Low-Altitude Wireless Networks: A Comprehensive Survey

arXiv:2509.11607 · eess.SP · Submitted 2025-09-15 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.

Rosa: I'm Rosa.

Dev: And I'm Dev, here with Taro.

Rosa: We're looking at the paper: "Low-Altitude Wireless Networks: A Comprehensive Survey".

Dev: Here's the gist of the paper. The rapid development of the low-altitude economy necessitates wireless infrastructure capable of supporting large-scale drone deployments and intelligent services in dynamic airspace, moving beyond traditional air-ground communication systems to integrate sensing, computation, control, and energy delivery.

Rosa: The absence of systematic low-altitude airspace planning exacerbates issues such as dynamic interference in three dimensions, coverage instability, and scalability.

Dev: A comprehensive framework termed Low-Altitude Wireless Network (LAWN) has emerged to unify communication, sensing, computation, control, and air traffic management into a single design.

Rosa: This paper provides a detailed overview of LAWN systems by introducing their fundamentals and performance evaluation metrics before delving into functional designs and reviewing critical concerns regarding privacy and security in open-air environments.

Paper summary: Rosa: So, to summarize this "Low-Altitude Wireless Networks: A Comprehensive Survey," the main thesis is that we need a new wireless infrastructure to support the low altitude economy because current terrestrial networks are inadequate for the demands of emerging low-altitude applications >

Dev: They point out that existing networks struggle with things like dynamic and mobile sensing, communication, computation, and control in three dimensional airspace because they are primarily static infrastructure >

Taro: The paper claims that LAWNs provide the solution by restructuring the operation paradigm through wireless technology to support the safe and efficient operation of the low altitude economy >

Rosa: Specifically, LAWNs achieve a synergistic integration of sensing computing and control within a network of mobile unmanned aerial vehicles, allowing for on-demand high resolution environmental perception beyond what static terrestrial sensors can offer >

Dev: They also show that this distributed approach enables things like payload delivery or infrastructure inspection by supporting a wider range of low altitude use cases >

Taro: Beyond just sensing, the paper covers how LAWNs enable networked control for dynamic reconfiguration, which is important for adapting to changing conditions in real time >

Rosa: And they explore energy efficiency through joint trajectory control and energy harvesting as part of their design strategy >

Dev: They also address scalability by looking at how beam alignment limits and interference management are handled when you have a lot of devices operating in the same space >

Taro: Then there's the multi-functional design aspect, showing integrated sensing and communications, networked control, wireless power transfer as a networkwide energy sharing paradigm >

Rosa: And they don't forget the security angle, detailing privacy preservation through differential privacy and various physical and network layer defenses against attacks >

Dev: Finally, they survey advanced AI techniques like Large AI Model-based LAWNs and Agentic AI to enable more autonomous operations within these networks >

Conclusion: Rosa: So looking at the whole "Low-Altitude Wireless Networks: A Comprehensive Survey," the title itself really captures the scope of what they're trying to do by surveying all these different aspects of wireless networking for this low altitude economy >

Dev: The authors are laying out a lot here about how to build something that isn't just a communication link but an integrated system that handles sensing, computation, control and energy delivery simultaneously >

Taro: It seems like the big implication is moving away from isolated functions and toward cooperative intelligent integration where different parts of the network make decisions together for mission success >

Rosa: That’s right. They stress that multi-functional LAWN designs are best understood through task integration rather than looking at just one function in a vacuum >

Dev: And they emphasize that the future direction is moving towards agentic AI because it offers a way to overcome limitations from passive optimization by embedding reasoning directly into the network entities for collaborative swarm operations >

Taro: It points toward systems that can handle real-world chaos by having embedded reasoning, which is what you need for resilient communication links when infrastructure isn't fully available >

Jun Wu, +, Yaoqi Yang, +, Weijie Yuan, *, Wenchao Liu, Jiacheng Wang, Tianqi Mao, Lin Zhou1, Yuanhao Cui5, Fan Liu6, Geng Sun9, Yiyan Ma11, Nan Wu4, Dezhi Zheng4 Jindan Xu6 Nan Ma5 Zhiyong Feng5 Wei Xu6 Dusit Niyato3 Chau Yuen3 Xiaojun Jing5 Zhiguo Shi7 Bo Ai12*, Shi Jin6 Dong In Kim8 Jiangzhou Wang6 Ping Zhang5 Hao Yin10*, Jun Zhang4*

Southern University of Science and Technology · National Key Laboratory on Near-Surface Detection · Nanyang Technological University · Beijing Institute of Technology · Beijing University of Posts and Telecommunications · Southeast University · Zhejiang University · Sungkyunkwan University · Jilin University · Institute of China Electronic System Engineering

eess.SP

Submitted: 2025-09-15

Updated: 2026-04-15

Journal ref: China Communications, vol. 23, no. 3, pp. 99-141, 2026

DOI: 10.23919/JCC.fa.2025-0429.202603

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 100/100

The gist: The rapid development of the low-altitude economy necessitates wireless infrastructure capable of supporting large-scale drone deployments and intelligent services in dynamic airspace…

Key concepts

Low-Altitude Wireless Network (LAWN)
A comprehensive framework designed to unify communication, sensing, computation, control, and air traffic management into a single design. It addresses the lack of systematic planning in low-altitude airspace by providing resilient links where traditional infrastructure is insufficient.
Integrated Sensing and Communications (ISAC)
A multi-functional design approach that combines sensing capabilities with communication functions within the same network. This allows drones to simultaneously gather environmental data and transmit information, enhancing situational awareness for autonomous operations.
Agentic AI
An advanced artificial intelligence technique where reasoning is embedded directly into network entities. This enables goal-directed, autonomous operations by allowing drones to make complex decisions collaboratively within a swarm rather than relying on simple passive optimization.

Terminology

Summary

The rapid development of the low-altitude economy necessitates wireless infrastructure capable of supporting large-scale drone deployments and intelligent services in dynamic airspace, moving beyond traditional air-ground communication systems to integrate sensing, computation, control, and energy delivery. p. 0

Where the paper says it

cn, yuanwj@sustech. cn Abstract: The rapid development of the low-altitude economy has imposed unprecedented demands on wireless infrastructure to accommodate large-scale drone deployments and facilitate intelligent services in dynamic airspace environments.

The absence of systematic low-altitude airspace planning exacerbates issues such as dynamic interference in three dimensions, coverage instability, and scalability. p. 0
Where the paper says it

Traditional aerial systems predominantly focus on air-ground communication services, often neglecting the integration of sensing, computation, control, and energy-delivering functions, which hinders the ability to meet diverse mission-critical demands. Besides, the absence of systematic low-altitude airspace planning and management exacerbates issues regarding dynamic interference in three-dimensional space, coverage instability, and scalability.

A comprehensive framework termed Low-Altitude Wireless Network (LAWN) has emerged to unify communication, sensing, computation, control, and air traffic management into a single design. p. 3
Where the paper says it

Summary of Core Contributions and Technical Focus Ref. Research Area Core Contribution Technical Focus [9] Robust Control Overview of wireless control issues in LAWNs MPC, remote estimation, and reliable communications [10] Air traffic flow management Propose convex air traffic flow optimization models Air traffic flow, optimization, modeling, traffic management [11] Airspace management Investigate the LAA management Airspace management [7, 12] AI-enabled LAWN Investigate learning-based techniques for efficient data processing Embodied AI, machine learning, and reinforcement learning [5] LAWN architectures Discuss the realization of LAWNs covering architecture, technologies Airspace management and energy optimization [13–15] Privacy and security preservation Review privacy and security challenges in LAWNs Physical-layer privacy and security preservation [16] Energy-aware design Provide a comprehensive survey on RF energy harvesting RF energy harvesting and wireless power transfer [17] RIS-aided LAWN communications Investigate the interplay between RIS and LAWNs RIS [18] ISAC-enabled LAWNs Summarize LAWN-enabled ISAC for 6G networks ISAC and sensing-aided communications [19] Computation offloading Propose a framework for LAWN services boosting edge intelligence Edge intelligence and computation offloading [20, 21] Channel modeling Introduce communication architectures for LAWNs Channel modeling, routing, and seamless handover [22] Remote sensing mapping Present the design and implementation of LAWNs tailored for photogrammetric image acquisition Photogrammetry, trajectory control, and 3-dimensional reconstruction [23] Aerial robotics Analyze the evolution and state-ofthe-art of aerial robot systems Navigation and control [24] Hardware design Provide a comprehensive survey of UAV hardware architecture Sensor integration and system stability [25] Image processing Survey the image processing applications in intelligent agriculture Deep learning Our paper Both in functional designs and practical implementations A comprehensive review of LAWNs in sensing, communication, computation, control, and EH; Integration of airspace management and air traffic flow optimization ISAC, edge intelligence, wireless control, wireless power transfer, path planning, and air traffic management ated various control methods of LAWNs in dynamic and uncertain environments, including model predictive control (MPC) and proportional-integrativederivative (PID).

This paper provides a detailed overview of LAWN systems by introducing their fundamentals and performance evaluation metrics before delving into functional designs and reviewing critical concerns regarding privacy and security in open-air environments. p. 0
Where the paper says it

This article provides a comprehensive overview of LAWN systems, introducing LAWN system fundamentals and performance evaluation metrics. Subsequently, we delve into the evolution of functional designs and review critical concerns surrounding privacy and security in the open-air network environment.

Furthermore, it surveys advanced artificial intelligence techniques that enhance LAWN functionality to enable increasingly autonomous operations, concluding with cutting-edge developments in airspace structuring, air traffic management (ATM), and path planning to facilitate practical deployment. p. 0
Where the paper says it

We survey advanced artificial intelligence techniques that enhance LAWN functionality and enable increasingly autonomous operations. Finally, we present the cutting-edge developments in airspace structuring, air traffic management, and path planning, providing insights to facilitate the practical deployment of LAWNs.

The main contributions of the paper are threefold:

  1. Necessity and Superiority: The authors demonstrate the necessity of LAWNs for the growth and sustainability of the low-altitude economy, proving their superiority over traditional terrestrial networks by offering enhanced functionality, satisfying stringent performance demands, and providing more secure operating environments. Specifically, LAWNs can deliver on-demand connectivity, dynamic resource allocation, and resilient communication links where terrestrial infrastructure is limited or unavailable. p. 4

    Where the paper says it

    The main contributions of the paper can be summarized as follows: • We demonstrate the necessity of LAWNs for enabling the growth and sustainability of the lowaltitude economy, showcasing their superiority over traditional terrestrial networks in offering enhanced functionality, satisfying more stringent performance demands, and providing more secure operating environments. Specifically, LAWNs can deliver on-demand connectivity, dynamic resource allocation, and resilient communication links in scenarios where terrestrial infrastructure is limited or unavailable, thereby unlocking new possibilities for aerial services and economic activities, while simultaneously offering advanced security features to mitigate vulnerabilities inherent in wireless communications.

  2. Conceptual Foundation: The paper defines the concept of LAWNs from architectural, functional, and technical perspectives to establish a comprehensive framework for understanding their nature, architectural design, and inherent operating mechanisms.

  3. Multi-faceted Insights: The authors offer insights from functional, performance, privacy, and security viewpoints by illustrating how LAWNs enable diverse functionalities (such as Integrated Sensing and Communications (ISAC), Networked Control, Mobile Edge Computing, and Wireless Power Transfer) while optimizing critical performance indicators and robustly defending against malicious attacks across multi-level defenses.

The paper is structured systematically: Section II introduces LAWN fundamentals, including system architecture ranging from Star to Hierarchical Mesh Networks; Section III discusses performance metrics such as timeliness/latency (using FBL transmission and AoI management), energy-efficient design (via joint trajectory control and energy harvesting), scalability/connectivity (addressing beam alignment limits and interference management), and connectivity. p. 4

Where the paper says it

Section II introduces the fundamentals of LAWNs, including system architecture and representative channel models. Then, section III discusses LAWN performance metrics in terms of timeliness and latency, energy-efficient design, scalability, and connectivity.

Section IV presents multi-functional designs, focusing on Integrated Sensing and Communications (ISAC) for distributed sensing, Networked Control for dynamic reconfiguration, Wireless Power Transfer as a networkwide energy sharing paradigm, and the integration of ISAC with edge intelligence. p. 3
Where the paper says it

Research Area Core Contribution Technical Focus [9] Robust Control Overview of wireless control issues in LAWNs MPC, remote estimation, and reliable communications [10] Air traffic flow management Propose convex air traffic flow optimization models Air traffic flow, optimization, modeling, traffic management [11] Airspace management Investigate the LAA management Airspace management [7, 12] AI-enabled LAWN Investigate learning-based techniques for efficient data processing Embodied AI, machine learning, and reinforcement learning [5] LAWN architectures Discuss the realization of LAWNs covering architecture, technologies Airspace management and energy optimization [13–15] Privacy and security preservation Review privacy and security challenges in LAWNs Physical-layer privacy and security preservation [16] Energy-aware design Provide a comprehensive survey on RF energy harvesting RF energy harvesting and wireless power transfer [17] RIS-aided LAWN communications Investigate the interplay between RIS and LAWNs RIS [18] ISAC-enabled LAWNs Summarize LAWN-enabled ISAC for 6G networks ISAC and sensing-aided communications [19] Computation offloading Propose a framework for LAWN services boosting edge intelligence Edge intelligence and computation offloading [20, 21] Channel modeling Introduce communication architectures for LAWNs Channel modeling, routing, and seamless handover [22] Remote sensing mapping Present the design and implementation of LAWNs tailored for photogrammetric image acquisition Photogrammetry, trajectory control, and 3-dimensional reconstruction [23] Aerial robotics Analyze the evolution and state-ofthe-art of aerial robot systems Navigation and control [24] Hardware design Provide a comprehensive survey of UAV hardware architecture Sensor integration and system stability [25] Image processing Survey the image processing applications in intelligent agriculture Deep learning Our paper Both in functional designs and practical implementations A comprehensive review of LAWNs in sensing, communication, computation, control, and EH; Integration of airspace management and air traffic flow optimization ISAC, edge intelligence, wireless control, wireless power transfer, path planning, and air traffic management ated various control methods of LAWNs in dynamic and uncertain environments, including model predictive control (MPC) and proportional-integrativederivative (PID). Besides, the study in [24] discussed the fundamental hardware components of multi-copter UAVs, outlining key methods for optimizing critical parameters to ensure reliable and effective UAV usage.

Section V details multi-level defenses: Privacy Preservation (differential privacy), Physical-Layer Security (beamforming and artificial noise injection), and Network-Layer Security (intrusion detection systems). p. 5
Where the paper says it

List of Acronyms Acronym Description 5G Fifth-generation 6G Sixth-generation A2A Air-to-air A2G Air-to-ground ADS-B Automatic dependent surveillance–broadcast AI Artificial intelligence ATM Air traffic management ATC Air traffic control CNPC Control and non-payload communication D2D Device-to-device EH Energy harvesting eVTOL Electric vertical take-off and landing GBS Ground base station GNSS Global navigation satellite system HAP High-altitude platform ISAC Integrated sensing and communication IoT Internet of Things LAE Low-altitude economy LAA Low-altitude airspace LAWN Low-altitude wireless network LiDAR Light detection and ranging LLM Large language model LoS Line-of-sight LTE Long-term evolution MARL Multi-agent reinforcement learning MIMO Multiple-input multiple-output mmWave Millimeter wave MEC Mobile edge computing MPC Model predictive control MFD Macroscopic fundamental diagram NLoS Non-line-of-sight NOMA Non-orthogonal multiple access PID Proportional–integral–derivative RF Radio frequency RIS Reconfigurable intelligent surface UAV Unmanned aerial vehicle UAM Urban air mobility WPT Wireless power transfer covering privacy preservation, physical-layer security, and network-layer security. Section VI focuses on advanced AI-driven LAWNs, including both largemodel-based and agentic AI-based architectures.

Section VI focuses on advanced AI-driven LAWNs, exploring Large AI Model-based LAWNs and Agentic AI, which embed reasoning into network entities for goal-directed autonomous operations. p. 5
Where the paper says it

List of Acronyms Acronym Description 5G Fifth-generation 6G Sixth-generation A2A Air-to-air A2G Air-to-ground ADS-B Automatic dependent surveillance–broadcast AI Artificial intelligence ATM Air traffic management ATC Air traffic control CNPC Control and non-payload communication D2D Device-to-device EH Energy harvesting eVTOL Electric vertical take-off and landing GBS Ground base station GNSS Global navigation satellite system HAP High-altitude platform ISAC Integrated sensing and communication IoT Internet of Things LAE Low-altitude economy LAA Low-altitude airspace LAWN Low-altitude wireless network LiDAR Light detection and ranging LLM Large language model LoS Line-of-sight LTE Long-term evolution MARL Multi-agent reinforcement learning MIMO Multiple-input multiple-output mmWave Millimeter wave MEC Mobile edge computing MPC Model predictive control MFD Macroscopic fundamental diagram NLoS Non-line-of-sight NOMA Non-orthogonal multiple access PID Proportional–integral–derivative RF Radio frequency RIS Reconfigurable intelligent surface UAV Unmanned aerial vehicle UAM Urban air mobility WPT Wireless power transfer covering privacy preservation, physical-layer security, and network-layer security. Section VI focuses on advanced AI-driven LAWNs, including both largemodel-based and agentic AI-based architectures.

Section VII addresses implementation via Low-Altitude Airspace (LAA) Structuring (Pipeline, Corridor, Layered Airspace) and Low-Altitude ATM (adapting MFDs with Explainable AI). p. 5
Where the paper says it

Section VI focuses on advanced AI-driven LAWNs, including both largemodel-based and agentic AI-based architectures. Section VII addresses implementation and management aspects in terms of airspace structuring, traffic management, and path planning.

Key technical areas covered include LAWN architectures, A2G and A2A channel modeling across various scenarios, performance metrics analysis, multi-functional design methods like ISAC and Networked Control, multi-level security defenses, advanced AI techniques (LLMs and Agentic AI), LAA structuring (Pipeline Airspace vs. p. 3

Where the paper says it

Research Area Core Contribution Technical Focus [9] Robust Control Overview of wireless control issues in LAWNs MPC, remote estimation, and reliable communications [10] Air traffic flow management Propose convex air traffic flow optimization models Air traffic flow, optimization, modeling, traffic management [11] Airspace management Investigate the LAA management Airspace management [7, 12] AI-enabled LAWN Investigate learning-based techniques for efficient data processing Embodied AI, machine learning, and reinforcement learning [5] LAWN architectures Discuss the realization of LAWNs covering architecture, technologies Airspace management and energy optimization [13–15] Privacy and security preservation Review privacy and security challenges in LAWNs Physical-layer privacy and security preservation [16] Energy-aware design Provide a comprehensive survey on RF energy harvesting RF energy harvesting and wireless power transfer [17] RIS-aided LAWN communications Investigate the interplay between RIS and LAWNs RIS [18] ISAC-enabled LAWNs Summarize LAWN-enabled ISAC for 6G networks ISAC and sensing-aided communications [19] Computation offloading Propose a framework for LAWN services boosting edge intelligence Edge intelligence and computation offloading [20, 21] Channel modeling Introduce communication architectures for LAWNs Channel modeling, routing, and seamless handover [22] Remote sensing mapping Present the design and implementation of LAWNs tailored for photogrammetric image acquisition Photogrammetry, trajectory control, and 3-dimensional reconstruction [23] Aerial robotics Analyze the evolution and state-ofthe-art of aerial robot systems Navigation and control [24] Hardware design Provide a comprehensive survey of UAV hardware architecture Sensor integration and system stability [25] Image processing Survey the image processing applications in intelligent agriculture Deep learning Our paper Both in functional designs and practical implementations A comprehensive review of LAWNs in sensing, communication, computation, control, and EH; Integration of airspace management and air traffic flow optimization ISAC, edge intelligence, wireless control, wireless power transfer, path planning, and air traffic management ated various control methods of LAWNs in dynamic and uncertain environments, including model predictive control (MPC) and proportional-integrativederivative (PID). Besides, the study in [24] discussed the fundamental hardware components of multi-copter UAVs, outlining key methods for optimizing critical parameters to ensure reliable and effective UAV usage.

Blocky Airspace), and Low-Altitude ATM. p. 5
Where the paper says it

List of Acronyms Acronym Description 5G Fifth-generation 6G Sixth-generation A2A Air-to-air A2G Air-to-ground ADS-B Automatic dependent surveillance–broadcast AI Artificial intelligence ATM Air traffic management ATC Air traffic control CNPC Control and non-payload communication D2D Device-to-device EH Energy harvesting eVTOL Electric vertical take-off and landing GBS Ground base station GNSS Global navigation satellite system HAP High-altitude platform ISAC Integrated sensing and communication IoT Internet of Things LAE Low-altitude economy LAA Low-altitude airspace LAWN Low-altitude wireless network LiDAR Light detection and ranging LLM Large language model LoS Line-of-sight LTE Long-term evolution MARL Multi-agent reinforcement learning MIMO Multiple-input multiple-output mmWave Millimeter wave MEC Mobile edge computing MPC Model predictive control MFD Macroscopic fundamental diagram NLoS Non-line-of-sight NOMA Non-orthogonal multiple access PID Proportional–integral–derivative RF Radio frequency RIS Reconfigurable intelligent surface UAV Unmanned aerial vehicle UAM Urban air mobility WPT Wireless power transfer covering privacy preservation, physical-layer security, and network-layer security. Section VI focuses on advanced AI-driven LAWNs, including both largemodel-based and agentic AI-based architectures.

The core concept emphasizes that multi-functional LAWN designs are best understood through task integration rather than isolated functions, requiring a coordinated mechanism mapping mission objectives into coupled decisions across ISAC, edge intelligence, networked control, and WPT. p. 3
Where the paper says it

Research Area Core Contribution Technical Focus [9] Robust Control Overview of wireless control issues in LAWNs MPC, remote estimation, and reliable communications [10] Air traffic flow management Propose convex air traffic flow optimization models Air traffic flow, optimization, modeling, traffic management [11] Airspace management Investigate the LAA management Airspace management [7, 12] AI-enabled LAWN Investigate learning-based techniques for efficient data processing Embodied AI, machine learning, and reinforcement learning [5] LAWN architectures Discuss the realization of LAWNs covering architecture, technologies Airspace management and energy optimization [13–15] Privacy and security preservation Review privacy and security challenges in LAWNs Physical-layer privacy and security preservation [16] Energy-aware design Provide a comprehensive survey on RF energy harvesting RF energy harvesting and wireless power transfer [17] RIS-aided LAWN communications Investigate the interplay between RIS and LAWNs RIS [18] ISAC-enabled LAWNs Summarize LAWN-enabled ISAC for 6G networks ISAC and sensing-aided communications [19] Computation offloading Propose a framework for LAWN services boosting edge intelligence Edge intelligence and computation offloading [20, 21] Channel modeling Introduce communication architectures for LAWNs Channel modeling, routing, and seamless handover [22] Remote sensing mapping Present the design and implementation of LAWNs tailored for photogrammetric image acquisition Photogrammetry, trajectory control, and 3-dimensional reconstruction [23] Aerial robotics Analyze the evolution and state-ofthe-art of aerial robot systems Navigation and control [24] Hardware design Provide a comprehensive survey of UAV hardware architecture Sensor integration and system stability [25] Image processing Survey the image processing applications in intelligent agriculture Deep learning Our paper Both in functional designs and practical implementations A comprehensive review of LAWNs in sensing, communication, computation, control, and EH; Integration of airspace management and air traffic flow optimization ISAC, edge intelligence, wireless control, wireless power transfer, path planning, and air traffic management ated various control methods of LAWNs in dynamic and uncertain environments, including model predictive control (MPC) and proportional-integrativederivative (PID). Besides, the study in [24] discussed the fundamental hardware components of multi-copter UAVs, outlining key methods for optimizing critical parameters to ensure reliable and effective UAV usage.

The evolution moves towards cooperative and intelligent integration. p. 3
Where the paper says it

Summary of Core Contributions and Technical Focus Ref. Research Area Core Contribution Technical Focus [9] Robust Control Overview of wireless control issues in LAWNs MPC, remote estimation, and reliable communications [10] Air traffic flow management Propose convex air traffic flow optimization models Air traffic flow, optimization, modeling, traffic management [11] Airspace management Investigate the LAA management Airspace management [7, 12] AI-enabled LAWN Investigate learning-based techniques for efficient data processing Embodied AI, machine learning, and reinforcement learning [5] LAWN architectures Discuss the realization of LAWNs covering architecture, technologies Airspace management and energy optimization [13–15] Privacy and security preservation Review privacy and security challenges in LAWNs Physical-layer privacy and security preservation [16] Energy-aware design Provide a comprehensive survey on RF energy harvesting RF energy harvesting and wireless power transfer [17] RIS-aided LAWN communications Investigate the interplay between RIS and LAWNs RIS [18] ISAC-enabled LAWNs Summarize LAWN-enabled ISAC for 6G networks ISAC and sensing-aided communications [19] Computation offloading Propose a framework for LAWN services boosting edge intelligence Edge intelligence and computation offloading [20, 21] Channel modeling Introduce communication architectures for LAWNs Channel modeling, routing, and seamless handover [22] Remote sensing mapping Present the design and implementation of LAWNs tailored for photogrammetric image acquisition Photogrammetry, trajectory control, and 3-dimensional reconstruction [23] Aerial robotics Analyze the evolution and state-ofthe-art of aerial robot systems Navigation and control [24] Hardware design Provide a comprehensive survey of UAV hardware architecture Sensor integration and system stability [25] Image processing Survey the image processing applications in intelligent agriculture Deep learning Our paper Both in functional designs and practical implementations A comprehensive review of LAWNs in sensing, communication, computation, control, and EH; Integration of airspace management and air traffic flow optimization ISAC, edge intelligence, wireless control, wireless power transfer, path planning, and air traffic management ated various control methods of LAWNs in dynamic and uncertain environments, including model predictive control (MPC) and proportional-integrativederivative (PID).

Furthermore, the paper highlights the transition of Wireless Power Transfer (WPT) from static ground charging to a dynamic energy sharing paradigm that sustains intelligent perception and resilient communication. p. 5
Where the paper says it

List of Acronyms Acronym Description 5G Fifth-generation 6G Sixth-generation A2A Air-to-air A2G Air-to-ground ADS-B Automatic dependent surveillance–broadcast AI Artificial intelligence ATM Air traffic management ATC Air traffic control CNPC Control and non-payload communication D2D Device-to-device EH Energy harvesting eVTOL Electric vertical take-off and landing GBS Ground base station GNSS Global navigation satellite system HAP High-altitude platform ISAC Integrated sensing and communication IoT Internet of Things LAE Low-altitude economy LAA Low-altitude airspace LAWN Low-altitude wireless network LiDAR Light detection and ranging LLM Large language model LoS Line-of-sight LTE Long-term evolution MARL Multi-agent reinforcement learning MIMO Multiple-input multiple-output mmWave Millimeter wave MEC Mobile edge computing MPC Model predictive control MFD Macroscopic fundamental diagram NLoS Non-line-of-sight NOMA Non-orthogonal multiple access PID Proportional–integral–derivative RF Radio frequency RIS Reconfigurable intelligent surface UAV Unmanned aerial vehicle UAM Urban air mobility WPT Wireless power transfer covering privacy preservation, physical-layer security, and network-layer security. Section VI focuses on advanced AI-driven LAWNs, including both largemodel-based and agentic AI-based architectures.

The conclusion points toward agentic AI as a promising paradigm for overcoming passive optimization limitations by embedding reasoning into network entities for collaborative swarm operations. p. 6
Where the paper says it

Moreover, it emphasizes large-scale network coordination, enabling collaborative efforts across multiple airspace-aware nodes to optimize performance and efficiency [30]. Furthermore, LAWNs require comprehensive optimization beyond physical layers.

Finally, the necessity of strategic alignment with international frameworks like ICAO and domestic regulations is stressed to ensure safety, interoperability, and compliance in deployment.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Increased cognitive capabilities through Large AI Models can enable UAVs to dynamically adjust flight paths based on real-time environmental data such as wind and obstacle conditions.

  2. Agentic AI-based LAWNs can transition UAVs from passive optimization engines to active, goal-directed autonomous systems by embedding reasoning, memory, tool utilization, and self-evolution into network entities.

  3. Large AI models in physical layer designs can be used for UAV path planning to enable the UAVs to dynamically adjust their flight paths based on real-time environmental data.

  4. High dimensional computing (HDC) offers a lightweight computational method for LAWNs, enabling robust communication and efficient information exchange while accommodating the limitations of UAV platforms.

  5. Multi-agent reinforcement learning (MARL) can be applied to develop multi-UAV collaborative search and attack frameworks that formulate exploration, target engagement, and collision avoidance in unknown environments as a multi-agent decision problem.

  6. Agentic AI can interpret high level intent and fuse multi modal observations through a task oriented cognitive layer to reason jointly about trade offs in communication reliability, control precision, and sensing accuracy.

  7. Distributed optimization can be used to jointly design multi role UAV functionality switching and trajectories for secure task offloading in UAV assisted mobile edge computing under dynamic conditions.

Abstract

The rapid development of the low-altitude economy has imposed unprecedented demands on wireless infrastructure to accommodate large-scale drone deployments and facilitate intelligent services in dynamic airspace environments. However, unlocking its full potential in practical applications presents significant challenges. Traditional aerial systems predominantly focus on air-ground communication services, often neglecting the integration of sensing, computation, control, and energy-delivering functions, which hinders the ability to meet diverse mission-critical demands. Besides, the absence of systematic low-altitude airspace planning and management exacerbates issues regarding dynamic interference in three-dimensional space, coverage instability, and scalability. To overcome these challenges, a comprehensive framework, termed low-altitude wireless network (LAWN), has emerged to seamlessly integrate communication, sensing, computation, control, and air traffic management into a unified design. This article provides a comprehensive overview of LAWN systems, introducing LAWN system fundamentals and the evolution of functional designs. Subsequently, we delve into performance evaluation metrics and review critical concerns surrounding privacy and security in the open-air network environment. Finally, we present the cutting-edge developments in airspace structuring and air traffic management, providing insights to facilitate the practical deployment of LAWNs.

Sources

Related papers