on the AV's intersection crossing maneuver. Using physics theorems and cosine law, formulae for the detecting angle (DA) and distance (DD), the two main components of the departure sight triangle, were developed for the acute- and obtuse-angle sides of the intersection for an AV approaching on the minor road; the minimum required DA and DD, with a given crossing distance, are thus proposed for the AV's operational design domain (ODD). Calculations indicate that the DD is mainly affected by the major road design speed and crossing distance, and that the DD increases very quickly as the speed and crossing distance increase. The intersection angle was found to have great impact on the DA on both the acute and obtuse sides, but its influence is negative on the acute side and positive on the obtuse side. On the acute side, the ODD detecting angle range is set as [83.4, 132.7], [80.7, 131.6], and [78.4, 130.7] degrees for major roads with 2, 4, and 6 lanes, respectively. On the obtuse side, the ODD is set as [57.4, 160.6], [70.6, 207.9], and [82.2, 249.1] m for the same respective roads. After comparing the DA and DD results, and depending on the intersection design attributes, it is concluded that most engineering attention should be paid to the DA on the acute side and DD on the obtuse side.