Agentic AI for UAV Trajectory Optimization and Fair Computation Offloading in Complex Low-Altitude Environments

To overcome the limitations of ground-based pseudolite systems susceptible to terrain obstructions, this paper proposes an air-ground collaborative regional radio positioning system (AGCRRPS) in GNSS-denied environments, including architecture, evaluation metrics, and a systematic UAV swarm trajectory optimization method. The AGCRRPS operates through sequential pseudorange broadcasting and positioning among ground anchors, aerial UAV swarms, and ground users to ensure the stable operation of the system. The UAV swarm’s trajectory design directly impacts the propagation of system accuracy. To characterize the error propagation in this layered air-ground structure, we derive a precision mapping model suitable for multi-layer systems and the equivalent Dilution of Precision (DOP) metric for instantaneous geometric configurations. Based on this, we formulate a multi-objective optimization function that effectively evaluates regional positioning systems, incorporating three dimensions: average accuracy, inter-user balance, and temporal stability. An adaptive trajectory representation protocol that optimizes UAV trajectories while preserving primary task objectives is developed. By leveraging the Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the multi-objective optimizer, we establish a systematic UAV swarm trajectory optimization approach, with simulation results demonstrating its effectiveness. Further simulations reveal the precision limits and inter-layer independence in multi-layer systems, providing theoretical insights for weak-anchor multi-tier navigation system design. Additionally, the influence of resource allocation on user performance is analyzed, offering practical guidance for anchor-UAV ratio configurations in engineering deployments.

In this paper, we study the maximization of the secrecy throughput of an air-to-ground UAV communication system through UAV trajectory optimization, in a scenario where multiple cooperating eavesdroppers exist. Two cooperative eavesdropping strategies, namely Selection Combing-Cooperative Eavesdropping (SC-CE) and Maximal Ratio Combining-Cooperative Eavesdropping (MRC-CE) are considered for the cooperating eavesdroppers. Based on the mathematical forms of the formulated optimization problems corresponding to the two cooperative eavesdropping schemes, we propose to use the Trajectory Increment Iteration (TII) algorithm and the Particle Swarm Optimization (PSO) algorithm to solve for the optimal trajectory, respectively. Simulation results show that by optimizing the UAV trajectory against cooperative eavesdropping, the physical layer security performance of the system can be effectively improved.

Most UAVs depend on realtime 3D point clouds to navigate through unknown environments. However, both point clouds processing and trajectory planning are computationally expensive and will deplete UAV's battery quickly. There are also inevitable uncertainties in point clouds, which further makes collision-free trajectory planning a very challenging problem. To address these issues, we propose an <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>e</u></b> nergy-efficient and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>c</u></b> loud-assisted aut <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>onom</u></b> ous navigation s <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>y</u></b> stem, called ECONOMY, which allows a UAV to transmit the point clouds through a cellular network to a computing cloud that plans the trajectories for the UAV in realtime. To maximize the UAV's energy-efficiency, we jointly optimize its velocity, trajectory, and transmission power. Since the formulated problem is non-convex, we decompose it into a UAV trajectory and velocity optimization problem (UTVO), and a UAV communication optimization problem (UCO), which are resolved by an intelligent solver built upon the Suggest-and-Improve framework, and gradient ascent, respectively. To address point clouds uncertainties, we devise probabilistic collision-free constraints which can be handled in a deterministic manner by exploiting the tight <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(n,2,\mathcal {R}^n)$</tex-math></inline-formula> -upper bound for convex sets. Simulation results for a UAV exploring a simulated urban environment demonstrate the efficacy and efficiency of ECONOMY.

Multi-unmanned aerial vehicle (UAV)-assisted communication is a critical technology for the low-altitude economy, supporting applications from logistics to emergency response. Semantic communication effectively enhances transmission efficiency and improves the communication performance of multi-UAV-assisted systems. Existing research on multi-UAV semantic communication networks predominantly assumes static ground devices, overlooking computation offloading and resource allocation challenges when ground devices are mobile. This overlooks the critical challenge of dynamically managing computation offloading and resources for mobile users, whose varying channel conditions and semantic compression needs directly impact system performance. To address this gap, this paper proposes a multi-UAV-assisted semantic communication model that novelly integrates user mobility with adaptive semantic compression, formulating a joint optimization problem for computation offloading and resource allocation. The objective is to minimize the maximum task processing latency through the joint optimization of UAV–device association, UAV trajectories, transmission power, task offloading ratios, and semantic compression depth. To solve this problem, we design a MAPPO-APSO algorithm integrating alternating iteration, multi-agent proximal policy optimization (MAPPO), and adaptive particle swarm optimization (APSO). Simulation results demonstrate that the proposed algorithm reduces the maximum task latency and system energy consumption by up to 20.7% and 16.1%, respectively, while maintaining transmission performance and outperforming benchmark approaches.

This paper presents a new approach which allows for the computation and optimization of feasible 3D flight trajectories within real time planning deadlines, for unmanned aerial systems (UAS) operating in environments with obstacles present. Sets of candidate flight trajectories have been generated through the application of maneuver automaton theory, where smooth trajectories are formed via the concatenation of predefined trim and maneuver primitives; generated using aircraft dynamic models. During typical UAS operations, multiple objectives may exist, therefore the use of multiobjective optimization can potentially allow for convergence to a solution which better reflects overall mission requirements. Multiple objective optimization of trajectories has been implemented through weighted sum aggregation. However, real-time planning constraints may be imposed on the multiobjective optimization process due to the existence of obstacles in the immediate path. Thus, a novel computationally adaptive trajectory decision (CATD) optimization system has been developed and implemented in simulation to dynamically manage, calculate and schedule system execution parameters to ensure that the trajectory solution search can generate a feasible solution, if one exists, within a given length of time. The inclusion of the CATD potentially increases overall mission efficiency and may allow for the implementation of the system on different UAS platforms with varying onboard computational capabilities. This approach has been demonstrated in this paper through simulation using a fixed wing UAS operating in low altitude environments with obstacles present.

Unmanned aerial vehicles (UAVs) with the potential of providing reliable high-rate connectivity, are becoming a promising component of future wireless networks. A UAV collects data from a set of randomly distributed sensors, where both the locations of these sensors and their data volume to be transmitted are unknown to the UAV. In order to assist the UAV in finding the optimal motion trajectory in the face of the uncertainty without the above knowledge whilst aiming for maximizing the cumulative collected data, we formulate a reinforcement learning problem by modelling the motion-trajectory as a Markov decision process with the UAV acting as the learning agent. Then, we propose a pair of novel trajectory optimization algorithms based on stochastic modelling and reinforcement learning, which allows the UAV to optimize its flight trajectory without the need for system identification. More specifically, by dividing the considered region into small tiles, we conceive state-action-reward-state-action (Sarsa) and Q-learning based UAV-trajectory optimization algorithms (i.e., SUTOA and QUTOA) aiming to maximize the cumulative data collected during the finite flight-time. Our simulation results demonstrate that both of the proposed approaches are capable of finding an optimal trajectory under the flight-time constraint. The preference for QUTOA vs. SUTOA depends on the relative position of the start and the end points of the UAVs.

In this article, we study the secure communication in unmanned aerial vehicle (UAV) aided and reconfigurable intelligent surface (RIS) empowered multiuser networks. In the proposed configuration, we consider UAV-mounted RIS to reflect the signal between the base station and the legitimate users in the presence of eavesdroppers. The problem is formulated as secrecy rate maximization with channel uncertainty constraints, which is nonconvex. Therefore, we decouple it into beamforming, phase shift, and UAV trajectory subproblems which are jointly optimized. For the beamforming and phase shift subproblems, we apply S-procedure and general sign-definiteness to transform them into tractable forms. And for the UAV trajectory, we unroll the constraints and apply first-order Taylor transform and the difference of two convex functions (DC) to obtain a relaxed convex problem that can be numerically solved. The proposed solution show effectiveness and improved the secrecy rate of the network.

Chapter 6 - Energy-efficient path planning of a solar-powered UAV for secure communication in the presence of eavesdroppers and no-fly zones

Minimizing Age of Information in UAV-Aided IoT Networks via Hierarchical Optimization of Cluster Heads and UAV Trajectories

With the rapid development of mobile edge computing (MEC) and unmanned aerial vehicle (UAV) communication networks, UAV-assisted edge computing has emerged as a promising paradigm for low-latency and energy-efficient computation. However, the time-varying nature of air-to-ground channels and the coupling between UAV trajectories and computation offloading decisions significantly increase system complexity. To address these challenges, this paper proposes an Adaptive UAV Edge Intelligence Framework (AUEIF) for joint UAV computation offloading and trajectory optimization under dynamic channels. Specifically, a dynamic graph-based system model is constructed to characterize the spatio-temporal correlation between UAV motion and channel variations. A hierarchical reinforcement learning-based optimization framework is developed, in which a high-level actor–critic module is responsible for generating coarse-grained UAV flight trajectories, while a low-level deep Q-network performs fine-grained optimization of task offloading ratios and computational resource allocation in real time. In addition, an adaptive channel prediction module leveraging long short-term memory (LSTM) networks is integrated to model temporal channel state transitions and to assist policy learning and updates. Extensive simulation results demonstrate that the proposed AUEIF achieves significant improvements in end-to-end latency, energy efficiency, and overall system stability compared with conventional deep reinforcement learning approaches and heuristic-based schemes while exhibiting strong robustness against dynamic and fluctuating wireless channel conditions.

Chance-constrained optimization provides a promi- sing framework for solving control and planning problems with uncertainties, due to its modeling capability to capture randomness in real-world applications. In this paper, we consider a UAV trajectory planning problem with probabilistic geo-fence, building on the chance-constrained optimization approach. In the considered problem, randomness of the model, such as the uncertain boundaries of geo-fences, is incorporated in the formulation. By solving the formulated chance-constrained optimization with a novel sampling based solution method, the optimal UAV trajectory is achieved while limiting the probability of collision with geo-fences to a prefixed threshold. Furthermore, to obtain a totally collision-free trajectory, i.e., avoiding the collision not only at the discrete time-steps but also within the entire time horizon, we build on the idea of an iterative scheme. That is, to iterate the solving of the chance-constrained optimization until the collision with probabilistic geo-fence is avoided at any time within the time horizon. At last, we validate the effectiveness of our method via numerical simulations.

With the rapid expansion of the Internet of Things (IoT), the demand for computational resources continues to soar, necessitating innovative solutions to address the needs of resource-constrained IoT users. Mobile edge computing (MEC) emerges as a promising remedy, mitigating the strain imposed by resource-intensive mobile applications. Concurrently, leveraging unmanned aerial vehicles (UAVs) as aerial platforms presents an enticing opportunity to enhance connectivity in wireless networks, owing to their on-demand deployment capabilities, high cruising altitudes, and maneuverability in three-dimensional space. This paper presents a comprehensive examination of UAV-enabled aerial MEC, elucidating its advantages, challenges, and recent advancements across various domains. Topics explored include joint optimization of UAV trajectory, computation offloading, and resource allocation, UAV deployment strategies, task scheduling, load balancing, interplay with other technologies, and machine learning-driven optimizations. Additionally, the paper outlines key avenues for future research endeavors.

Joint Optimization of UAV Energy Consumption and Trajectory Under Communication Service Quality and Perception Error Constraints

Joint optimization of trajectory and resource allocation in cellular-connected multi-UAV MEC networks

Dynamic soaring is an effective method to improve the endurance time and flight distance of small unmanned air vehicles. However, effective use the gradient change of the wind field to plan and track UAV trajectory has always been the focus and difficulty of current research. To solve this problem, trajectory optimization and tracking control for dynamic soaring of small unmanned air vehicles are presented in this paper. Firstly, the six degrees of freedom dynamics model with a consideration of the wind information is established. Secondly, soaring trajectory planning is formulated as an optimization problem and solved by using the Gaussian Pseudospectral method. Thirdly, a cascade dual loop scheme is used to design a tracking controller, where the outer loop employs a PID controller with virtual control signals for position control. A sliding mode control with adaptive non-singular fast terminal sliding mode control is proposed for inner loop attitude control. This method is robust to system parameter perturbation and uncertainties. Simulation shows that the proposed method can generate the trajectory in the gradient wind for dynamic soaring and ensure the aircraft tracks this trajectory even if in the presence of disturbance.