Automated driving
DOI: 10.1145/3380963
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 critical challenge of maintaining effective human-automation interaction in automated driving systems. The authors argue that while automated vehicles are often portrayed as fully replacing human drivers, current technology necessitates a partnership where humans remain active participants. The research is motivated by the unique characteristics of automated driving: it involves time-sensitive, safety-critical scenarios; it is used by nonprofessional users who lack specialized training; and it operates within embodied, situated physical systems. The authors contend that Human-Computer Interaction (HCI) is essential for designing these systems to ensure safety, accessibility for diverse user populations, and effective management of driver attention during non-driving tasks. The paper employs a theoretical review and conceptual framework approach rather than empirical experimentation. It synthesizes insights from 50 years of human-automation interaction research and applies interruption theory to the specific context of automated driving. A key methodological contribution is the proposal of a "negotiated attention interleaving" framework. This framework reinterprets the "transition of control"—when a vehicle requests the human to resume driving—not as a simple task switch, but as a complex interruption process. The authors utilize hidden Markov models as a formal tool to systematically analyze and design for "mode confusion," a state where a driver’s belief about the system’s functionality diverges from its actual state due to dynamic changes in system behavior or environmental conditions. The findings highlight the "irony of automation," where reducing basic driving tasks leads drivers to engage in non-driving activities, thereby reducing situational awareness and slowing responses to safety-critical events. The authors identify that both humans and automated systems are dynamic; humans reappropriate technology and suffer from skill decay, while systems change via software updates and environmental learning. This dynamism creates risks of mode confusion. The proposed framework decomposes the transition of control into multiple stages, including pre-alerts, attention interleaving between the original task and driving, and resumption of the original task. The authors argue that current research overly focuses on minimizing the time between alert and physical action, whereas interruption literature suggests that allowing time for careful preparation and interleaving reduces workload, stress, and mental distraction. The significance of this work lies in its call to keep the human in the loop through better-designed HCI interventions. By applying interruption theories to automated driving, the authors provide a structured way to understand and design for transitions of control, moving beyond simplistic alert-response models. This approach allows designers to target specific stages of the interruption process to improve safety and user experience. The paper concludes that HCI methods and theories are critical for the safe exploitation of automated vehicles, offering a bridge between engineering developments and human behavioral insights. It emphasizes that successful automated driving requires intuitive systems that account for the dynamic nature of human belief and system functionality, ensuring that nonprofessional users can safely navigate the complexities of shared control.
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 | 2026-06-17 |
| archive | success | openalex | — | — | 5 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-25 |
| clean | success | clean | — | — | 1 | 2026-06-20 |
| chunk | success | chunk | — | — | 1 | 2026-06-20 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-20 |
| enrich | success | openalex | — | — | 1 | 2026-06-20 |
| promote | success | — | — | — | 1 | 2026-06-17 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-25 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-20 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-25; 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).
- Theoretical Contribution: conceptual framework