TY - GEN
T1 - Intelligent Planning and Full-Process Modeling for UAV Based on Large Language Models
AU - Chen, Jianbin
AU - Han, Bing
AU - Wang, Shu
AU - Yang, Xiaoyu
AU - Zhang, Peiyuan
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2027.
PY - 2027
Y1 - 2027
N2 - With the rapid advancement of unmanned aerial vehicle (UAV) technology and the expanding range of application scenarios, intelligent UAV planning faces increasingly complex and diverse demands. Current UAV planning approaches often involve significant human intervention in representation modeling and planning control, lacking an integrated architecture and intelligent methodologies. To address this issue, this paper proposes a comprehensive modeling and planning framework for intelligent UAV planning based on large language models. The approach aims to achieve a modular representation of task modeling, planning, and solution derivation starting from high-level task design. For the intelligent UAV planning problem, this paper integrates UAV representation modeling techniques with tree-based behavior control scheduling techniques and uses the Robot Operating System 2 (ROS2) for simulation. By optimizing planning and control scheduling, the proposed method improves the efficiency of UAV task execution.
AB - With the rapid advancement of unmanned aerial vehicle (UAV) technology and the expanding range of application scenarios, intelligent UAV planning faces increasingly complex and diverse demands. Current UAV planning approaches often involve significant human intervention in representation modeling and planning control, lacking an integrated architecture and intelligent methodologies. To address this issue, this paper proposes a comprehensive modeling and planning framework for intelligent UAV planning based on large language models. The approach aims to achieve a modular representation of task modeling, planning, and solution derivation starting from high-level task design. For the intelligent UAV planning problem, this paper integrates UAV representation modeling techniques with tree-based behavior control scheduling techniques and uses the Robot Operating System 2 (ROS2) for simulation. By optimizing planning and control scheduling, the proposed method improves the efficiency of UAV task execution.
KW - Behavior tree
KW - Intelligent planning
KW - Planning domain definition language (pddl)
KW - Representation modeling
UR - https://www.scopus.com/pages/publications/105050794225
U2 - 10.1007/978-981-92-4392-1_21
DO - 10.1007/978-981-92-4392-1_21
M3 - Conference contribution
AN - SCOPUS:105050794225
SN - 9789819243914
T3 - Lecture Notes in Electrical Engineering
SP - 246
EP - 263
BT - Proceedings of 2025 9th Chinese Conference on Swarm Intelligence and Cooperative Control - Swarm Decision and Planning Technologies
A2 - Li, Xiaoduo
A2 - Li, Yichen
A2 - Feng, Zhi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2025
Y2 - 31 October 2025 through 3 November 2025
ER -