Beyond object identification: How train drivers evaluate the risk of collision

TL;DR

This study investigates how train drivers assess collision risk by analyzing their cues and reasoning processes, highlighting the importance of understanding human judgment to improve train safety and AI systems.

Contribution

It provides detailed insights into train drivers' risk evaluation cues and inference processes, informing the development of better safety systems and AI assistance.

Findings

Drivers consider actions and mental states of people involved.

Risk evaluations involve concept relations and inferences.

Inferences vary systematically across different situations.

Abstract

When trains collide with obstacles, the consequences are often severe. To assess how artificial intelligence might contribute to avoiding collisions, we need to understand how train drivers do it. What aspects of a situation do they consider when evaluating the risk of collision? In the present study, we assumed that train drivers do not only identify potential obstacles but interpret what they see in order to anticipate how the situation might unfold. However, to date it is unclear how exactly this is accomplished. Therefore, we assessed which cues train drivers use and what inferences they make. To this end, image-based expert interviews were conducted with 33 train drivers. Participants saw images with potential obstacles, rated the risk of collision, and explained their evaluation. Moreover, they were asked how the situation would need to change to decrease or increase collision risk. From their verbal reports, we extracted concepts about the potential obstacles, contexts, or consequences, and assigned these concepts to various categories (e.g., people's identity, location, movement, action, physical features, and mental states). The results revealed that especially for people, train drivers reason about their actions and mental states, and draw relations between concepts to make further inferences. These inferences systematically differ between situations. Our findings emphasise the need to understand train drivers' risk evaluation processes when aiming to enhance the safety of both human and automatic train operation.