Generalization of cut-in pre-crash scenarios for autonomous vehicles based on accident data.

The utilization of high-risk test cases constitutes an effective approach to enhance the safety testing of autonomous vehicles (AVs) and enhance their efficiency. This research paper presents a derivation of 2052 high-hazard pre-crash scenarios for testing autonomous driving, which were based on 23 high-hazard cut-in accident scenarios from the National Automobile Accident In-Depth Investigation System (NAIS) through combining importance sampling and combined testing methods. Compared to the direct combination of the original distribution after sampling, the proposed method has a 2.

Analysis of pedestrian accident severity by considering temporal instability and heterogeneity.

The aim of this study was to investigate the effects of temporal instability and possible heterogeneity on pedestrian accident severity, 48786 accident data from 2018 to 2021 in the UK STATS database were used as the study object, and accident severity was used as the dependent variable, and 49 accident characteristics were selected as independent variables from 6 characteristics of accident pedestrian, driver, vehicle, road, environment and time to construct the pedestrian accident mean heterogeneity random-parameter logit model and examined its temporal stability. The results of model estimation and likelihood ratio tests indicate that the variables affecting pedestrian injury severity are highly variable and not stable over the years. And further demonstrates the potential of models that address unobserved heterogeneity for significant relationships in pedestrian accident severity analyses.