Real-Time Estimation of Drivers' Trust in Automated Driving Systems
DOI: 10.1007/s12369-020-00694-1
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 real-time trust estimation in automated driving systems (ADS) to mitigate trust miscalibration, such as overtrust or undertrust. Traditional self-reporting methods are impractical for continuous monitoring due to disruption and bias. The authors propose a framework using a Kalman filter-based approach to estimate drivers’ trust dynamically based on observable behaviors, avoiding intrusive psychophysiological sensors. The study employed a simulated SAE Level 3 ADS with 80 participants. Drivers performed a non-driving-related task (NDRT) while the system issued true alarms, false alarms, or misses. Trust dynamics were modeled using a discrete, linear time-invariant state-space model. The estimator integrated three observation variables: ADS usage time ratio, focus time ratio on the NDRT (measured via eye-tracking), and NDRT performance. Model parameters were identified using maximum likelihood estimation from 76 participants, with four held out for validation. Results demonstrated that the proposed estimator successfully computed trust estimates over successive interactions. Accuracy improved as participants interacted with the system, with estimates converging toward self-reported trust levels. The model effectively captured trust variations induced by system errors. These findings validate the use of behavioral cues for robust, real-time trust estimation. This approach enables the development of trust-aware ADS capable of adapting behaviors to align driver trust with system reliability, enhancing safety and acceptance in human-robot interaction.
Key finding
Kalman filter approach successfully computes trust estimates over successive interactions between driver and automated driving system, demonstrating feasibility of real-time trust measurement for designing trust-aware automated vehicles.
Methodology
lab_experiment
Sample size: 80
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_normalize on 2026-05-27 (2 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-05 |
| archive | success | canonical_url | — | — | 2 | 2026-06-02 |
| extract | success | cached | — | — | 2 | 2026-06-07 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | crossref | — | — | 2 | 2026-06-04 |
| promote | success | — | — | — | 2 | 2026-06-06 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-07 |
| tag | success | vector_similarity | — | — | 16 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-05-08 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-07; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- trust calibration
- trust in automation foundations
- automation
- automation surprise
- situational awareness
- mode awareness
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).
- Empirical Findings: self report data
- Methodological Resource: validation psychometrics
- Theoretical Contribution: computational model