Modeling Driving Behavior at Roundabouts: Impact of Roundabout Layout and Surrounding Traffic on Driving Behavior
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the challenge of predicting driver behavior at roundabouts, a task motivated by the increasing prevalence of these intersections and the associated safety risks, particularly crashes involving cyclists. The research aims to develop models for driver behavior prediction, specifically focusing on whether drivers intend to leave the roundabout or continue circulating. The work builds upon previous field studies that utilized steering wheel status and machine learning algorithms to recognize driving intentions with high accuracy. The primary objective is to understand how two specific factors influence this recognition: the geometric layout of the roundabout and the presence of surrounding traffic, particularly cyclists. To investigate these factors, the authors conducted a simulator study involving thirteen participants (three females and ten males). The experimental design was divided into two parts corresponding to two research questions. For the first question regarding roundabout layout, the study manipulated two geometric factors: roundabout diameter (26 m and 40 m) and entry-exit angles (ranging from 90° to 270°). For the second question regarding surrounding traffic, the study introduced cyclists in four different positions relative to the driver. The simulator recorded various driving behavior variables, including position, velocity, acceleration, steering wheel position, and gaze/head direction. The results for the first research question demonstrated that steering wheel angle is quantitatively and logarithmically related to roundabout geometric features. This relationship allows for the prediction of driving behavior across generic roundabout designs based on their physical layout. Regarding the second research question, the presence of surrounding cyclists significantly impacted driving pattern recognition. Specifically, the accuracy of recognizing driving patterns reached 100% later in the presence of cyclists compared to scenarios without traffic, regardless of the cyclists' direction. However, the magnitude of this delay varied by position, with cyclists approaching from the left having the smallest impact on recognition timing. The significance of this work lies in its contribution to the development of more robust driver behavior prediction models for intelligent transportation systems. By establishing a logarithmic link between steering behavior and roundabout geometry, the study provides a basis for predicting driver intentions in diverse infrastructure settings. Furthermore, identifying the specific delays caused by vulnerable road users like cyclists highlights the need for adaptive systems that account for surrounding traffic conditions. These findings support the creation of safer, more responsive automated driving aids and traffic management systems that can better anticipate driver actions in complex intersection environments.
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 author_sweep_intake on 2026-05-28.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-28 |
| archive | success | canonical_url | — | — | 10 | 2026-06-09 |
| extract | success | cached | — | — | 2 | 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 | 2026-05-28 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 1 | 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).
- Theoretical Contribution: computational model