Driver Assistance System With a Dual Control Scheme: Effectiveness of Identifying Driver Drowsiness and Preventing Lane Departure Accidents
DOI: 10.1109/thms.2016.2549032
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 challenge of driver drowsiness, a leading cause of fatal traffic accidents, by developing and evaluating a driver assistance system (ADAS) with a dual control scheme. The system is designed to simultaneously perform vehicle safety control and identify the driver’s state, specifically targeting the prevention of lane departure accidents caused by sleepiness. Unlike traditional systems that merely warn drivers or fully take over control, this approach uses partial control to assess whether the driver maintains appropriate situation awareness. The motivation stems from the limitations of existing warning systems, which may fail if a drowsy driver is unable or unwilling to respond, and fully automated systems, which do not account for the specific characteristics of sleepy drivers. The researchers implemented a two-stage control algorithm based on adaptive dual control theory. In the first stage, when the system predicts a lane departure within one second, it applies partial steering torque to keep the vehicle parallel to the lane markers but not centered, leaving the remaining control to the driver. If the driver corrects the steering within five seconds, the system assumes the driver is alert and disengages. If the driver fails to act, the system executes a second-stage control to center the vehicle. Repeated activation of these controls indicates a loss of situation awareness due to drowsiness. The system uses steering torque control to allow driver intervention and employs a gain adjustment mechanism to minimize conflict between human and system inputs. To validate the system, the authors conducted a driving simulator experiment with twenty student participants. The participants drove on a straight, two-lane expressway at a constant speed of 100 km/h, performing only lateral control tasks across three trials scheduled during typical drowsiness periods (afternoon). Drowsiness was induced by restricting caffeine intake and scheduling drives after lunch. Driver state was monitored using objective measures, such as eyelid opening and blink counts via a Smart Eye system, and subjective assessments using the Kitajima sleepiness scale. Lane-keeping performance and system intervention frequencies were recorded at 120 Hz. The results validated the hypothesis that drowsy drivers fail to implement necessary corrective steering actions, leading to repeated activations of the assistance system’s safety controls. The study demonstrated that the dual control scheme effectively identifies driver drowsiness by observing the interaction between the driver and the system. Furthermore, algorithms used to determine whether a driver could continue driving were evaluated through leave-one-out cross-validation and proven effective. The findings suggest that this adaptive assistance method, which provides support only when necessary and identifies drowsiness through behavioral response to partial control, is a viable strategy for preventing sleep-related lane departure accidents.
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 | OpenAlex-citations | — | — | 1 | 2026-06-19 |
| archive | success | unpaywall | — | — | 2 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-19 |
| chunk | success | chunk | — | — | 1 | 2026-06-19 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-19 |
| promote | success | — | — | — | 1 | 2026-06-19 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-19 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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).
- Methodological Resource: tool software
- Theoretical Contribution: computational model