Multi-Agent Strategy Explanations for Human-Robot Collaboration

TL;DR

This paper introduces a framework for generating visual and textual explanations of multi-agent strategies in human-robot collaboration, improving user understanding and collaboration efficiency.

Contribution

It presents a novel method for explaining multi-agent policies using landmark states and large language models, addressing a gap in explainable AI for collaborative settings.

Findings

Users better explore strategy space with explanations

Enhanced collaboration efficiency with new robot partners

Effective visual and textual explanation generation

Abstract

As robots are deployed in human spaces, it is important that they are able to coordinate their actions with the people around them. Part of such coordination involves ensuring that people have a good understanding of how a robot will act in the environment. This can be achieved through explanations of the robot's policy. Much prior work in explainable AI and RL focuses on generating explanations for single-agent policies, but little has been explored in generating explanations for collaborative policies. In this work, we investigate how to generate multi-agent strategy explanations for human-robot collaboration. We formulate the problem using a generic multi-agent planner, show how to generate visual explanations through strategy-conditioned landmark states and generate textual explanations by giving the landmarks to an LLM. Through a user study, we find that when presented with explanations from our proposed framework, users are able to better explore the full space of strategies and collaborate more efficiently with new robot partners.