2026· IEEE Transactions on Cognitive Communications and Networking· Vol 12, pp. 9625-9640· 0 citations· 47 references
Computer Science
Abstract
Low-altitude embodied intelligence (LAEI) has emerged as a promising solution for operational efficiency and sustainability of the emerging low-altitude economy via perception–reasoning–action loops. The ground base stations with limited service coverages fail to achieve ubiquitous connectivity in widespread environments. The aerial agents embedded in flying bodies ensure pervasive intelligence across dynamic three-dimensional spaces. However, the joint optimization of flight trajectories and resource allocation for hierarchical UAV networks introduces large state and action spaces, posing significant challenges for real-time mission execution. In this paper, we propose an agentic Generative Artificial Intelligence (GenAI)-based LAEI framework. In the framework, a joint optimization problem is formulated to minimize long-term average energy consumption while ensuring task queue stability and satisfying spatial kinematic constraints. The Lyapunov optimization technique decomposes the long-term energy minimization problem into deterministic per-slot sub-problems with low computational complexity. A diffusion-based GenAI algorithm synthesizes optimal trajectories through an iterative denoising process, where the model-based resource allocation problem serves as guidance to accelerate convergence. Finally, extensive simulation experiments indicate that the proposed GenAI-enabled algorithm outperforms other baseline schemes, delivering minimized energy consumption and enhanced resource utilization in dynamic low-altitude embodied intelligence environments.
Low-altitude wireless networks (LAWNs) are emerging as a foundational infrastructure for the low-altitude economy, necessitating unmanned aerial vehicles (UAVs) to operate as embodied wireless agents that can navigate complex air-ground environments. This paper investigates the critical challenge of maintaining reliable and covert information transmission for such agents under stringent mobility and detection constraints. To address this, we propose an embodied agentic framework that synergizes safety-critical path planning with cognitive predictive beamforming through a hierarchical execution-reasoning loop. Specifically, the execution layer utilizes model predictive control (MPC) to solve a constrained optimization problem, linearizing obstacle-avoidance requirements into tractable dual-variable inequalities to ensure collision-free navigation. This generates a deterministic sequence of future coordinates that serves as a spatial intent prior to reduce environmental uncertainty. Subsequently, the cognitive reasoning layer leverages a large language model (LLM) to integrate these motion priors with sensing-assisted historical channel state information and warden locations through a cross-modal attention mechanism. By capturing the intricate dependencies between the agent kinematic states and the non-stationary wireless channel, the LLM proactively optimizes predictive beamforming to satisfy covertness requirements against mobile wardens. Simulation results validate the efficacy of this joint design, demonstrating that the UAV successfully tracks reference trajectories while maintaining safety margins in obstacle-cluttered environments. Furthermore, the proposed framework achieves superior covertness performance compared to conventional benchmarks.
Space-Air-Ground Integrated Networks (SAGINs) can extend connectivity, but their communication, computing, and platform operations create tightly coupled energy demands. Solar-powered High-Altitude Platforms (HAPs) offer a promising middle layer by combining persistent regional coverage, renewable-energy harvesting, and onboard computing. However, realizing this potential requires more than optimizing individual links or processors, as radio transmission, task execution, backhaul use, and battery preservation share a common energy budget. Therefore, we introduce a HAP-native Agentic AI framework. It continuously perceives communication, computing, energy, mobility, and mission states; invokes quantitative tools for prediction and verification; and coordinates executable actions through a closed control loop. Then, a multi-timescale design separates fast radio control from task orchestration and long-term energy planning. Furthermore, a disaster-recovery case study illustrates how the framework responds to backhaul congestion, traffic surges, and declining solar generation, improving energy efficiency, task completion, and latency over other baselines. We finally identify trustworthy control, collaborative multi-HAP orchestration, and digital-twin-assisted lifelong adaptation as key steps toward deployable, sustainable, and resilient SAGIN intelligence.
Classical path planning algorithms such as A* applied to multi-UAV systems are unable to cope with multi-UAV complex scenarios in urban low altitude. This is due to the limitations in computational speed and convergence at a local optimal which are unable to guarantee the optimal flight energy and mission success rate. For such purposes, the Upgraded Gooseneck Barnacle Optimization (UGBO) algorithm is proposed based on the concept of swarm intelligence meta-heuristic intelligence with three mechanisms of improvements. They are opposing-based learning for better diversity of initial population, self-adaptive population adjust to balancing explore and exploit, and a forbidden strategy to get out of the local optimal. An improved energy consumption model considering aerobic drag, and wind impacts are employed, with clear multi-UAV coordination in the process through horizontal layer and proximity deconfliction in three-dimensional space, so the trajectory will be physically realizable and collision-free. Simulation in a 100 m × 100 m × 50 m simulation environment including fifteen to twenty static obstacles, and three to five dynamic obstacles show the UGBO achieve the path length nine hundred fifty meters, flight energy four hundred eighty units, calculation time twelve seconds, and average optimal fitness 0.85. These are, compared to other three classical algorithms A*, ACO, and PSO, improved by 19.5-33.1%, 19.3-33.3%, and 25.0-112.5%, respectively. Also, comprehensive experimental comparison with the state-of-the-art research such as PR-DQN, APF-RRT, T-DRL, and AHMP demonstrates that UGBO perform well with 3.1-17.4% improvement from those four approaches. Through ablating test, the study show that the improvement of opposition-based learning plays the most significant role in all three mechanisms. The results show an efficient multi-UAV path planning for urban aerial vehicles that outperform current solutions and can be readily integrated into learning-based approaches and deployed on physical hardware.
Rapid advances in drone technology, combined with the growing congestion of terrestrial transport networks, are driving the emergence of the low-altitude economy. Uncrewed Aerial Vehicles (UAVs) are increasingly deployed for low-altitude economy applications such as urban logistics and transportation, yet their expansion is constrained by the scarcity of spectrum resources. Although Multi-Agent Reinforcement Learning (MARL) offers a promising decentralized approach to improve spectral efficiency of UAVs, existing MARL methods suffer from high training costs, often requiring extensive environmental interactions. To overcome these limitations, we propose a novel Multi-Agent Model-Based reinforcement learning algorithm for decentralized spectrum sharing among UAVs in the low-altitude economy, which we denote as MAMBA-UAV. Adopting a Centralized Training with Decentralized Execution (CTDE) paradigm, MAMBA-UAV equips each UAV with a learned world model that captures compact environmental representations and predicts system dynamics. These world models are then utilized during MARL training to simulate interactions, thereby reducing the reliance on repeated real-environment rollouts. Through comprehensive simulations, we demonstrate that MAMBA-UAV substantially reduces the number of environmental interactions required for UAVs to achieve competitive spectrum-sharing performance, lowering training costs while maintaining high performance.
Tianle Li, Peixi Peng, Qingyu Liu et al.· IEEE Transactions on Cogniti...· 0 citations
The proliferation of low-altitude intelligent agents is increasing the demand for timely and socially responsible collaborative sensing in dynamic urban environments. However, jointly addressing heterogeneous spatiotemporal demands, environmental uncertainty, and human-centered operational constraints remains challenging. This paper studies 3D multi-UAV path planning and task assignment under uncertain ground PoI demands. Unlike existing work assuming static and fully known PoIs, we model persistent, temporally predictable, and emergent demands within a unified framework. We further incorporate altitude-dependent societal and environmental costs, including noise exposure and public safety risks, to balance sensing performance with socially compliant operations. To solve the resulting large-scale mixed-integer nonlinear problem, we propose FORTUNE, a hierarchical offline-online framework. Offline, a Transformer predicts Type-II PoI activation windows, while an enhanced sparrow search algorithm generates coordinated flight plans through priority-aware decoding and danger-aware evolution. Online, a lightweight refinement module accommodates emerging Type-III PoIs while preserving global mission coherence. Experiments on real-world traffic data and synthetic scenarios show that FORTUNE consistently outperforms state-of-the-art methods in effectiveness, scalability, and practical applicability.
Minghui Liwang, Wenhan Jia, Xinlei Yi et al.· 0 citations
Unmanned Aerial Vehicles (UAVs) are pivotal for facilitating data collection in emergency scenarios. Despite the potential of Multi-Agent Deep Reinforcement Learning (MADRL) in coordinating such systems, existing researches struggle to resolve the high-dimensional coupling of data collection, trajectory planning, and energy scheduling under strict collision avoidance and Return-To-Base (RTB) constraints. This paper proposes a energy-aware cooperative MADRL framework designed to maximize data collection utility under energy constraints. Specifically, we employ a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) approach featuring a Centralized Training with Decentralized Execution (CTDE) design and a multi-objective reward mechanism to balance conflicting optimization goals. Extensive simulations validate the advantages of the proposed framework over leading baselines. Notably, the algorithm exhibits significant quantitative advantages in complex high-load scenarios. These outcomes prove that our method achieves higher task completion rates while strictly adhering to RTB and safety protocols.
Jing Mei, Jinglei Xu, Zhao Tong et al.· IEEE Transactions on Network...· 0 citations