2026· IEEE Open Journal of the Communications Society· Vol 7, pp. 9067-9081· 0 citations· 30 references
TL;DR
Simulation results confirm the effectiveness of distributed optimization and DRL-based coordination for scalable, resilient, and adaptable UAV deployment in disaster response and other mission-critical scenarios.
Abstract
This paper proposes a multi-tier coordination framework for autonomous Unmanned Aerial Vehicle (UAV) swarm deployment in joint radar-communication (JRC)-enabled post-disaster assessment. The proposed framework adopts a distributed/coordinated optimization approach, where analytical updates are derived for the initial 3D UAV positioning and bandwidth–power allocation, jointly optimizing sensing quality and communication performance under resource constraints. Building on this foundation, a Deep Reinforcement Learning (DRL) agent is also developed to dynamically refine UAVs’ positions in real time, adapting to environmental uncertainties and mission dynamics. The proposed hybrid optimization–learning framework targets the balance between optimality and complexity by enabling adaptive and intelligent decision-making for real-time and efficient deployment of distributed UAV swarms. The DRL policy adapts well to dynamic, mobile-target scenarios, while the distributed optimization enables rapid and pre-training-free deployment, making it ideal for time-critical missions. Unlike existing approaches that either rely on centralized control or neglect the interplay between sensing and communication, our framework enables distributed, infrastructure-free coordination. Simulation results show that the proposed framework achieves up to 13% and 27% higher average sensing SNR when varying the number of targets and total available power per UAV, respectively, compared to communication-centric, radar-centric, and learning-based baselines. These results confirm the effectiveness of distributed optimization and DRL-based coordination for scalable, resilient, and adaptable UAV deployment in disaster response and other mission-critical scenarios.
Results show that topology‐aware cooperative learning can provide a scalable and practical solution for reliable UAV communication in future intelligent aerial and 6G‐enabled networks, particularly in dense deployments.
V. Nam, A. Chehri, Weiwei Jiang et al.· Expert systems· 0 citations
A multi-agent deep reinforcement learning (MADRL) methodology based on the Multi-Agent Proximal Policy Optimization (MAPPO) approach, which simultaneously achieves high field coverage completeness, robust communication energy efficiency, and a high depot-return rate under hard battery constraints without any inter-UAV communication overhead at execution time.
A hierarchical joint optimization algorithm is developed within a multi-agent deep reinforcement learning (MADRL) framework to coordinate UAVs and MTs in a distributed manner and outperforms other benchmarks under varying network scales and capabilities by jointly optimizing UAV operations and resource utilization.
Tiankui Zhang, Wenlong Xu, Tianyi Shi et al.· IEEE Internet of Things Jour...· 0 citations
Unmanned Aerial Vehicles (UAVs) have gained widespread attention in diverse applications like military, medical, aerial surveillance and many more. Presently, the problem of limited bandwidth and geographic factors has raised the need for effective and timely data transfer. Training UAVs with reinforcement learning-based algorithms facilitates autonomous decision-making capabilities. In this paper, we proposed an intelligent system for the optimal UAV selection process by evaluating the continuous performance of each UAV. The analyzing factors are based on the real-world factors affecting the quality of signals, such as noise interference, relative motion between source and wave, and transmission power. Based on the systematic conditions observed, the system provides efficient rewards. To promote the selection of the optimal UAV and enhance the learning process, the state information of the UAV is fed into a deep neural network (DQN), which predicts the 'Q-values'. Our system implements a deep Q-learning algorithm, which enhances the agent's performance by systematically learning from its experience. The model operates accurately by selecting the most reliable UAV, thus, enhancing the throughput by optimal power allocation. It outperforms other conventional models in terms of timely data delivery and energy utilization. The system adapts various complex patterns by analyzing the historical and present scenarios. Empowered by this intelligent system, time-critical decision-making can be achieved with minimal energy consumption.
Divyanshu Bhardwaj, Angel Kanjiya, N. Jadav et al.· 2026 IEEE International Work...· 0 citations
In temporary emergency communication coverage scenarios where terrestrial communication infrastructure is damaged or lacks sufficient capacity, UAVs equipped with base stations have emerged as an effective solution due to their flexible deployment and rapid response capability. However, in multi-UAV networks, the three-dimensional deployment of UAVs significantly affects air-to-ground link quality, while power allocation further determines the level of system interference and throughput performance. To address this issue, this paper considers a multi-UAV communication system and jointly takes into account user link reliability and service requirement satisfaction, thereby establishing a joint optimization model for QoS-constrained coverage and network throughput. To address the non-convex joint optimization problem, a problem-tailored dual-population cooperative NSGA-II framework, termed IDPC-NSGA-II, is developed. By coupling dual-population evolution, adaptive mutation, uncovered-user-guided local search, and interference-aware repair with the characteristics of multi-UAV emergency communications, the proposed method improves the trade-off between QoS-constrained coverage and network throughput. Simulation results in a representative emergency communication scenario show that the proposed method achieves a favorable trade-off between QoS-constrained coverage and throughput, and outperforms the compared algorithms under the considered network setting.
Guifen Chen, Ruiyang Liu· Digital Signal and Computer...· 0 citations
Unmanned Aerial Vehicles (UAVs) are increasingly deployed as embodied aerial agents in low-altitude economies, forming mobile aerial edge networks that enable flexible computation offloading for vehicles. However, their limited endurance and frequent join/leave behaviours result in highly dynamic topologies, undermining long-term resource availability. Moreover, existing vehicle-centric task scheduling strategies cause resource contention and decision complexity in dense environments. To address these challenges, this paper proposes a hierarchical and scalable reinforcement learning-based scheduling framework (SkySched). In SkySched, UAVs collaboratively make deployment and task scheduling decisions. The framework consists of two tightly coupled modules. First, an adaptive UAV deployment module introduces a capability encoding mechanism that compresses heterogeneous UAV attributes into a unified one-dimensional capability index. This compact representation enables a Scalable Proximal Policy Optimization (SPPO) algorithm to efficiently coordinate UAV positioning, maximizing task coverage and sustaining network-wide computing availability under dynamic topology variations. Second, a hierarchical task scheduling module is designed, where K-means-based Roadside Unit (RSU) clustering enables vertical task offloading, while a SPPO-driven horizontal UAV-to-UAV task redistribution mechanism achieves fine-grained load balancing across the UAV swarm. Simulations demonstrate that SkySched consistently outperforms state-of-the-art methods in terms of task coverage and load fairness, validating its effectiveness as an agentic AI-driven embodied networking solution for UAV-assisted vehicular edge computing.
Meng Yi, V. Lee, Miao Du et al.· IEEE Transactions on Cogniti...· 0 citations
