CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios

2025-04-30

AI Summary

To address challenges in semantic understanding, rigid task planning, and non-adaptive coordination among heterogeneous urban low-altitude UAV swarms operating in dynamic environments, this paper proposes a decentralized, emergent “Coordination Field” mechanism for task allocation. Integrated with large language models (LLMs), it establishes an end-to-end framework that parses high-level natural-language instructions into executable low-level UAV actions. The method combines distributed multi-agent coordination with a 2D urban simulation environment. Across 50 comparative trials, it achieves a 23% improvement in mission coverage and a 37% reduction in response latency, significantly outperforming baseline approaches in dynamic adaptability. The core contribution lies in the first integration of LLM-driven semantic interpretation with physics-grounded Coordination Field modeling—establishing a novel paradigm for autonomous, heterogeneous swarm coordination in complex urban settings.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

With the increasing demand for heterogeneous Unmanned Aerial Vehicle (UAV) swarms to perform complex tasks in urban environments, system design now faces major challenges, including efficient semantic understanding, flexible task planning, and the ability to dynamically adjust coordination strategies in response to evolving environmental conditions and continuously changing task requirements. To address the limitations of existing approaches, this paper proposes coordination field agentic system for coordinating heterogeneous UAV swarms in complex urban scenarios. In this system, large language models (LLMs) is responsible for interpreting high-level human instructions and converting them into executable commands for the UAV swarms, such as patrol and target tracking. Subsequently, a Coordination field mechanism is proposed to guide UAV motion and task selection, enabling decentralized and adaptive allocation of emergent tasks. A total of 50 rounds of comparative testing were conducted across different models in a 2D simulation space to evaluate their performance. Experimental results demonstrate that the proposed system achieves superior performance in terms of task coverage, response time, and adaptability to dynamic changes.

Problem

• Efficient semantic understanding in UAV swarms
• Flexible task planning for urban scenarios
• Dynamic coordination strategy adjustment

Innovation

• LLMs interpret high-level human instructions
• Coordination field guides UAV motion
• Decentralized adaptive task allocation