Driver Model Using Fuzzy Logic for Virtual Validation
DOI: 10.3233/atde240019
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 generating realistic traffic in virtual simulations for the validation of Advanced Driver Assistance Systems (ADAS) and autonomous driving technologies. While computer simulations reduce the time, cost, and risk associated with physical testing, they often fail to accurately reproduce human driver behavior, particularly rare or atypical reactions. To improve the reliability of these virtual validations, the authors propose a driver behavior model based on fuzzy logic that incorporates both objective factors (e.g., weather, road conditions) and subjective factors (e.g., fatigue, stress, personality). The work is part of the 3SA project, which aims to develop tools for testing delegated driving systems using digital simulation. The proposed model utilizes a hierarchical architecture inspired by Michon’s driving task model, consisting of strategic, tactical, and operational levels. The authors focus on the tactical level, which handles decision-making through a maneuver decision module influenced by driver motivation, intention, and state. In the first phase of implementation, the model uses fuzzy logic to select maneuvers based on the Time to Collision (TTC) with surrounding vehicles and the ego vehicle’s speed. The fuzzy controller employs triangular and trapezoidal membership functions defined by French road safety regulations. The system defines three distinct driver profiles—“Timid,” “Normal,” and “Reckless”—which dictate specific ranges for acceleration variation and steering angle changes. For instance, the “Timid” profile exhibits smoother acceleration but harder braking, while the “Reckless” profile prioritizes maintaining speed with abrupt acceleration. The model was validated using SCANeR Studio software co-simulated with Matlab/Simulink. The simulation scenario involved a four-lane highway where the ego vehicle, initially traveling at 90 km/h, encountered a preceding vehicle that significantly reduced its speed. The results demonstrated that the fuzzy logic model successfully reproduced distinct driving styles under identical initial conditions. The “Reckless” profile performed maneuvers at higher speeds and executed multiple overtakes to minimize deceleration. Conversely, the “Timid” profile spent more time decelerating, avoided high speeds, and performed fewer overtakes, resulting in a longer scenario completion time. The “Normal” profile maintained the speed limit without abrupt maneuvers, serving as a baseline reference. The significance of this work lies in its ability to generate more natural and diverse traffic patterns in numerical simulations, thereby enhancing the robustness of ADAS validation. By integrating driver personality and state into the decision-making process, the model moves beyond simple scenario replication to capture the variability of human behavior. The authors conclude that this approach effectively represents the influence of driver profiles on maneuver selection. Future work will involve expanding the model to include additional factors such as environmental conditions and driver workload, as well as validating the model against data from real drivers to further refine its accuracy.
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 | 2026-06-17 |
| archive | success | openalex | — | — | 5 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-25 |
| 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 | 2026-06-25 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-25; 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: validation psychometrics, tool software
- Theoretical Contribution: computational model