Data from "OptiCarVis: Improving Automated Vehicle Functionality Visualizations Using Bayesian Optimization to Enhance User Experience"

Authors

Pascal Jansen*, Mark Colley*, Svenja Krauß, Daniel Hirschle, Enrico Rukzio
(*Joint First Authors)

Citation

To cite this dataset, please use the following:

@inproceedings{Jansen2025Opticar,
author = {Pascal Jansen and Mark Colley and Svenja Krauß and Daniel Hirschle and Enrico Rukzio},
title = {OptiCarVis: Improving Automated Vehicle Functionality Visualizations Using Bayesian Optimization to Enhance User Experience},
year = {2025},
booktitle = {Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '25)},
location = {Yokohama, Japan},
pages = {April 26-May 1},
doi = {10.1145/3706598.3713514},
publisher = {ACM},
isbn = {979-8-4007-1394-1/25/04} }

Abstract

Automated vehicle (AV) acceptance relies on user understanding via feedback visualizations. Traditional "one-size-fits-all" designs are often suboptimal and resource-intensive. This study introduces OptiCarVis, a Human-in-the-Loop (HITL) Multi-Objective Bayesian Optimization (MOBO) framework for personalizing AV feedback visualizations. By leveraging subjective user feedback and computational optimization, OptiCarVis significantly improved perceived safety, trust, predictability, and acceptance while reducing cognitive load in a study with 117 participants. This dataset supports further research into personalized optimization for automotive UI design.

Dataset Description

The dataset includes:

Responses to trust, safety, cognitive load, predictability, and aesthetics metrics
Design parameters for each optimization iteration
Comparisons between cold-start, warm-start, and traditional design methods
Expert-generated standard design parameters

We also provide the R-scripts for the evaluation of the data.

Licensing

This dataset is shared under a Creative Commons Attribution (CC BY) license. You are free to use, adapt, and distribute this dataset with proper attribution to the authors.

Contact

For inquiries, please contact Pascal Jansen (pascal.jansen@uni-ulm.de) or Mark Colley (m.colley@ucl.ac.uk).

M-Colley/opticarvis-data