Human-Centered Intervention Based on Tactical-Level Input in Unscheduled Takeover Scenarios for Highly-Automated Vehicles
DOI: 10.1007/s13177-019-00217-x
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the safety and efficiency challenges associated with unscheduled takeover requests in Level 3 highly-automated vehicles. When automated driving systems encounter functional limitations, such as unexpected roadworks or occluded signs, drivers must intervene abruptly. Because drivers often engage in non-driving related tasks during automation, these unscheduled takeovers can lead to insufficient situational awareness, increased workload, and dangerous driving situations. The authors propose a human-centered intervention method using Tactical-Level Input (TLI) via a multimodal Driver-Vehicle Interface (DVI). Unlike manual takeover, which requires immediate operational control of steering and pedals, TLI allows drivers to input medium-term commands (e.g., "turn right," "lane change") while the system retains lateral and longitudinal control, thereby reducing the cognitive and physical burden on the driver. The researchers designed a multimodal DVI system comprising touchscreen, hand-gesture, and haptic interfaces, supported by visual (LED indicators) and acoustic feedback to convey system status and takeover requests. To evaluate this system, they conducted experiments using a driving simulator with 11 participants. The experimental scenario involved an unscheduled takeover triggered by a simulated roadwork zone requiring a lane change. Participants performed three types of trials: manual driving, takeover using TLI, and manual takeover. During automated driving, participants engaged in a 2-back cognitive-visual task to simulate distraction. The study measured driver reaction time, physiological responses (skin conductance and heart rate via wristbands), and subjective workload using the NASA Task Load Index. The results demonstrated that TLI significantly improved takeover performance compared to manual takeover. The average driver reaction time for TLI was 4.27 seconds, significantly lower than the 6.27 seconds recorded for manual takeover ($p < 0.05$). Physiological data indicated that TLI reduced mental stress; maximum skin conductance values were lower in the TLI condition, and heart rates remained more stable compared to the spikes observed during manual takeover. Furthermore, subjective assessments revealed that TLI decreased workload across all NASA-TLX subscales, including mental, physical, and temporal demands. Most participants also expressed a preference for TLI over manual takeover. The significance of this research lies in its validation of TLI as a safer and more efficient method for handling unscheduled takeovers in conditional automation. By allowing drivers to interact at the tactical level rather than the operational level, the proposed DVI system mitigates the risks associated with sudden task switching and lack of situational awareness. The findings suggest that integrating multimodal interfaces with tactical command inputs can enhance driver-vehicle collaboration, reduce driver workload, and improve overall safety in Level 3 automated driving scenarios. This approach offers a practical pathway for designing human-centered automation systems that better accommodate human limitations during critical intervention moments.
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 | 2026-06-07 |
| archive | success | canonical_url | — | — | 1 | 2026-06-09 |
| extract | success | pdftotext | — | — | 2 | 2026-06-09 |
| clean | success | clean | — | — | 1 | 2026-06-09 |
| chunk | success | chunk | — | — | 1 | 2026-06-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-09 |
| promote | success | — | — | — | 1 | 2026-06-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-09 |
| tag | success | vector_similarity | — | — | 8 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-09 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-09; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- takeover transitions
- automation
- manual
- automation surprise
- control interfaces
- teleoperation remote driving
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: behavioral performance data
- Methodological Resource: measurement protocol
- Theoretical Contribution: conceptual framework