Generalized Mission Planning for Heterogeneous Multi-Robot Teams via LLM-constructed Hierarchical Trees

2025-01-27

AI Summary

Heterogeneous multi-robot teams struggle to simultaneously accommodate individual capability disparities and ensure global coordination efficiency in complex, dynamic task environments. Method: This paper proposes a hierarchical task planning framework leveraging large language models (LLMs). It uniquely employs the LLM as an active constructor that autonomously generates interpretable, executable hierarchical task trees. Custom APIs and capability-constrained modeling enable end-to-end mapping from semantic instructions to robot-level actions. Integrated with a multi-robot cooperative scheduling algorithm, the framework supports generalized planning and real-time re-planning across diverse robot types and task scales. Contribution/Results: Experiments demonstrate significant improvements in task decomposition rationality and scheduling feasibility. The framework exhibits superior flexibility, scalability, and robustness across heterogeneous scenarios, enabling effective adaptation to dynamic environmental changes and varying team compositions.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multi-Robot Systems
• Humans and AI: Planning and Decision Support for Human-Machine Teams

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
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

We present a novel mission-planning strategy for heterogeneous multi-robot teams, taking into account the specific constraints and capabilities of each robot. Our approach employs hierarchical trees to systematically break down complex missions into manageable sub-tasks. We develop specialized APIs and tools, which are utilized by Large Language Models (LLMs) to efficiently construct these hierarchical trees. Once the hierarchical tree is generated, it is further decomposed to create optimized schedules for each robot, ensuring adherence to their individual constraints and capabilities. We demonstrate the effectiveness of our framework through detailed examples covering a wide range of missions, showcasing its flexibility and scalability.

Problem

• Multi-Robot Teams
• Task Allocation
• Individual Capabilities and Needs

Innovation

• Task Planning
• Hierarchical Tree Structure
• Multi-Robot Team Optimization