Human reliability analysis in situated driving context considering human experience using a fuzzy-based clustering approach
DOI: 10.1109/ichms53169.2021.9582451
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 critical need for dynamic human reliability analysis (HRA) in the context of advanced driver assistance systems (ADAS) and automated driving. While human error accounts for 94% of traffic accidents, existing HRA methods, such as the Cognitive Reliability and Error Analysis Method (CREAM), typically evaluate human performance statically, failing to account for the continuously changing nature of driving situations. The authors aim to bridge this gap by developing a data-driven approach that quantifies human driver experience (HDE) and evaluates human reliability in real-time within a situated driving context, thereby reducing reliance on expert knowledge. To achieve this, the study adapts the CREAM framework by generating a new list of Common Performance Conditions (CPCs) specific to driving, including variables such as time to collision, ego-vehicle speed, and acceleration. The core innovation involves the quantitative characterization of HDE using three specific variables: ego-vehicle speed, longitudinal acceleration, and lateral acceleration. To determine the levels and membership functions for these CPCs and HDE variables without manual expert tuning, the authors employ a fuzzy neighborhood density-based spatial clustering algorithm with noise (FN-DBSCAN). A genetic algorithm is integrated to automatically optimize the clustering parameters, ensuring the membership functions accurately reflect driving data distributions. The experimental validation utilized a driving simulator (SCANeRT M studio) to collect data from participants across different scenarios. The results demonstrate that the proposed method successfully generates dynamic membership functions for CPCs and HDE variables. The study introduces a new metric, the Human Performance Reliability Score (HPRS), which combines the Human Driver Reliability Score (HDRS) derived from CPCs with the quantified HDE. Analysis of the HPRS over time revealed that it fluctuates dynamically, primarily influenced by longitudinal and lateral acceleration. Unlike previous methods that produced discrete, jumping integer values, this fuzzy-based approach yields continuous scores, allowing for a more granular assessment of control modes (e.g., strategic, tactical, opportunistic). The HPRS values in the tested scenarios remained above the opportunistic level, indicating stable performance. The significance of this work lies in its ability to provide a formalized, numerical quantification of human driver experience and reliability in dynamic contexts. By automating the generation of membership functions through fuzzy clustering and genetic algorithms, the method reduces subjectivity and enables real-time, online estimation of human reliability. This approach lays the foundation for safer human-machine transitions in automated vehicles, particularly during takeover scenarios where immediate assessment of driver capability is crucial. The study concludes that this data-driven, fuzzy-based adaptation of CREAM is a viable step toward continuous monitoring of driver reliability, addressing the limitations of static analysis in complex, evolving driving environments.
Key finding
The proposed fuzzy-based clustering approach successfully quantifies human driver experience and calculates a dynamic human performance reliability score that varies in real-time based on driving variables and context.
Methodology
simulation_modeling
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 | — | — | 7 | 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 | — | — | — | 1 | 2026-05-28 |
| 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).
- Methodological Resource: validation psychometrics, tool software
- Theoretical Contribution: computational model