Classification of Automated Lane-Change Styles by Modeling and Analyzing Truck Driver Behavior: A Driving Simulator Study

Wang, Zheng; Guan, Muhua; Lan, Jin; Yang, Bo; Kaizuka, Tsutomu; Taki, Junichi; Nakano, Kimihiko · 2022 · IEEE Open Journal of Intelligent Transportation Systems

DOI: 10.1109/ojits.2022.3222442

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of improving driver acceptance for automated lane-change systems in commercial trucks. While automation reduces workload and enhances safety, drivers often reject systems that do not align with their personal driving styles or expectations. The authors propose a method to design automated lane-change systems with distinct decision-making styles—aggressive, medium, and conservative—by modeling and analyzing the behavior of professional truck drivers. The research aims to determine if these distinct styles can be distinguished by drivers and evaluated as safe and reliable from both the ego vehicle’s perspective and that of surrounding traffic. The methodology involved two phases of driving simulator experiments with 12 professional truck drivers. In the first phase, participants performed discretionary lane changes in a simulated highway environment where a lead vehicle decelerated, prompting a lane change. The simulator featured a real truck cabin, motion platform, and high-fidelity visuals. Data on relative distances to surrounding vehicles, longitudinal acceleration, and maneuver duration were recorded to identify parameters for a discrete gap-acceptance model. These parameters were classified into three styles using the 25th, 50th, and 75th percentiles of the observed data. In the second phase, the same participants evaluated the automated system implementing these three styles. They experienced the automation from two perspectives: as the driver of the automated ego vehicle (Scenario A) and as the driver of a surrounding vehicle affected by the lane change (Scenario B). The results demonstrated that drivers could clearly distinguish between the aggressive, medium, and conservative automated lane-change styles. The aggressive style utilized smaller gap thresholds (approximately 42 meters), while the conservative style required larger gaps (approximately 58 meters). Subjective evaluations indicated that all three styles were perceived as safe and reliable by the participants. The study confirmed that the automated system’s behavior aligned with human expectations for each style category, validating the hypothesis that percentile-based parameter selection creates distinguishable and acceptable driving behaviors. The significance of this work lies in its contribution to human-centered automation design for commercial vehicles. By providing a framework to classify and implement different driving styles, the study offers insights into creating adaptable automated systems that cater to individual driver preferences and situational needs. This approach can enhance user acceptance and comfort in automated trucking, addressing the critical need for human-machine cooperation in intelligent transportation systems. The findings suggest that incorporating variable driving styles into automated systems is a viable strategy for improving the integration of automation into professional driving contexts.

Key finding

Drivers were able to distinguish between aggressive, medium, and conservative automated lane-change styles and evaluated all three as safe and reliable.

Methodology

simulator

Sample size: 12

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.

StageOutcomeToolModelPromptAttemptsCompleted
discover success 1 2026-05-07
archive success canonical_url 12 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 semantic_scholar 2 2026-06-04
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.

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).