Estimating Trust in Human-Robot Collaboration through Behavioral Indicators and Explainability

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Campagna, Giulio, Lagomarsino, Marta, Lorenzini, Marta, Chrysostomou, Dimitrios, Rehm, Matthias, Ajoudani, Arash
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911402950656000
author Campagna, Giulio
Lagomarsino, Marta
Lorenzini, Marta
Chrysostomou, Dimitrios
Rehm, Matthias
Ajoudani, Arash
author_facet Campagna, Giulio
Lagomarsino, Marta
Lorenzini, Marta
Chrysostomou, Dimitrios
Rehm, Matthias
Ajoudani, Arash
contents Industry 5.0 focuses on human-centric collaboration between humans and robots, prioritizing safety, comfort, and trust. This study introduces a data-driven framework to assess trust using behavioral indicators. The framework employs a Preference-Based Optimization algorithm to generate trust-enhancing trajectories based on operator feedback. This feedback serves as ground truth for training machine learning models to predict trust levels from behavioral indicators. The framework was tested in a chemical industry scenario where a robot assisted a human operator in mixing chemicals. Machine learning models classified trust with over 80\% accuracy, with the Voting Classifier achieving 84.07\% accuracy and an AUC-ROC score of 0.90. These findings underscore the effectiveness of data-driven methods in assessing trust within human-robot collaboration, emphasizing the valuable role behavioral indicators play in predicting the dynamics of human trust.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Estimating Trust in Human-Robot Collaboration through Behavioral Indicators and Explainability
Campagna, Giulio
Lagomarsino, Marta
Lorenzini, Marta
Chrysostomou, Dimitrios
Rehm, Matthias
Ajoudani, Arash
Robotics
Industry 5.0 focuses on human-centric collaboration between humans and robots, prioritizing safety, comfort, and trust. This study introduces a data-driven framework to assess trust using behavioral indicators. The framework employs a Preference-Based Optimization algorithm to generate trust-enhancing trajectories based on operator feedback. This feedback serves as ground truth for training machine learning models to predict trust levels from behavioral indicators. The framework was tested in a chemical industry scenario where a robot assisted a human operator in mixing chemicals. Machine learning models classified trust with over 80\% accuracy, with the Voting Classifier achieving 84.07\% accuracy and an AUC-ROC score of 0.90. These findings underscore the effectiveness of data-driven methods in assessing trust within human-robot collaboration, emphasizing the valuable role behavioral indicators play in predicting the dynamics of human trust.
title Estimating Trust in Human-Robot Collaboration through Behavioral Indicators and Explainability
topic Robotics
url https://arxiv.org/abs/2601.19856