Human-Machine Shared Driving Control for Semi-Autonomous Vehicles Using Level of Cooperativeness

Nguyen, Anh-Tu; Rath, Jagat Jyoti; Lv, Chen; Guerra, Thierry-Marie; Lauber, Jimmy · 2021 · Crossref

DOI: 10.3390/s21144647

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 managing human-machine interaction (HMI) in semi-autonomous vehicles, specifically focusing on lane-keeping assistance. The authors identify that conflicts often arise between human drivers and automation systems during complex maneuvers, such as obstacle avoidance or sharp curve navigation, when their control inputs oppose each other. To mitigate these conflicts and improve driving safety and comfort, the study proposes a novel haptic shared control architecture that dynamically adjusts the level of automation assistance based on the driver’s cooperativeness and workload. The methodology employs a driver-in-the-loop (DiL) vehicle model that integrates vehicle yaw-slip dynamics, steering column dynamics, and a dynamic driver model representing compensatory and anticipatory behaviors. A key innovation is the introduction of a "cooperative index" calculated from the product of driver and automation torques over a time window. This index determines the cooperative status: fully cooperative when torques align, and non-cooperative when they oppose. Based on this status and the driver’s torque input, a driver activity variable is computed to determine the required level of haptic authority. This authority is translated into a time-varying assistance factor that modulates the assistance torque. To handle the time-varying nature of both the assistance factor and vehicle speed, the control law is designed using a polytopic linear parameter-varying (LPV) framework. Lyapunov stability theory is applied to guarantee closed-loop stability and $\ell_\infty$-gain performance, ensuring robustness against bounded disturbances like road curvature. The proposed control scheme was validated through high-fidelity simulations under various driving conditions, including different road curvatures and parametric uncertainties. The results demonstrate that the shared control method effectively manages driver-automation conflicts by reducing automation authority during non-cooperative scenarios, thereby allowing the human driver to maintain dominant control when necessary. Conversely, during cooperative states, the system provides appropriate assistance to support the driver. The simulations indicate significant improvements in lane tracking accuracy, vehicle stability, and driving comfort compared to fixed-assistance or non-shared control strategies. The significance of this work lies in its integration of HMI management directly into the control loop design, rather than treating it as a separate layer. By explicitly accounting for the cooperative status and driver workload, the proposed LPV-based shared control approach offers a robust solution for semi-autonomous vehicles. It enhances safety by minimizing conflicting inputs and improves user acceptance by adapting assistance levels to the driver’s real-time performance and intent. This framework provides a foundation for more intuitive and effective human-machine collaboration in conditional automation systems.

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.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified_with_issues.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• automation

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: computational model, conceptual framework