Driver-Automation Cooperation Oriented Approach for Shared Control of Lane Keeping Assist Systems
DOI: 10.1109/tcst.2018.2842211
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 designing shared lateral control for Lane Keeping Assist (LKA) systems, specifically focusing on resolving conflicts between human drivers and automation. Existing shared control methods often treat driver inputs as disturbances or fail to allow drivers to override automation, leading to potential safety issues and poor cooperation. The authors propose a novel "two-level cooperative control scheme" that combines system perception with robust control to adaptively share control authority. The goal is to ensure vehicle stability and tracking performance while minimizing driver-automation conflict through smooth transitions in control authority. The methodology relies on a human-in-the-loop vehicle (HiLV) model that integrates a bicycle model of vehicle lateral dynamics with a simplified two-level driver model. The driver model accounts for both compensatory behavior (tracking a near point) and anticipatory behavior (tracking a far point), allowing the system to predict driver intentions. The control architecture consists of two hierarchical parts: an operational part and a tactical part. The operational part employs two local optimal-based controllers designed for lane keeping and conflict management, respectively. The tactical part acts as a control supervisor that orchestrates smooth transitions between these controllers. This supervisor utilizes real-time data from driver monitoring systems (for state evaluation) and vehicle vision systems (for environment perception and risk assessment). The control design is formulated as a Linear Matrix Inequality (LMI) optimization problem, guaranteeing closed-loop stability via Lyapunov stability arguments. The study validates the proposed approach through hardware experiments conducted on the SHERPA dynamic driving simulator with human drivers. The experiments demonstrate that the shared control strategy effectively manages the transition of control authority between the driver and the LKA system. By incorporating real-time information on driver behavior and driving conditions, the system adapts its assistance level to avoid conflicting with the driver’s steering actions. The results confirm that the method maintains vehicle stability and tracking performance while significantly reducing the conflict between human and automated control inputs. The significance of this work lies in its ability to provide a rigorous, stability-guaranteed framework for driver-automation cooperation. Unlike previous approaches that either reject driver inputs or lack adaptive authority allocation, this method allows for simultaneous control where the driver can express intentions that either conform to or override the automation. This enhances mutual understanding between the driver and the system, improving safety and comfort in highway driving conditions. The use of LMI optimization ensures that the complex human-machine interaction is handled within a robust control framework, offering a practical solution for next-generation Advanced Driver Assistance Systems (ADAS).
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 | 2026-06-25 |
| archive | success | semantic_scholar | — | — | 6 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | success | openalex | — | — | 1 | 2026-06-26 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| 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