REBEL: Rule-based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teaming

2024-09-24

AI Summary

Initial task allocation (ITA) in multi-human, multi-robot collaboration faces three key challenges: difficulty in forming heterogeneous agent-complementary pairings, weak alignment with multiple human objectives, and poor adaptability to dynamic environments. Method: This paper proposes a rule-guided and experience-enhanced large language model (LLM) reasoning framework. It integrates a symbolic rule engine, contextualized LLM inference, experience cache retrieval, and policy distillation to achieve lightweight, interpretable, human-intervenable, and evolvable ITA decisions. Contribution/Results: Compared to existing learning-based approaches, our method significantly reduces computational overhead while enabling explicit injection of multi-objective user preferences and real-time response to team reconfiguration. Experiments demonstrate improved preference alignment and faster reaction to emergent events in both single- and multi-objective ITA tasks. Moreover, it effectively enhances pre-trained policies, yielding higher task completion rates and greater collaborative robustness.

Technology Category

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

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Multi-human multi-robot teams are increasingly recognized for their efficiency in executing large-scale, complex tasks by integrating heterogeneous yet potentially synergistic humans and robots. However, this inherent heterogeneity presents significant challenges in teaming, necessitating efficient initial task allocation (ITA) strategies that optimally form complementary human-robot pairs or collaborative chains and establish well-matched task distributions. While current learning-based methods demonstrate promising performance, they often incur high computational costs and lack the flexibility to incorporate user preferences in multi-objective optimization (MOO) or adapt to last-minute changes in dynamic real-world environments. To address these limitations, we propose REBEL, an LLM-based ITA framework that integrates rule-based and experience-enhanced learning to enhance LLM reasoning capabilities and improve in-context adaptability to MOO and situational changes. Extensive experiments validate the effectiveness of REBEL in both single-objective and multi-objective scenarios, demonstrating superior alignment with user preferences and enhanced situational awareness to handle unexpected team composition changes. Additionally, we show that REBEL can complement pre-trained ITA policies, further boosting situational adaptability and overall team performance. Website at https://sites.google.com/view/ita-rebel .

Problem

• Efficient initial task allocation in multi-human multi-robot teams
• Handling dynamic changes and user preferences in task allocation
• Reducing computational costs while improving adaptability and performance

Innovation

• Integrates rule-based and experience-enhanced learning
• Enhances LLM reasoning for task allocation
• Improves adaptability to dynamic team changes