The rapid growth of low-altitude aerial services and applications, driven by uncrewed aerial vehicles (UAVs), calls for a new class of digital infrastructure beyond conventional terrestrial networks. The low-altitude wireless network (LAWN) has been proposed as dynamically reconfigurable three-dimensional architectures that integrate aerial and ground nodes to provide connectivity, sensing, and control in open, safety-critical airspace. This tutorial presents a comprehensive treatment of LAWNs from the joint perspectives of artificial intelligence (AI) and signal processing. We first review the historical evolution and architectural foundations of LAWNs, introducing altitude-based layers and functional planes, and summarizing the regulatory and standardization landscape. Building on this system view, we then discuss signal processing fundamentals for LAWNs, including 3D channel and system models, performance metrics, waveform and receiver design, localization and tracking, and multi-functionality co-design. Next, we survey AI techniques for LAWNs, covering discriminative and generative models for perception, control, resource management, and security, as well as emerging paradigms such as foundation models, large language models, and digital twins for mission planning and closed-loop optimization. To illustrate AI-signal processing integration in practice, we provide a case study of an AI-driven multi-tier LAWN with hybrid satellite, high-altitude, and ground nodes. The tutorial concludes by outlining key research challenges in architecture design, signal processing-AI co-design, safety and security, experimentation, and standardization, and by highlighting opportunities for LAWNs to evolve into dependable, AI-native infrastructure for the intelligent skies.
Weijie Yuan, G. Sun, Jiacheng Wang et al.· IEEE Journal on Selected Top...· 0 citations
Low-altitude uncrewed aerial vehicle (UAV) communication offers notable advantages over terrestrial base stations in terms of flexibility and deployment efficiency. However, the high likelihood of line-of-sight (LoS) propagation renders the communication links between UAVs and ground users (GUs) particularly susceptible to eavesdropping. To address this issue, we consider an intelligent reflecting surface (IRS)-assisted low-altitude UAV secure communication system, in which communication security is strengthened through adaptive control of the wireless propagation environment, even when eavesdroppers are present. We aim to maximize the secrecy rate of GUs while minimizing the UAV energy consumption by jointly optimizing the continuous UAV trajectory, power allocation, and discrete IRS phase shifts. Considering the dynamic, non-convex, and NP-hard nature of the optimization problem, we propose an agentic artificial intelligence (AI) approach, namely alternating optimization (AO) and generative diffusion model-based deep deterministic policy gradient (AO-GDMDDPG) approach. The proposed agentic AI approach is composed of two cooperative agents that operate over a hybrid and high-dimensional decision space, in which the UAV agent adopts a generative AI (GenAI)-enhanced deep reinforcement learning (DRL) method to optimize continuous decision variables, whereas the IRS agent relies on the AO method to determine discrete IRS phase shifts. Simulation results demonstrate the superiority of the AO-GDMDDPG approach over benchmark algorithms with respect to secrecy rate improvement and UAV energy consumption reduction.
Wenwen Xie, G. Sun, Jiahui Li et al.· IEEE Transactions on Cogniti...· 0 citations
Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited corrective supervision for interactive closed-loop execution. Reinforcement learning (RL) offers a promising solution, while its effectiveness is constrained by inefficient use of samples, long-tailed scene distributions, and policy distribution shift during optimization. To this end, we propose RecoverFly, a failure-aware RL post-training framework for end-to-end UAV-VLA policies. Specifically, RecoverFly adapts token-level RL for stable optimization of grammar-constrained autoregressive UAV actions, revisits unresolved failure cases to strengthen corrective learning and sample utilization, and combines a two-stage long-tail scene curriculum with reference-policy regularization to improve scene adaptation while preserving acquired capabilities. Experiments on the TravelUAV benchmark demonstrate that RecoverFly achieves the best performance on the seen, unseen-map, and unseen-object splits. Moreover, compared to the AerialVLA initialization, RecoverFly improves success rate by 3.12 to 8.37 percentage points under a total rollout budget of about 30\% of the training-set size, validating its effectiveness, robustness, and generalization capabilities.
Boxiong Wang, Hui Kang, G. Sun et al.· 0 citations