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

TL;DR

This paper presents a data-driven framework that uses behavioral indicators and explainability to assess trust in human-robot collaboration, achieving over 80% accuracy in a chemical industry scenario.

Contribution

It introduces a novel framework combining behavioral indicators, preference-based optimization, and machine learning to predict trust levels in human-robot interactions.

Findings

Machine learning models classified trust with over 80% accuracy.

The Voting Classifier achieved 84.07% accuracy and 0.90 AUC-ROC.

Behavioral indicators effectively predict trust dynamics.

Abstract

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.