An fNIRS dataset for driving risk cognition of passengers in highly automated driving scenarios
DOI: 10.1038/s41597-024-03353-6
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper introduces a novel functional near-infrared spectroscopy (fNIRS) dataset designed to quantify the driving risk cognition of passengers in highly automated driving scenarios. The research is motivated by the shift in autonomous vehicle safety from driver-centric to passenger-centric monitoring, as human passengers act as critical sensors for detecting risks that automated algorithms may miss. While existing datasets focus on human drivers’ physiological and behavioral data, there is a lack of data regarding the mental activities of passengers. The authors aim to provide data support for distinguishing driving risk levels via brain-computer interface systems, potentially enabling the prevention of hazards in scenarios where risk remains high for extended periods before an incident occurs. The study collected data from 20 participants using a driving simulator equipped with a hardware-in-the-loop system. Participants acted as passengers, observing 12 tasks, each consisting of a virtual test drive segment containing 25 randomly selected scenarios from a library of 14 distinct highly automated driving situations. These scenarios included lead vehicle cut-outs, emergency braking, surrounding vehicle cut-ins, and pedestrian crossings, varying by distance and direction. An 8-channel fNIRS device monitored prefrontal cortex activity, recording raw intensity data convertible to oxy-hemoglobin ($\Delta$Hbo) and deoxy-hemoglobin ($\Delta$HbR) changes. The acquisition system also recorded vehicle kinematic data (position, velocity, acceleration) and participant responses to auditory stimuli to ensure attention. Data were synchronized and segmented into low-risk and high-risk episodes based on calculated risk fields derived from scenario dynamics. The dataset, made available on OpenNeuro, includes raw fNIRS intensity data, driving scenario parameters, and split points defining risk episodes. Preliminary analysis of four scenario types, specifically focusing on cut-in events, demonstrated that high-risk scenarios induce significant changes in prefrontal cortex activity. The authors verified the rationality of episode division through data summary charts and noted a positive correlation between scenario risk and mental activity in Brodmann area 10. Although only a subset of the 14 scenario types has been fully analyzed in prior publications, this dataset provides comprehensive coverage of all 14 types, including raw data for the remaining ten unanalyzed scenarios. The significance of this work lies in its contribution to Safety of the Intended Functionality (SOTIF) for autonomous vehicles. By providing a standardized, open-access dataset of passenger brain activity correlated with specific driving risks, the study facilitates the development of brain-computer interface systems capable of real-time risk assessment. This resource supports future research into passenger-in-the-loop decision-making and offers a pathway to mitigate functional insufficiencies in automated driving algorithms by leveraging human cognitive perception of risk.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 3 | 2026-08-10 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 11 | 2026-08-11 |
| verify | success | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data
- Methodological Resource: tool software, dataset resource