PPTP: Performance-Guided Physiological Signal-Based Trust Prediction in Human-Robot Collaboration

TL;DR

This paper presents PPTP, a novel framework that uses physiological signals and collaboration performance to accurately predict human trust levels in human-robot construction tasks, enhancing safety and efficiency.

Contribution

The study introduces a new multimodal physiological signal-based trust prediction framework guided by collaboration performance, achieving high accuracy and addressing individual physiological variability.

Findings

Over 81% accuracy in three-level trust classification

74.3% accuracy in seven-level trust classification

Outperforms baseline methods by 6.7%

Abstract

Trust prediction is a key issue in human-robot collaboration, especially in construction scenarios where maintaining appropriate trust calibration is critical for safety and efficiency. This paper introduces the Performance-guided Physiological signal-based Trust Prediction (PPTP), a novel framework designed to improve trust assessment. We designed a human-robot construction scenario with three difficulty levels to induce different trust states. Our approach integrates synchronized multimodal physiological signals (ECG, GSR, and EMG) with collaboration performance evaluation to predict human trust levels. Individual physiological signals are processed using collaboration performance information as guiding cues, leveraging the standardized nature of collaboration performance to compensate for individual variations in physiological responses. Extensive experiments demonstrate the efficacy of our cross-modality fusion method in significantly improving trust classification performance. Our model achieves over 81% accuracy in three-level trust classification, outperforming the best baseline method by 6.7%, and notably reaches 74.3% accuracy in high-resolution seven-level classification, which is a first in trust prediction research. Ablation experiments further validate the superiority of physiological signal processing guided by collaboration performance assessment.