Connecting Surrogate Safety Measures to Crash Probablity via Causal Probabilistic Time Series Prediction

TL;DR

This paper introduces a probabilistic time series prediction method using transformer-MAF to connect surrogate safety measures like speed and acceleration to crash probability, enabling proactive safety analysis.

Contribution

It presents a novel approach linking surrogate safety measures to crash risk through causal probabilistic modeling with transformer-MAF.

Findings

Predicted sequences are accurate in both conflict and normal contexts.

Estimated crash probabilities are reasonable and interpretable.

Conditional crash probability effectively reflects evasive action impacts.

Abstract

Surrogate safety measures can provide fast and pro-active safety analysis and give insights on the pre-crash process and crash failure mechanism by studying near misses. However, validating surrogate safety measures by connecting them to crashes is still an open question. This paper proposed a method to connect surrogate safety measures to crash probability using probabilistic time series prediction. The method used sequences of speed, acceleration and time-to-collision to estimate the probability density functions of those variables with transformer masked autoregressive flow (transformer-MAF). The autoregressive structure mimicked the causal relationship between condition, action and crash outcome and the probability density functions are used to calculate the conditional action probability, crash probability and conditional crash probability. The predicted sequence is accurate and the estimated probability is reasonable under both traffic conflict context and normal interaction context and the conditional crash probability shows the effectiveness of evasive action to avoid crashes in a counterfactual experiment.