A Review of Shared Control for Automated Vehicles: Theory and Applications
DOI: 10.1109/thms.2020.3017748
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This review paper addresses the lack of a global synthesis regarding shared control in automated vehicles, a field characterized by increasing interest in Advanced Driver Assistance Systems (ADAS) that keep the driver in the loop. The authors aim to provide a comprehensive overview of the theory and applications of shared control, specifically focusing on systems with SAE automation levels 0–2. The motivation stems from the challenges of transitioning between partial and high automation, legal responsibility issues, and the need for cooperative systems that enhance driver performance and comfort without causing conflict or overtrust. The methodology involves a systematic review of scientific literature collected from databases like Google Scholar and Web of Science between June 2017 and August 2019. The authors classified contributions into theory-oriented and application-oriented categories. Theory-oriented articles were selected based on their contribution to definitions, arbitration, metaphors, and control frameworks. Application-oriented articles were filtered to include only those tested in simulation or real vehicles, using the steering wheel as the primary control interface, and adhering to specific shared control definitions. The review distinguishes between coupled (mechanically linked, haptic guidance) and uncoupled (input-mixing, drive-by-wire) control mechanisms, as well as model-based and model-free algorithms. The findings clarify the theoretical landscape, defining shared control as a congruent, simultaneous interaction between human and machine on the same task, distinct from traded or cooperative control. The paper identifies key metaphors for design, such as the rider-horse and parent-child models, which emphasize bidirectional communication and proportional assistance based on risk. In terms of applications, lane keeping is the most prevalent use case, followed by obstacle avoidance and control resumption. The review highlights that driver-in-the-loop simulators are the dominant evaluation platform, with few studies conducted in real vehicles. Crucially, the analysis reveals that model-based controllers, which incorporate driver models, effectively reduce steering conflicts. Furthermore, variables such as driver state, effort, and safety indicators significantly influence the calculation of automation authority. The significance of this work lies in its structured categorization of shared control technologies, providing a clear distinction between coupled and uncoupled frameworks and their respective algorithmic approaches. By synthesizing theoretical definitions with empirical application results, the paper establishes a foundation for future developments in cooperative ADAS. It underscores the importance of arbitration mechanisms that harmonize driver and automation actions, suggesting that future implementations should leverage driver modeling to minimize conflict and ensure safe, comfortable transitions in partially automated driving environments. The review also points to the need for more real-vehicle testing and the potential expansion of shared control beyond steering to include longitudinal control interfaces.
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 | 2026-06-17 |
| archive | success | unpaywall | — | — | 2 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-18 |
| chunk | success | chunk | — | — | 1 | 2026-06-18 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-18 |
| promote | success | — | — | — | 1 | 2026-06-17 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| 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, conceptual framework