Adapting Behaviour Based On Trust In Human-Agent Ad Hoc Teamwork

TL;DR

This paper introduces a framework for human-agent ad hoc teamwork that dynamically infers trust levels and adapts agent behavior to improve collaboration and team performance in real-world scenarios.

Contribution

It presents a novel method for inferring trust and adapting agent behavior in human-agent teams, validated through real-world experiments.

Findings

Trust-aware adaptive behavior improves team performance.

The framework effectively infers trust levels from observations.

Adaptive strategies influence trust dynamics positively.

Abstract

This work proposes a framework that incorporates trust in an ad hoc teamwork scenario with human-agent teams, where an agent must collaborate with a human to perform a task. During the task, the agent must infer, through interactions and observations, how much the human trusts it and adapt its behaviour to maximize the team's performance. To achieve this, we propose collecting data from human participants in experiments to define different settings (based on trust levels) and learning optimal policies for each of them. Then, we create a module to infer the current setting (depending on the amount of trust). Finally, we validate this framework in a real-world scenario and analyse how this adaptable behaviour affects trust.