Assessing Drivers' Situation Awareness in Semi-Autonomous Vehicles: ASP based Characterisations of Driving Dynamics for Modelling Scene Interpretation and Projection
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the critical safety challenge of driver takeover in semi-autonomous vehicles, specifically focusing on how to assess and support a driver’s situation awareness when automation requests human control. The authors argue that seamless cooperation between driver and system requires the automation to understand the driver’s mental state, particularly during handover scenarios where the driver must quickly interpret the traffic scene and project future dynamics to drive safely. To address this, the paper presents SituSYS, a modular software and hardware framework designed to detect, interpret, and guide driver attention based on their situational awareness. The system is implemented within the Robot Operating System (ROS) and consists of three layers: sensing, modeling, and human-machine interface (HMI). The sensing layer utilizes vehicle sensors for environmental data and mobile eye-tracking (PupilLabs) to record driver gaze. The core contribution is the modeling layer, which employs Answer Set Programming (ASP) to reason about the driver’s interpretation (Level 2) and projection (Level 3) of the scene, based on Endsley’s model of situation awareness. The system calculates fixation probabilities for scene objects to estimate what the driver perceives (Level 1). It then uses a hybrid Python-ASP process to generate an interpretation model of the driver’s current mental belief state and a projection model of possible future events, such as lane changes, using Event Calculus logic. The authors validated the approach through a case study in a driving simulator involving a takeover scenario at a construction site where the ego vehicle’s lane ended. The system successfully maintained a real-time representation of the scene (operating at approximately 30 Hz) and identified gaps and spatial configurations relevant to the driver’s task. By comparing the driver’s interpreted scene against the ground truth from vehicle sensors, the system generated a prioritized list of diverging elements to guide the driver’s attention via the HMI. The ASP-based reasoning correctly identified possible lane change events consistent with the driver’s task and the current traffic dynamics. The significance of this work lies in demonstrating that declarative logic programming, specifically ASP, can effectively model complex cognitive functions like scene interpretation and projection in real-time driving contexts. The framework provides a foundation for human-centered assistance systems that can adaptively guide driver attention to critical, missed elements during takeover requests. While the paper confirms the technical feasibility and real-time capability of the ASP-based modeling, it notes that long-term empirical studies are required to fully assess the system’s impact on driving performance and safety.
Key finding
An ASP-based declarative framework integrated with eye-tracking and scene sensors provides transparent symbolic modelling of driver SA (perception/comprehension/projection) during semi-autonomous takeover, demonstrated in simulated and real driving.
Methodology
lab_experiment
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. Discovered via discover_arxiv on 2026-05-04 (5 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | arxiv | — | — | 3 | 2026-05-04 |
| archive | success | — | — | — | 1 | 2026-05-04 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | normalization | — | — | 2 | 2026-05-28 |
| promote | success | — | — | — | 1 | 2026-05-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 17 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
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).
- Theoretical Contribution: conceptual framework, theory or model, computational model