RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms

2025-07-02

AI Summary

Traditional UAV swarm navigation suffers from semantic communication deficits and rigid role structures, limiting generalization and task scalability; meanwhile, existing LLM-driven approaches lack online learning capability and over-rely on static priors, hindering environmental exploration and individual adaptability. To address these issues, this paper proposes a semantics-enhanced dynamic coordination framework. Its core contributions are: (1) a dynamic heterogeneous role mechanism with RMIX-guided semantic role assignment; (2) structured natural-language communication integrating LLM priors and an online policy co-evolution mechanism; and (3) a semi-offline training paradigm. Evaluated in MPE simulations and SITL experiments, the framework achieves significant improvements—+28.6% in task coverage, −41.3% in convergence time—and superior cross-scenario generalization, outperforming conventional MARL and pure-LLM baselines.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Multiagent Systems: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• 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

Intelligent control of Unmanned Aerial Vehicles (UAVs) swarms has emerged as a critical research focus, and it typically requires the swarm to navigate effectively while avoiding obstacles and achieving continuous coverage over multiple mission targets. Although traditional Multi-Agent Reinforcement Learning (MARL) approaches offer dynamic adaptability, they are hindered by the semantic gap in numerical communication and the rigidity of homogeneous role structures, resulting in poor generalization and limited task scalability. Recent advances in Large Language Model (LLM)-based control frameworks demonstrate strong semantic reasoning capabilities by leveraging extensive prior knowledge. However, due to the lack of online learning and over-reliance on static priors, these works often struggle with effective exploration, leading to reduced individual potential and overall system performance. To address these limitations, we propose a Role-Adaptive LLM-Driven Yoked navigation algorithm RALLY. Specifically, we first develop an LLM-driven semantic decision framework that uses structured natural language for efficient semantic communication and collaborative reasoning. Afterward, we introduce a dynamic role-heterogeneity mechanism for adaptive role switching and personalized decision-making. Furthermore, we propose a Role-value Mixing Network (RMIX)-based assignment strategy that integrates LLM offline priors with MARL online policies to enable semi-offline training of role selection strategies. Experiments in the Multi-Agent Particle Environment (MPE) environment and a Software-In-The-Loop (SITL) platform demonstrate that RALLY outperforms conventional approaches in terms of task coverage, convergence speed, and generalization, highlighting its strong potential for collaborative navigation in agentic multi-UAV systems.

Problem

• Enhance UAV swarm navigation with adaptive roles and semantic communication
• Bridge semantic gap in MARL for better generalization and scalability
• Combine LLM reasoning with MARL for improved exploration and performance

Innovation

• LLM-driven semantic decision framework
• Dynamic role-heterogeneity mechanism
• RMIX-based semi-offline training strategy