Compositional Coordination for Multi-Robot Teams with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zhehui, Shi, Guangyao, Wu, Yuwei, Kumar, Vijay, Sukhatme, Gaurav S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914108684632064
author Huang, Zhehui
Shi, Guangyao
Wu, Yuwei
Kumar, Vijay
Sukhatme, Gaurav S.
author_facet Huang, Zhehui
Shi, Guangyao
Wu, Yuwei
Kumar, Vijay
Sukhatme, Gaurav S.
contents Multi-robot coordination has traditionally relied on a mission-specific and expert-driven pipeline, where natural language mission descriptions are manually translated by domain experts into mathematical formulation, algorithm design, and executable code. This conventional process is labor-intensive, inaccessible to non-experts, and inflexible to changes in mission requirements. Here, we propose LAN2CB (Language to Collective Behavior), a novel framework that leverages large language models (LLMs) to streamline and generalize the multi-robot coordination pipeline. LAN2CB transforms natural language (NL) mission descriptions into executable Python code for multi-robot systems through two core modules: (1) Mission Analysis, which parses mission descriptions into behavior trees, and (2) Code Generation, which leverages the behavior tree and a structured knowledge base to generate robot control code. We further introduce a dataset of natural language mission descriptions to support development and benchmarking. Experiments in both simulation and real-world environments demonstrate that LAN2CB enables robust and flexible multi-robot coordination from natural language, significantly reducing manual engineering effort and supporting broad generalization across diverse mission types. Website: https://sites.google.com/view/lan-cb
format Preprint
id arxiv_https___arxiv_org_abs_2507_16068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compositional Coordination for Multi-Robot Teams with Large Language Models
Huang, Zhehui
Shi, Guangyao
Wu, Yuwei
Kumar, Vijay
Sukhatme, Gaurav S.
Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
Multi-robot coordination has traditionally relied on a mission-specific and expert-driven pipeline, where natural language mission descriptions are manually translated by domain experts into mathematical formulation, algorithm design, and executable code. This conventional process is labor-intensive, inaccessible to non-experts, and inflexible to changes in mission requirements. Here, we propose LAN2CB (Language to Collective Behavior), a novel framework that leverages large language models (LLMs) to streamline and generalize the multi-robot coordination pipeline. LAN2CB transforms natural language (NL) mission descriptions into executable Python code for multi-robot systems through two core modules: (1) Mission Analysis, which parses mission descriptions into behavior trees, and (2) Code Generation, which leverages the behavior tree and a structured knowledge base to generate robot control code. We further introduce a dataset of natural language mission descriptions to support development and benchmarking. Experiments in both simulation and real-world environments demonstrate that LAN2CB enables robust and flexible multi-robot coordination from natural language, significantly reducing manual engineering effort and supporting broad generalization across diverse mission types. Website: https://sites.google.com/view/lan-cb
title Compositional Coordination for Multi-Robot Teams with Large Language Models
topic Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2507.16068