TY - GEN
T1 - UAV Dual-Agent
T2 - 2nd International Symposium on Intelligent Computing and Networking ISICN 2025
AU - Bai, Gengyi
AU - Luo, Xiling
AU - Wang, Yupeng
AU - Zhou, Jialiu
AU - Shen, Jiameng
AU - Sun, Zeyang
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Recently, large language models (LLMs) have demonstrated a high level of intelligence, with extraordinary common sense, reasoning, and planning skills that frequently provide insightful guidance. The prospects are vast for the application of these capabilities in the operation, maintenance, and management of low-altitude unmanned aerial vehicles (UAVs). However, general LLMs lack specific expertise in UAVs, making it challenging for them to provide expert and insightful guidance or recommendations. To bridge this gap, we present the UAV dual-agent—a framework using large language models and knowledge graphs to address UAVs operation and maintenance issues, thereby providing in-depth decision support for urban low-altitude UAV through natural language dialogue. By constructing a UAV doctree, utilizing a knowledge graph to correct and supplement the doctree, and employing collaborative reasoning with LLMs, we have achieved a 40% increase in the accuracy of operational decisions compared to general LLMs.
AB - Recently, large language models (LLMs) have demonstrated a high level of intelligence, with extraordinary common sense, reasoning, and planning skills that frequently provide insightful guidance. The prospects are vast for the application of these capabilities in the operation, maintenance, and management of low-altitude unmanned aerial vehicles (UAVs). However, general LLMs lack specific expertise in UAVs, making it challenging for them to provide expert and insightful guidance or recommendations. To bridge this gap, we present the UAV dual-agent—a framework using large language models and knowledge graphs to address UAVs operation and maintenance issues, thereby providing in-depth decision support for urban low-altitude UAV through natural language dialogue. By constructing a UAV doctree, utilizing a knowledge graph to correct and supplement the doctree, and employing collaborative reasoning with LLMs, we have achieved a 40% increase in the accuracy of operational decisions compared to general LLMs.
KW - LLM
KW - UAV
KW - agent
KW - knowledge graph
UR - https://www.scopus.com/pages/publications/105023193808
U2 - 10.1007/978-3-032-09694-4_45
DO - 10.1007/978-3-032-09694-4_45
M3 - 会议稿件
AN - SCOPUS:105023193808
SN - 9783032096937
T3 - Lecture Notes in Networks and Systems
SP - 590
EP - 602
BT - Proceedings of the International Symposium on Intelligent Computing and Networking 2025 - ISICN 2025
A2 - Rodriguez Martinez, Manuel
A2 - Lu, Kejie
A2 - Ye, Feng
A2 - Qian, Yi
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 17 March 2025 through 19 March 2025
ER -