用大模型直接把自然语言指令转成机器人协作代码
Compositional Coordination for Multi-Robot Teams with Large Language Models
- 通过行为树解析语言任务，再生成可执行控制代码
- 在仿真和真实环境均实现跨任务灵活协作，减少人工编程
- 适合非专家快速部署多机器人系统，推动智能协作普及
多机器人协同传统上依赖任务特定且由专家主导的流程，需将自然语言任务描述手动转化为数学表述、算法设计与可执行代码。该过程耗时费力，对非专家不友好，且难以适应任务变更。本文提出LAN2CB（Language to Collective Behavior）框架，利用大语言模型（LLMs）简化并泛化多机器人协调流程。LAN2CB通过两个核心模块：(1) 任务分析，将自然语言描述解析为行为树；(2) 代码生成，结合行为树与结构化知识库生成机器人控制代码。研究还构建了一个自然语言任务描述数据集，用于模型开发与评估。仿真与真实环境实验表明，LAN2CB能从自然语言实现鲁棒、灵活的多机器人协同，显著降低人工工程成本，并支持多种任务类型的广泛泛化。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。