Evaluating the safety of autonomous vehicle–pedestrian interactions: An extreme value theory approach

Alozi, Abdul Razak; Hussein, Mohamed

doi:10.1016/j.amar.2022.100230

Cited by 27 publications

(10 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the accurate prediction of collisions, this study employs the framework developed in Alozi and Hussein ( 19 ) to evaluate the safety of active road users in AV environments. Across a scale of traffic conflict severity, measured using the PET, predicted collisions can be approximated using the extreme events with high severity.…”

Section: Methodsmentioning

confidence: 99%

“…The technique has been validated against actual collision records in several studies ( 39 , 40 ). This approach was used recently to assess the safety of pedestrians interacting with AVs in urban areas ( 19 ). The study developed a framework for predicting pedestrian–AV collisions using real-world conflict data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Early traffic collision prediction, conducted by Alozi and Hussein ( 19 ), indicated alarming numbers of AV–pedestrian collisions per driven distance, which signaled the need for further investigation of AV conflicts. In this study, we aim to conduct a thorough assessment of pedestrian and cyclist safety in AV environments.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Active Road User Interactions With Autonomous Vehicles: Proactive Safety Assessment

Alozi

Hussein

2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

This study aims to conduct a thorough assessment of pedestrian and cyclist safety in autonomous vehicle (AV) environments. To that end, the study utilized AV sensor data of over 1,500 driving hours from five sources in Canada, the United States, and Singapore. The sensor data were used to extract conflicts between AVs and active road users. The conflicts were then processed to develop accurate estimates of AV collisions involving pedestrians and cyclists based on the extreme value theory. Further in-depth assessments were conducted on the identified conflicts, by type and location, to highlight potential issues leading to risky conflicts. The results showed that the total number of predicted AV collisions involving active road users was 2.17 collisions per million AV kilometers travelled. Collisions involving pedestrians were slightly higher than those involving cyclists. Also, collisions in clear weather conditions slightly exceeded collisions in adverse weather conditions, although the difference was not statistically significant. The relative risk of collisions was developed for both pedestrian and cyclist conflicts per AV movement type. The results showed that for pedestrians, interactions with right-turning AVs are the riskiest, while interactions with left-turning AVs are the riskiest for cyclists. A thorough analysis of conflicts revealed many issues, including a higher tendency for pedestrian violations when interacting with AVs, aggressive AV behavior (particularly when interacting with pedestrians while making a right turn), AVs struggling to predict the path of cyclists (mainly because of cyclist violations), and AVs failing to interpret pedestrian intentions in some cases.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Active Road User Interactions With Autonomous Vehicles: Proactive Safety Assessment

Alozi

Hussein

2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most interesting aspect of this approach is the possibility to estimate this probability without the use of crash data, which are instead used only for model validation. In the last few years, extreme value theory (EVT) has been applied in various road safety works (Alozi and Hussein, 2022;Arun et al, 2022;Cavadas et al, 2020;Farah and Azevedo, 2017;Fu et al, 2021Fu et al, , 2020Orsini et al, 2020Orsini et al, , 2019Wang et al, 2018;Zheng et al, 2018aZheng et al, , 2014, with more or less complex and sophisticated procedures. It has also been applied in the specific case of before-after road safety analyses (Zheng et al, 2018b;, which, however, did not focus on vulnerable road users.…”

Section: From Traffic Conflicts To Crash Probabilitiesmentioning

confidence: 99%

Before-after safety analysis of a shared space implementation

Orsini

Batista

Friedrich

et al. 2023

Case Studies on Transport Policy

View full text Add to dashboard Cite

“…The TTC threshold was chosen with a statistical analysis based on EVT. This theory has been applied in several road safety studies to estimate crash probabilities with SMSs (36)(37)(38)(39)(40)(41)(42)(43)(44)(45)(46)(47)(48)(49). The procedure consists in fitting an extreme value distribution using the observed SMS, and then extrapolating a crash probability by considering crashes as ''extreme'' surrogate events.…”

Section: Ttc Threshold Selection (Parameter U)mentioning

confidence: 99%

Conflict-Based Real-Time Road Safety Analysis: Sensitivity to Data Collection Duration and its Implications for Model Resilience

Orsini

Gastaldi

Rossi

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Conflict-based approaches to real-time road safety analysis can provide several benefits over traditional crash-based models. In particular, as traffic conflicts are much more frequent than crashes, models can be trained with significantly shorter collection periods. Since existing literature has not investigated the sensitivity of real-time conflict prediction models (RTConfPM) to data collection duration, here we aim to fill this gap and discuss the implications for model resilience. A real-world highway case study was analyzed. Methodologically, various traffic variables aggregated into 5 min intervals were selected as predictors, synthetic minority oversampling technique (SMOTE) was applied to deal with unbalanced classification issues, and support vector machine (SVM) was chosen as classifier. The dichotomous response variable separated safe and unsafe intervals into two classes; the latter were defined considering a minimum number of rear-end conflicts within the interval, which were identified using a surrogate measure of safety (SMS), that is, time-to-collision. Several RTConfPMs were trained and tested, considering different data collection durations and different criteria to define the unsafe situation class. The results, which were shown to be robust with respect to the machine learning classifier used, indicate that the models were able to provide reliable predictions with just three to five days of data, and that the increase in performance with collection periods longer than 10 to 15 days was negligible. These findings can be generalized by considering the number of unsafe situations corresponding to the data collection period of each tested model; they highlight the relevance of RTConfPM as a more flexible and resilient alternative to the crash-based approach.

show abstract

Evaluating the safety of autonomous vehicle–pedestrian interactions: An extreme value theory approach

Cited by 27 publications

References 65 publications

Active Road User Interactions With Autonomous Vehicles: Proactive Safety Assessment

Active Road User Interactions With Autonomous Vehicles: Proactive Safety Assessment

Before-after safety analysis of a shared space implementation

Conflict-Based Real-Time Road Safety Analysis: Sensitivity to Data Collection Duration and its Implications for Model Resilience

Contact Info

Product

Resources

About