Clustering Trust Dynamics in a Human-Robot Sequential Decision-Making Task

TL;DR

This paper introduces a framework for trust-aware decision-making in human-robot teams, modeling trust dynamics and categorizing user trust behaviors to improve collaborative performance.

Contribution

It presents a novel trust update model, classifies trust dynamics into three types, and links personal traits to trust behavior predictions.

Findings

Trust model accurately captures trust changes

Participants cluster into three trust types

Personal traits predict trust dynamics

Abstract

In this paper, we present a framework for trust-aware sequential decision-making in a human-robot team. We model the problem as a finite-horizon Markov Decision Process with a reward-based performance metric, allowing the robotic agent to make trust-aware recommendations. Results of a human-subject experiment show that the proposed trust update model is able to accurately capture the human agent's moment-to-moment trust changes. Moreover, we cluster the participants' trust dynamics into three categories, namely, Bayesian decision makers, oscillators, and disbelievers, and identify personal characteristics that could be used to predict which type of trust dynamics a person will belong to. We find that the disbelievers are less extroverted, less agreeable, and have lower expectations toward the robotic agent, compared to the Bayesian decision makers and oscillators. The oscillators are significantly more frustrated than the Bayesian decision makers.