HMCF: A Human-in-the-loop Multi-Robot Collaboration Framework Based on Large Language Models

TL;DR

This paper introduces HMCF, a framework that combines large language models and human oversight to improve multi-robot collaboration, adaptability, and safety in complex, large-scale tasks like disaster response.

Contribution

It presents a novel human-in-the-loop framework leveraging LLMs for adaptable, safe, and efficient multi-robot task planning and execution, addressing generalization and heterogeneity challenges.

Findings

Outperforms state-of-the-art task planning methods with 4.76% higher success rate.

Demonstrates robust zero-shot generalization to diverse tasks and environments.

Achieves high task success with minimal human intervention.

Abstract

Rapid advancements in artificial intelligence (AI) have enabled robots to performcomplex tasks autonomously with increasing precision. However, multi-robot systems (MRSs) face challenges in generalization, heterogeneity, and safety, especially when scaling to large-scale deployments like disaster response. Traditional approaches often lack generalization, requiring extensive engineering for new tasks and scenarios, and struggle with managing diverse robots. To overcome these limitations, we propose a Human-in-the-loop Multi-Robot Collaboration Framework (HMCF) powered by large language models (LLMs). LLMs enhance adaptability by reasoning over diverse tasks and robot capabilities, while human oversight ensures safety and reliability, intervening only when necessary. Our framework seamlessly integrates human oversight, LLM agents, and heterogeneous robots to optimize task allocation and execution. Each robot is equipped with an LLM agent capable of understanding its capabilities, converting tasks into executable instructions, and reducing hallucinations through task verification and human supervision. Simulation results show that our framework outperforms state-of-the-art task planning methods, achieving higher task success rates with an improvement of 4.76%. Real-world tests demonstrate its robust zero-shot generalization feature and ability to handle diverse tasks and environments with minimal human intervention.