Handling Trust Between Drivers and Automated Vehicles for Improved Collaboration
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This extended abstract outlines research aimed at improving safety and performance in human-robot interactions, specifically within the context of drivers and automated vehicles (AVs). The work is motivated by the transition from traditional automation to robotic teammates, where trust dynamics become bidirectional. The primary problem addressed is trust miscalibration, where drivers either undertrust (disuse) or overtrust (misuse) AV capabilities, leading to safety risks. The author proposes two core research questions: how an AV can measure, process, and influence a driver’s trust to prevent miscalibration, and whether an AV can assess its own trust in the driver to optimize control switching. To address the first question, the author developed a control engineering-based framework for real-time trust estimation and calibration. This method utilizes a Kalman filter to fuse real-time data from multiple sources, including eye-tracking devices, the driver’s usage rate of AV self-driving functions, and performance on non-driving related tasks. These observable variables were matched with self-reported trust levels to model trust dynamics. Experiments were conducted using simulations of SAE Level 3 automated driving systems to fit the model. The resulting trust management framework allows the AV to detect miscalibrations by comparing the estimated trust against the AV’s actual capabilities in specific driving contexts. Upon detecting a mismatch, the AV triggers verbal interactions with tailored communication styles and messages to provide situation awareness and risk assessments, thereby encouraging the driver to recalibrate their trust. Regarding the second question, the paper describes current work on developing a bi-directional trust model that represents both the driver’s trust in the AV and the AV’s trust in the driver. This model treats trust as the probability of task success, computed using Bayesian processes to dynamically update beliefs about an agent’s capabilities relative to task requirements. The framework defines metric spaces for tasks and agent capabilities, allowing the AV to assess whether a driver possesses the necessary cognitive, physical, and sensory skills for specific driving conditions. The significance of this research lies in its potential to facilitate seamless collaboration in human-robot teams by moving beyond the traditional tool-operator paradigm to a teammate-teammate dynamic. By enabling AVs to autonomously estimate and process trust in both directions, the system can improve task allocation and negotiation between humans and robots. The author concludes that such bi-directional trust modeling is fundamental for assigning tasks based on capabilities and trust, ultimately enhancing teamwork and safety in automated driving and broader human-robot interaction contexts.
Key finding
A trust management framework using real-time estimation and verbal communication successfully identified and corrected driver trust miscalibration in simulated automated driving scenarios.
Methodology
simulator
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 unpaywall on 2026-05-06 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-28 |
| archive | success | canonical_url | — | — | 16 | 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 | openalex | — | — | 2 | 2026-05-08 |
| promote | success | — | — | — | 1 | 2026-05-06 |
| 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.