Open Human-Robot Collaboration using Decentralized Inverse Reinforcement Learning

TL;DR

This paper introduces a new framework for open human-robot collaboration that allows agents to join or leave tasks flexibly, and extends inverse reinforcement learning to learn in these open systems, demonstrated in firefighting and assembly tasks.

Contribution

It proposes the oDec-MDP framework for modeling open HRC scenarios and generalizes Dec-AIRL for learning in these environments, advancing flexible multiagent collaboration.

Findings

Framework improves collaboration efficiency over closed systems.

Method successfully applied in firefighting and assembly domains.

Open model enables agents to manage multiple tasks flexibly.

Abstract

The growing interest in human-robot collaboration (HRC), where humans and robots cooperate towards shared goals, has seen significant advancements over the past decade. While previous research has addressed various challenges, several key issues remain unresolved. Many domains within HRC involve activities that do not necessarily require human presence throughout the entire task. Existing literature typically models HRC as a closed system, where all agents are present for the entire duration of the task. In contrast, an open model offers flexibility by allowing an agent to enter and exit the collaboration as needed, enabling them to concurrently manage other tasks. In this paper, we introduce a novel multiagent framework called oDec-MDP, designed specifically to model open HRC scenarios where agents can join or leave tasks flexibly during execution. We generalize a recent multiagent inverse reinforcement learning method - Dec-AIRL to learn from open systems modeled using the oDec-MDP. Our method is validated through experiments conducted in both a simplified toy firefighting domain and a realistic dyadic human-robot collaborative assembly. Results show that our framework and learning method improves upon its closed system counterpart.