IMR-LLM: Industrial Multi-Robot Task Planning and Program Generation using Large Language Models

2026-03-03

AI Summary

This work addresses the challenge of generating executable programs for industrial multi-robot collaborative tasks, which involve strict temporal constraints and complex dependencies that current large language models (LLMs) struggle to handle. The authors propose IMR-LLM, a novel framework that integrates LLMs with disjunctive graphs and process trees through a hierarchical planning mechanism. At the high level, disjunctive graphs model task dependencies and invoke a deterministic solver to produce a feasible task schedule; at the low level, process trees guide the LLM to generate syntactically and semantically correct executable code. Additionally, the study introduces IMR-Bench, the first benchmark tailored to this domain. Experimental results demonstrate that IMR-LLM significantly outperforms existing approaches across all evaluation metrics, achieving efficient and reliable multi-robot task planning and program synthesis.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multi-Robot Systems

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

In modern industrial production, multiple robots often collaborate to complete complex manufacturing tasks. Large language models (LLMs), with their strong reasoning capabilities, have shown potential in coordinating robots for simple household and manipulation tasks. However, in industrial scenarios, stricter sequential constraints and more complex dependencies within tasks present new challenges for LLMs. To address this, we propose IMR-LLM, a novel LLM-driven Industrial Multi-Robot task planning and program generation framework. Specifically, we utilize LLMs to assist in constructing disjunctive graphs and employ deterministic solving methods to obtain a feasible and efficient high-level task plan. Based on this, we use a process tree to guide LLMs to generate executable low-level programs. Additionally, we create IMR-Bench, a challenging benchmark that encompasses multi-robot industrial tasks across three levels of complexity. Experimental results indicate that our method significantly surpasses existing methods across all evaluation metrics.

Problem

• Industrial Multi-Robot
• Task Planning
• Program Generation
• Sequential Constraints
• Task Dependencies

Innovation

• Large Language Models
• Multi-Robot Task Planning
• Disjunctive Graph
• Process Tree
• Industrial Automation