Automatic MILP Model Construction for Multi-Robot Task Allocation and Scheduling Based on Large Language Models

2025-03-18

AI Summary

Multi-robot task allocation and scheduling in smart manufacturing face challenges including complex modeling, poor adaptability to dynamic constraints, and high sensitivity to data privacy. Method: This paper proposes a knowledge-enhanced, localized LLM collaborative modeling framework that achieves fully automated offline translation from natural language descriptions to executable MILP code. The framework integrates a domain-specific knowledge base with lightweight distilled models: DeepSeek-R1-Distill-Qwen-32B for constraint extraction and fine-tuned Qwen2.5-Coder-7B-Instruct for MILP code generation. Contribution/Results: Evaluated on an aircraft skin manufacturing case, the framework achieves 100% modeling success rate, 82% constraint identification accuracy, and 90% code generation accuracy. It ensures strict data confinement (no data leaves the local domain) and sub-millisecond response latency, significantly enhancing both modeling efficiency and robustness for dynamic scheduling under stringent privacy requirements.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multi-Robot Systems
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

With the accelerated development of Industry 4.0, intelligent manufacturing systems increasingly require efficient task allocation and scheduling in multi-robot systems. However, existing methods rely on domain expertise and face challenges in adapting to dynamic production constraints. Additionally, enterprises have high privacy requirements for production scheduling data, which prevents the use of cloud-based large language models (LLMs) for solution development. To address these challenges, there is an urgent need for an automated modeling solution that meets data privacy requirements. This study proposes a knowledge-augmented mixed integer linear programming (MILP) automated formulation framework, integrating local LLMs with domain-specific knowledge bases to generate executable code from natural language descriptions automatically. The framework employs a knowledge-guided DeepSeek-R1-Distill-Qwen-32B model to extract complex spatiotemporal constraints (82% average accuracy) and leverages a supervised fine-tuned Qwen2.5-Coder-7B-Instruct model for efficient MILP code generation (90% average accuracy). Experimental results demonstrate that the framework successfully achieves automatic modeling in the aircraft skin manufacturing case while ensuring data privacy and computational efficiency. This research provides a low-barrier and highly reliable technical path for modeling in complex industrial scenarios.

Problem

• Automates MILP model construction for multi-robot task allocation.
• Addresses data privacy in production scheduling using local LLMs.
• Enhances dynamic adaptation to industrial constraints via knowledge-augmented models.

Innovation

• Automated MILP modeling using local LLMs
• Knowledge-guided DeepSeek-R1-Distill-Qwen-32B model
• Supervised fine-tuned Qwen2.5-Coder-7B-Instruct model