LLM-Flock: Decentralized Multi-Robot Flocking via Large Language Models and Influence-Based Consensus

2025-05-10

AI Summary

Large language models (LLMs) exhibit hallucinatory reasoning, logical inconsistency, and lack of coordination awareness when directly applied to multi-robot formation control, leading to unstable physical execution. Method: We propose an influence-aware distributed LLM planning consensus mechanism, embedding state-of-the-art LLMs (e.g., Llama3.1-405B) into a decentralized collaborative framework. It employs influence-weighted plan fusion and distributed consensus optimization for robust formation control on ROS/Crazyflie platforms. Contribution/Results: This work presents the first stable, LLM-driven physical drone formation—achieving zero crash rate and 42% faster convergence in simulation. Real-world validation demonstrates dynamic obstacle avoidance and shape-adaptive formation with five Crazyflie nano-drones. It establishes the first feasible, scalable decentralized paradigm for deploying LLMs in real-world multi-robot systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• 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
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large Language Models (LLMs) have advanced rapidly in recent years, demonstrating strong capabilities in problem comprehension and reasoning. Inspired by these developments, researchers have begun exploring the use of LLMs as decentralized decision-makers for multi-robot formation control. However, prior studies reveal that directly applying LLMs to such tasks often leads to unstable and inconsistent behaviors, where robots may collapse to the centroid of their positions or diverge entirely due to hallucinated reasoning, logical inconsistencies, and limited coordination awareness. To overcome these limitations, we propose a novel framework that integrates LLMs with an influence-based plan consensus protocol. In this framework, each robot independently generates a local plan toward the desired formation using its own LLM. The robots then iteratively refine their plans through a decentralized consensus protocol that accounts for their influence on neighboring robots. This process drives the system toward a coherent and stable flocking formation in a fully decentralized manner. We evaluate our approach through comprehensive simulations involving both state-of-the-art closed-source LLMs (e.g., o3-mini, Claude 3.5) and open-source models (e.g., Llama3.1-405b, Qwen-Max, DeepSeek-R1). The results show notable improvements in stability, convergence, and adaptability over previous LLM-based methods. We further validate our framework on a physical team of Crazyflie drones, demonstrating its practical viability and effectiveness in real-world multi-robot systems.

Problem

• Address unstable behaviors in LLM-based multi-robot flocking
• Integrate LLMs with decentralized influence-based consensus
• Improve stability and convergence in robot formations

Innovation

• Integrates LLMs with influence-based consensus protocol
• Decentralized plan refinement via neighbor influence
• Evaluated with both closed and open-source LLMs