Adaptive Task Allocation in Multi-Human Multi-Robot Teams under Team Heterogeneity and Dynamic Information Uncertainty

2024-09-20

arXiv.org

AI Summary

Addressing the coupled challenges of agent heterogeneity, dynamic task evolution, and uncertain runtime state information in multi-human–multi-robot heterogeneous teams, this paper proposes ATA-HRL, an adaptive two-stage task allocation framework. ATA-HRL introduces a novel “initial assignment–condition-triggered reallocation” mechanism, integrated with hierarchical reinforcement learning (HRL) to enable cross-temporal-scale decision-making. To explicitly model and mitigate state uncertainty, it incorporates an auxiliary supervised state representation learning module. By unifying heterogeneous team modeling and enabling dynamic state awareness, ATA-HRL significantly improves task completion rate (+18.7%) and resource utilization (+22.3%) in large-scale environmental monitoring tasks. Extensive evaluations demonstrate superior robustness over existing state-of-the-art methods under varying uncertainty conditions and dynamic task arrivals.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Intelligent Robots: State Estimation
• Multiagent Systems: Teamwork

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Task allocation in multi-human multi-robot (MH-MR) teams presents significant challenges due to the inherent heterogeneity of team members, the dynamics of task execution, and the information uncertainty of operational states. Existing approaches often fail to address these challenges simultaneously, resulting in suboptimal performance. To tackle this, we propose ATA-HRL, an adaptive task allocation framework using hierarchical reinforcement learning (HRL), which incorporates initial task allocation (ITA) that leverages team heterogeneity and conditional task reallocation in response to dynamic operational states. Additionally, we introduce an auxiliary state representation learning task to manage information uncertainty and enhance task execution. Through an extensive case study in large-scale environmental monitoring tasks, we demonstrate the benefits of our approach.

Problem

• Addresses task allocation in multi-human multi-robot teams
• Handles team heterogeneity and dynamic information uncertainty
• Proposes adaptive framework using hierarchical reinforcement learning

Innovation

• Hierarchical reinforcement learning for task allocation
• Initial task allocation leveraging team heterogeneity
• Auxiliary state representation for information uncertainty