DEV: A Driver-Environment-Vehicle Closed-Loop Framework for Risk-Aware Adaptive Automation of Driving
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 limitations of static driving automation levels, such as the SAE taxonomy, which fail to support effective real-time cooperation between human drivers and automated systems. The authors argue that fixed automation levels contribute to risks like driver disengagement, reduced situation awareness, and mode confusion. To mitigate these issues, the paper proposes the DEV (Driver-Environment-Vehicle) framework, a closed-loop system designed for risk-aware adaptive automation. The framework aims to dynamically adjust the operational level of vehicle automation based on the continuous interplay between the driver’s state, the complexity of the driving environment, and the vehicle’s available automation resources. The DEV framework is structured around three core components, each quantified by a specific index. First, Driver Involvement is measured via the Driver Involvement Deficit (DID), which estimates the proportion of cognitive, perceptual, and physical resources unavailable for driving due to factors like drowsiness, distraction, or lack of willingness. Second, Environment Complexity is assessed using the Environment Complexity Index (ECI), which reflects the resource demands placed on the driver by contextual factors such as traffic density, road geometry, and visibility. Third, Vehicle Engagement is quantified by the Vehicle Engagement Index (VEI), representing the proportion of automation features available within the vehicle’s Operational Design Domain (ODD). The framework integrates these indices to perform real-time risk assessment, defined as the likelihood of adverse outcomes resulting from the interaction of these three elements. The authors formalize the relationship between these components by analyzing the cumulative deficit (CD) derived from the Driver Involvement Deficit and Vehicle Engagement Deficit. They identify a high-risk region where the combined resources of the driver and vehicle are insufficient to safely perform the driving task, necessitating proactive measures such as automated safety stops. Conversely, they identify a low-risk region characterized by resource redundancy, where the system can optimize cooperation by selecting an appropriate operational automation level. The framework suggests that in low-complexity environments, automation can assume more responsibility, whereas high-complexity scenarios require greater driver involvement. The paper also highlights the importance of cooperation modes, such as shared or traded control, in mitigating risk. The significance of this work lies in providing a comprehensive theoretical foundation for developing dynamic, risk-aware driving automation systems. By moving beyond static automation levels, the DEV framework offers a structured approach to aligning multidisciplinary research efforts in human-machine interaction. The authors conclude that future work must focus on developing reliable estimation methods for the proposed indices, empirically validating risk assessment models, and designing human-machine interfaces that facilitate clear understanding and trust. This framework serves as a guide for creating systems that ensure smooth transitions of control and maintain optimal safety through adaptive cooperation between humans and machines.
Key finding
The DEV framework provides a structured method for dynamically adjusting driving automation levels based on real-time assessments of driver involvement, environment complexity, and vehicle engagement to minimize driving risk.
Methodology
theoretical
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 oa_check on 2026-05-27.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-07 |
| archive | success | openalex | — | — | 6 | 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 | 2026-06-04 |
| 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
- automation complacency bias
- mode awareness
- driverless ads
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