Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

Yuqi PING; Tianhao LIANG; Huahao DING; Guangyu LEI; Junwei WU; Xuan ZOU; Kuan SHI; Rui SHAO; Chiya ZHANG; Weizheng ZHANG; Weijie YUAN; Tingting ZHANG

doi:10.1109/MWC.2025.3630121

Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

Yuqi PING^*
, Tianhao LIANG^*
, Huahao DING
, Guangyu LEI
, Junwei WU
, Xuan ZOU
, Kuan SHI
, Rui SHAO
, Chiya ZHANG
, Weizheng ZHANG
, Weijie YUAN
, Tingting ZHANG

^*Corresponding author for this work

School of Interdisciplinary Studies

Research output: Journal Publications › Journal Article (refereed) › peer-review

Abstract

Recent breakthroughs in multimodal large language models (MLLMs) have endowed AI systems with unified perception, reasoning, and natural-language interaction across text, image, and video modalities. Meanwhile, unmanned aerial vehicle (UAV) swarms are increasingly deployed in dynamic, safety-critical missions that demand rapid situational awareness and autonomous adaptation. This paper explores potential solutions for integrating MLLMs with UAV swarms to enhance intelligence and adaptability across diverse tasks. Specifically, we first outline the fundamental architectures and functions of UAVs and MLLMs. Then, we present a comprehensive framework for an MLLM-enabled UAV swarm system and discuss the opportunities it offers. Next, we demonstrate the capabilities of the proposed framework through a forest firefighting case study that includes both simulation and real-world experiments. Finally, we discuss the challenges and future research directions for MLLM-enabled UAV swarms.

Original language	English
Number of pages	9
Journal	IEEE Wireless Communications
DOIs	https://doi.org/10.1109/MWC.2025.3630121
Publication status	Published - 16 Dec 2025

Bibliographical note

Publisher Copyright:
© 2002-2012 IEEE.

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62501194 and Grant 62171160, in part by Guangdong Provincial Key Laboratory (2024) under Grant 2024KSYS023, in part by China Postdoctoral Science Foundation under Grant GZC20252782, in part by Shenzhen Science and Technology Program under Grant KJZD20240903100022029, and in part by the Major Key Project of PCL under Grant PCL2024A07.

Keywords

UAV swarm
forest fire protection
multimodal large language models

Access to Document

10.1109/MWC.2025.3630121Licence: Other

Cite this

@article{7b1b0ddce859442488ea837eb5516cf5,

title = "Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems",

abstract = "Recent breakthroughs in multimodal large language models (MLLMs) have endowed AI systems with unified perception, reasoning, and natural-language interaction across text, image, and video modalities. Meanwhile, unmanned aerial vehicle (UAV) swarms are increasingly deployed in dynamic, safety-critical missions that demand rapid situational awareness and autonomous adaptation. This paper explores potential solutions for integrating MLLMs with UAV swarms to enhance intelligence and adaptability across diverse tasks. Specifically, we first outline the fundamental architectures and functions of UAVs and MLLMs. Then, we present a comprehensive framework for an MLLM-enabled UAV swarm system and discuss the opportunities it offers. Next, we demonstrate the capabilities of the proposed framework through a forest firefighting case study that includes both simulation and real-world experiments. Finally, we discuss the challenges and future research directions for MLLM-enabled UAV swarms.",

keywords = "UAV swarm, forest fire protection, multimodal large language models",

author = "Yuqi PING and Tianhao LIANG and Huahao DING and Guangyu LEI and Junwei WU and Xuan ZOU and Kuan SHI and Rui SHAO and Chiya ZHANG and Weizheng ZHANG and Weijie YUAN and Tingting ZHANG",

note = "Publisher Copyright: {\textcopyright} 2002-2012 IEEE.",

year = "2025",

month = dec,

day = "16",

doi = "10.1109/MWC.2025.3630121",

language = "English",

journal = "IEEE Wireless Communications",

issn = "1536-1284",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

AU - PING, Yuqi

AU - LIANG, Tianhao

AU - DING, Huahao

AU - LEI, Guangyu

AU - WU, Junwei

AU - ZOU, Xuan

AU - SHI, Kuan

AU - SHAO, Rui

AU - ZHANG, Chiya

AU - ZHANG, Weizheng

AU - YUAN, Weijie

AU - ZHANG, Tingting

PY - 2025/12/16

Y1 - 2025/12/16

N2 - Recent breakthroughs in multimodal large language models (MLLMs) have endowed AI systems with unified perception, reasoning, and natural-language interaction across text, image, and video modalities. Meanwhile, unmanned aerial vehicle (UAV) swarms are increasingly deployed in dynamic, safety-critical missions that demand rapid situational awareness and autonomous adaptation. This paper explores potential solutions for integrating MLLMs with UAV swarms to enhance intelligence and adaptability across diverse tasks. Specifically, we first outline the fundamental architectures and functions of UAVs and MLLMs. Then, we present a comprehensive framework for an MLLM-enabled UAV swarm system and discuss the opportunities it offers. Next, we demonstrate the capabilities of the proposed framework through a forest firefighting case study that includes both simulation and real-world experiments. Finally, we discuss the challenges and future research directions for MLLM-enabled UAV swarms.

AB - Recent breakthroughs in multimodal large language models (MLLMs) have endowed AI systems with unified perception, reasoning, and natural-language interaction across text, image, and video modalities. Meanwhile, unmanned aerial vehicle (UAV) swarms are increasingly deployed in dynamic, safety-critical missions that demand rapid situational awareness and autonomous adaptation. This paper explores potential solutions for integrating MLLMs with UAV swarms to enhance intelligence and adaptability across diverse tasks. Specifically, we first outline the fundamental architectures and functions of UAVs and MLLMs. Then, we present a comprehensive framework for an MLLM-enabled UAV swarm system and discuss the opportunities it offers. Next, we demonstrate the capabilities of the proposed framework through a forest firefighting case study that includes both simulation and real-world experiments. Finally, we discuss the challenges and future research directions for MLLM-enabled UAV swarms.

KW - UAV swarm

KW - forest fire protection

KW - multimodal large language models

UR - https://www.scopus.com/pages/publications/105025458401

U2 - 10.1109/MWC.2025.3630121

DO - 10.1109/MWC.2025.3630121

M3 - Journal Article (refereed)

SN - 1536-1284

JO - IEEE Wireless Communications

JF - IEEE Wireless Communications

ER -

Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this