UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents

📅 2026-09-16
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
论文探讨了通过融合物理-数字AI代理来解决无人机理解人类意图和飞行动态的问题,提出了5+5框架以实现适应性和持续进化的无人机自主性。
📝 Abstract
Unmanned aerial vehicles (UAVs) extend embodied intelligence into continuous three-dimensional space, where perception, reasoning, physical embodiment, and action are tightly coupled through flight and environmental interaction. Recent advances in foundation models, world models, and AI agents are shifting UAV autonomy from task-specific perception and control toward systems that can interpret human intent, understand open environments, reason about physical consequences, and organize complex behaviors under embodiment and flight-dynamic constraints. We characterize this emerging paradigm as UAV embodied intelligence (UAV EI) and distinguish it from its system realization, the embodied-intelligent UAV (EI UAV). To provide a unified view of the field, we introduce a 5+5 framework that describes UAV EI through five capability dimensions and EI UAVs through five architectural layers spanning physical embodiment, general cognition, embodied skills, external interaction, and system harnessing. Based on this framework, we systematically review recent progress in embodied morphology, embodied perception, world models, embodied planning, vision-language navigation, embodied manipulation, and embodied collaboration. We further identify long-horizon autonomy, predictive physical reasoning, test-time skill acquisition, and autonomous capability evolution as key challenges toward more general aerial embodied intelligence. Finally, we argue that harnessing physical-digital AI agents, through persistent coupling of digital intelligence with physical sensing, dynamics, action, and feedback, provides a system-level pathway toward adaptive and continuously evolving UAV autonomy. Project resources are available at our project website and GitHub repository.
Problem

Research questions and friction points this paper is trying to address.

UAVs
Embodied Intelligence
Human Intents
Flying Dynamics
Physical-Digital AI Agents
Innovation

Methods, ideas, or system contributions that make the work stand out.

UAV Embodied Intelligence
Physical-Digital AI Agents
Foundation Models
World Models
Adaptive Autonomy
💼 Related Jobs
No related jobs found.
Yonglin Tian
Yonglin Tian
Institute of Automation, Chinese Academy of Sciences
Parallel intelligenceParallel umanned systemsIntelligent vehiclesAutonomous driving
W
Weiyi Wang
Institute of Automation, Chinese Academy of Sciences, China
H
Houhua Lu
Beihang University, China
X
Xinyi Li
Shanxi Datong University, China
Y
Yihao Wu
Institute of Automation, Chinese Academy of Sciences, China
J
Jingyang Chen
Johns Hopkins University, USA
J
Jianli Sun
Institute of Automation, Chinese Academy of Sciences, China
C
Chengxiang Li
University of Sanya, China
Y
Yinuo Chen
Wenzhou-Kean University, China
Fei Lin
Fei Lin
Macau University of Science and Technology
Parallel IntelligenceLarge Language ModelEmbodied AgentAI4Science
T
Tengchao Zhang
Macau University of Science and Technology, Macao, China
Jing Yang
Jing Yang
East China Normal University
Knowledge GraphCrowdSourcing
Deyi Ji
Deyi Ji
Tencent; USTC Ph.D.
Multimodal LLMComputer VisionNLP
J
Jian Di
University of Science and Technology of China, China
Naiqi Wu
Naiqi Wu
Macau University of Science and Technology, and Guangdong University of Technology
Discrete event SystemsPetri net theory and applicationsSchedulingIntelligent transportation systems
Yisheng Lv
Yisheng Lv
The University of Chinese Academy of Sciences, and Chinese Academy of Sciences
Parallel IntelligenceAI for TransportationAutonomous VehiclesParallel Transportation Systems