Towards Cooperative Driving: Involving the Driver in an Autonomous Vehicle's Decision Making
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 addresses the challenge of maintaining autonomous driving functionality when vehicles encounter system limitations or uncertainties, such as obstacles or ambiguous traffic situations. Current approaches often require full handovers of control to the driver, which can be disruptive and unsafe if the driver is disengaged. The authors propose a "cooperative driving" model where the vehicle and driver collaborate through a multimodal interface. Instead of demanding immediate manual control, the system presents specific propositions (e.g., "pass obstacle" or "stop") for the driver to approve or reject, allowing the vehicle to continue autonomous operation if a safe option is selected. To evaluate this concept, the researchers conducted a within-subject driving simulator study with 32 licensed participants. The experimental design involved a cooperative assistant prototype displayed on a tablet in the center console, utilizing visual and auditory cues. Participants encountered scenarios involving a broken-down vehicle, varying in complexity (simple vs. complex traffic context) and proposition executability (legal vs. illegal maneuvers). The study manipulated two independent variables: the number of options presented (two or three) and the input modality (touch vs. speech). Participants were distracted by watching movie trailers during autonomous phases to simulate real-world disengagement. The system provided a time budget for interaction, after which it would request a takeover if no decision was made. The results indicated that participants felt comfortable using the cooperative interface and were capable of assessing situations safely without relying blindly on the system. The study measured interaction duration, proposition selection, and user-reported comfort, distraction, and trust. Participants successfully handled both simple and complex scenarios, often choosing to take over control when the system’s propositions violated traffic regulations or were unsafe. The multimodal interface effectively alerted disengaged drivers, and the ability to select via touch or speech provided flexibility. The findings suggest that cooperative interfaces can minimize unnecessary handovers while maintaining safety, as drivers remained engaged enough to make informed decisions. The significance of this work lies in its contribution to human-machine cooperation in automated driving. By involving the driver in decision-making at system boundaries rather than forcing full control handovers, the approach enhances convenience and potentially safety. The study provides empirical evidence that drivers can effectively collaborate with autonomous systems using multimodal interfaces, even when initially disengaged. This supports the development of Level 3 and 4 automation systems that can handle everyday driving uncertainties more gracefully, reducing driver annoyance and improving the overall user experience of autonomous vehicles.
Key finding
Participants in a driving simulator study felt comfortable using cooperative interfaces to resolve autonomous vehicle uncertainties and were able to handle all situations safely by assessing the context rather than relying blindly on the system.
Methodology
simulator
Sample size: 32
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 | — | — | — | 1 | 2026-05-07 |
| archive | success | canonical_url | — | — | 7 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-07 |
| promote | success | — | — | — | 1 | 2026-05-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- automation
- situational awareness
- automation surprise
- mode awareness
- takeover transitions
- acceptance adoption
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: conceptual framework, theory or model