A Temporal Planning Framework for Multi-Agent Systems via LLM-Aided Knowledge Base Management

2025-02-26

AI Summary

This work addresses the challenge of jointly optimizing temporal planning, resource constraints, and parallel execution in multi-robot task coordination. We propose PLANTOR—a framework integrating large language models (LLMs) with a Prolog knowledge base to construct reusable, composable symbolic knowledge foundations. Methodologically, it employs a two-stage LLM-driven knowledge base construction and a three-step hybrid planning pipeline: semantic parsing → mixed-integer linear programming (MILP)-based temporal and resource optimization → Prolog-based formal verification—yielding ROS2-compatible behavior trees. Our key contribution is the first demonstration of LLM-generated, formally correct, and interpretable composable knowledge bases, effectively bridging neural scalability with symbolic rigor. Evaluation on block assembly and arch bridge construction tasks confirms efficacy: high knowledge base generation accuracy with minimal human feedback; verifiable, traceable planning outcomes; and end-to-end generation of executable behavior trees.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

This paper presents a novel framework, called PLANTOR (PLanning with Natural language for Task-Oriented Robots), that integrates Large Language Models (LLMs) with Prolog-based knowledge management and planning for multi-robot tasks. The system employs a two-phase generation of a robot-oriented knowledge base, ensuring reusability and compositional reasoning, as well as a three-step planning procedure that handles temporal dependencies, resource constraints, and parallel task execution via mixed-integer linear programming. The final plan is converted into a Behaviour Tree for direct use in ROS2. We tested the framework in multi-robot assembly tasks within a block world and an arch-building scenario. Results demonstrate that LLMs can produce accurate knowledge bases with modest human feedback, while Prolog guarantees formal correctness and explainability. This approach underscores the potential of LLM integration for advanced robotics tasks requiring flexible, scalable, and human-understandable planning.

Problem

• Enhance multi-agent temporal planning efficiency.
• Integrate LLMs for robot task knowledge management.
• Ensure scalable, flexible, and explainable robotic planning.

Innovation

• Integrates LLMs with Prolog
• Two-phase knowledge base generation
• Three-step planning with MILP