Perceived risk evolution in automated driving inferred from large-scale discrete ratings

TL;DR

This paper introduces a kernel constrained inverse model to infer the temporal evolution of perceived risk in automated driving from large-scale discrete ratings, revealing detailed scenario dynamics and cue associations beyond single severity scores.

Contribution

It presents a novel method to infer and analyze the evolution of perceived risk over time using large-scale discrete ratings and deep neural networks, providing deeper insights into risk dynamics.

Findings

Differentiates accumulated perceived risk from within clip concentration.

Identifies scenario differences not visible from peak ratings.

Maps risk evolution to vehicle and motion cues with interpretable attribution.

Abstract

Perceived risk in automated driving is often measured as discrete scores that summarise riding experience but this obscures volatile peaks from sustained elevation. Here we treat discrete clipwise ratings as constraints on an unobserved inferred evolution and apply a kernel constrained inverse model to infer the temporal evolution of perceived risk. Across 2,164 participants and 141,628 discrete clipwise ratings spanning 236 hours of scripted motorway interactions, we infer evolutions under kernel constraints whose shapes follow priors from independent handset-based ratings and whose timing is fixed by scripted manoeuvre markers. The inferred perceived risk evolutions differentiate accumulated perceived risk from within clip concentration, revealing scenario differences that are not identifiable from peak judgements alone. We then map these inferred evolutions from observable vehicle and relative motion cues under strict event level holdout using a deep neural network, enabling interpretable attribution analyses. Attribution shows distinct patterns between risk rising and falling segments, with a shift toward conflict cues in the rising phase, and a rebound toward stability cues in the falling phase. Attribution concentration increases only modestly at high perceived risk levels. These results move beyond treating perceived risk as a single severity score by characterising within episode dynamics and phase dependent cue associations in scripted motorway interactions.