A Unified Bi-directional Model for Natural and Artificial Trust in Human-Robot Collaboration

TL;DR

This paper presents a bi-directional trust model for human-robot collaboration that predicts trust based on task capabilities and agent beliefs, outperforming existing models in multi-task trust prediction.

Contribution

The paper introduces a novel capabilities-based bi-directional multi-task trust model that accounts for uncertainty in agent capabilities and applies to both humans and robots.

Findings

Model outperforms existing trust prediction models in human experiments.

Simulations demonstrate effectiveness for robotic trust assessment.

Applicable to control authority allocation in human-robot teams.

Abstract

We introduce a novel capabilities-based bi-directional multi-task trust model that can be used for trust prediction from either a human or a robotic trustor agent. Tasks are represented in terms of their capability requirements, while trustee agents are characterized by their individual capabilities. Trustee agents' capabilities are not deterministic; they are represented by belief distributions. For each task to be executed, a higher level of trust is assigned to trustee agents who have demonstrated that their capabilities exceed the task's requirements. We report results of an online experiment with 284 participants, revealing that our model outperforms existing models for multi-task trust prediction from a human trustor. We also present simulations of the model for determining trust from a robotic trustor. Our model is useful for control authority allocation applications that involve human-robot teams.