1.
Wang, Zhipeng; Ng, Soon Xin; El-Hajjar, Mohammed
A 3D Spatial Information Compression Based Deep Reinforcement Learning Technique for UAV Path Planning in Cluttered Environments Journal Article
In: IEEE Open Journal of Vehicular Technology, vol. 6, pp. 647–661, 2025, ISSN: 2644-1330.
Abstract | Links | BibTeX | Tags: 3D path planning, 3D spatial information compression, Autonomous aerial vehicles, Classification algorithms, Convergence, deep reinforcement learning, Navigation, Path planning, Principal component analysis, Search problems, Solid modeling, Three-dimensional displays, Training, training efficiency, unmanned aerial vehicles
@article{wang_3d_2025,
title = {A 3D Spatial Information Compression Based Deep Reinforcement Learning Technique for UAV Path Planning in Cluttered Environments},
author = {Zhipeng Wang and Soon Xin Ng and Mohammed El-Hajjar},
url = {https://ieeexplore.ieee.org/document/10878448},
doi = {10.1109/OJVT.2025.3540174},
issn = {2644-1330},
year = {2025},
date = {2025-01-01},
urldate = {2025-10-08},
journal = {IEEE Open Journal of Vehicular Technology},
volume = {6},
pages = {647–661},
abstract = {Unmanned aerial vehicles (UAVs) can be considered in many applications, such as wireless communication, logistics transportation, agriculture and disaster prevention. The flexible maneuverability of UAVs also means that the UAV often operates in complex 3D environments, which requires efficient and reliable path planning system support. However, as a limited resource platform, the UAV systems cannot support highly complex path planning algorithms in lots of scenarios. In this paper, we propose a 3D spatial information compression (3DSIC) based deep reinforcement learning (DRL) algorithm for UAV path planning in cluttered 3D environments. Specifically, the proposed algorithm compresses the 3D spatial information to 2D through 3DSIC, and then combines the compressed 2D environment information with the current UAV layer spatial information to train UAV agents for path planning using neural networks. Additionally, the proposed 3DSIC is a plug and use module that can be combined with various DRL frameworks such as Deep Q-Network (DQN) and deep deterministic policy gradient (DDPG). Our simulation results show that the training efficiency of 3DSIC-DQN is 4.028 times higher than that directly implementing DQN in a 100 textbackslashtimes 100 textbackslashtimes 50 3D cluttered environment. Furthermore, the training efficiency of 3DSIC-DDPG is 3.9 times higher than the traditional DDPG in the same environment. Moreover, 3DSIC combined with fast recurrent stochastic value gradient (FRSVG), which can be considered as the most state-of-the-art DRL algorithm for UAV path planning, exhibits 2.35 times faster training speed compared with the original FRSVG algorithm.},
keywords = {3D path planning, 3D spatial information compression, Autonomous aerial vehicles, Classification algorithms, Convergence, deep reinforcement learning, Navigation, Path planning, Principal component analysis, Search problems, Solid modeling, Three-dimensional displays, Training, training efficiency, unmanned aerial vehicles},
pubstate = {published},
tppubtype = {article}
}
Unmanned aerial vehicles (UAVs) can be considered in many applications, such as wireless communication, logistics transportation, agriculture and disaster prevention. The flexible maneuverability of UAVs also means that the UAV often operates in complex 3D environments, which requires efficient and reliable path planning system support. However, as a limited resource platform, the UAV systems cannot support highly complex path planning algorithms in lots of scenarios. In this paper, we propose a 3D spatial information compression (3DSIC) based deep reinforcement learning (DRL) algorithm for UAV path planning in cluttered 3D environments. Specifically, the proposed algorithm compresses the 3D spatial information to 2D through 3DSIC, and then combines the compressed 2D environment information with the current UAV layer spatial information to train UAV agents for path planning using neural networks. Additionally, the proposed 3DSIC is a plug and use module that can be combined with various DRL frameworks such as Deep Q-Network (DQN) and deep deterministic policy gradient (DDPG). Our simulation results show that the training efficiency of 3DSIC-DQN is 4.028 times higher than that directly implementing DQN in a 100 textbackslashtimes 100 textbackslashtimes 50 3D cluttered environment. Furthermore, the training efficiency of 3DSIC-DDPG is 3.9 times higher than the traditional DDPG in the same environment. Moreover, 3DSIC combined with fast recurrent stochastic value gradient (FRSVG), which can be considered as the most state-of-the-art DRL algorithm for UAV path planning, exhibits 2.35 times faster training speed compared with the original FRSVG algorithm.
2.
Nguyen, Doan Hieu; Nguyen, Xuan Tung; Jeong, Seon-Geun; Chien, Trinh Van; Hanzo, Lajos; Hwang, Won-Joo
Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems Journal Article
In: IEEE Transactions on Vehicular Technology, pp. 1–6, 2025, ISSN: 1939-9359.
Abstract | Links | BibTeX | Tags: Cell-free massive MIMO, Convergence, Convolutional neural networks, Integrated circuit modeling, Massive MIMO, Pilot Allocation, Quantum circuit, Quantum Machine Learning, Quantum state, Qubit, Throughput, Training, Vectors
@article{nguyen_hybrid_2025,
title = {Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems},
author = {Doan Hieu Nguyen and Xuan Tung Nguyen and Seon-Geun Jeong and Trinh Van Chien and Lajos Hanzo and Won-Joo Hwang},
url = {https://ieeexplore.ieee.org/document/11091511},
doi = {10.1109/TVT.2025.3588212},
issn = {1939-9359},
year = {2025},
date = {2025-01-01},
urldate = {2025-10-08},
journal = {IEEE Transactions on Vehicular Technology},
pages = {1–6},
abstract = {A sophisticated hybrid quantum convolutional neural network (HQCNN) is conceived for handling the pilot assignment task in cell-free massive MIMO systems, while maximizing the total ergodic sum throughput. The existing model-based solutions found in the literature are inefficient and/or computationally demanding. Similarly, conventional deep neural networks may struggle in the face of high-dimensional inputs, require complex architectures, and their convergence is slow due to training numerous hyperparameters. The proposed HQCNN leverages parameterized quantum circuits (PQCs) relying on superposition for enhanced feature extraction. Specifically, we exploit the same PQC across all the convolutional layers for customizing the neural network and for accelerating the convergence. Our numerical results demonstrate that the proposed HQCNN offers a total network throughput close to that of the excessive-complexity exhaustive search and outperforms the state-of-the-art benchmarks.},
keywords = {Cell-free massive MIMO, Convergence, Convolutional neural networks, Integrated circuit modeling, Massive MIMO, Pilot Allocation, Quantum circuit, Quantum Machine Learning, Quantum state, Qubit, Throughput, Training, Vectors},
pubstate = {published},
tppubtype = {article}
}
A sophisticated hybrid quantum convolutional neural network (HQCNN) is conceived for handling the pilot assignment task in cell-free massive MIMO systems, while maximizing the total ergodic sum throughput. The existing model-based solutions found in the literature are inefficient and/or computationally demanding. Similarly, conventional deep neural networks may struggle in the face of high-dimensional inputs, require complex architectures, and their convergence is slow due to training numerous hyperparameters. The proposed HQCNN leverages parameterized quantum circuits (PQCs) relying on superposition for enhanced feature extraction. Specifically, we exploit the same PQC across all the convolutional layers for customizing the neural network and for accelerating the convergence. Our numerical results demonstrate that the proposed HQCNN offers a total network throughput close to that of the excessive-complexity exhaustive search and outperforms the state-of-the-art benchmarks.
3.
Zheng, Zijian; Deng, Yansha; Yi, Wenqiang; Shin, Hyundong; Nallanathan, Arumugam
Over-the-Air Computation Enabled Semi-Asynchronous Wireless Federated Learning Journal Article
In: IEEE Transactions on Communications, pp. 1–1, 2025, ISSN: 1558-0857.
Abstract | Links | BibTeX | Tags: aggregation optimization, Atmospheric modeling, Computational modeling, Convergence, Federated learning, Noise, Optimization, over-the-air computation, Semi-asynchronous federated learning, Servers, Synchronization, Training, Wireless networks
@article{zheng_over–air_2025,
title = {Over-the-Air Computation Enabled Semi-Asynchronous Wireless Federated Learning},
author = {Zijian Zheng and Yansha Deng and Wenqiang Yi and Hyundong Shin and Arumugam Nallanathan},
url = {https://ieeexplore.ieee.org/document/11048956},
doi = {10.1109/TCOMM.2025.3582727},
issn = {1558-0857},
year = {2025},
date = {2025-01-01},
urldate = {2025-10-08},
journal = {IEEE Transactions on Communications},
pages = {1–1},
abstract = {The emerging field of federated learning (FL) holds significant promise for advancing edge intelligence while preserving data privacy. However, as FL systems scale or become more heterogeneous, challenges such as spectrum scarcity and the straggler problem arise. To address these issues, this paper proposes SA-AirFed, a semi-asynchronous FL architecture compatible with Over-the-Air Computation (AirComp). We develop an efficient scheduling scheme that meets AirComp’s requirements and analyze the factors affecting convergence under the Lipschitz-Smooth condition. Building on insights from the convergence analysis, we design an adaptive algorithm that mitigates staleness from semi-asynchronous aggregation and noise from AirComp by dynamically adjusting aggregation weights, formulated as a convex quadratic programming problem. Experimental results on MNIST and CIFAR-10 demonstrate that SA-AirFed significantly reduces wall-clock training time while achieving greater robustness compared to baseline models.},
keywords = {aggregation optimization, Atmospheric modeling, Computational modeling, Convergence, Federated learning, Noise, Optimization, over-the-air computation, Semi-asynchronous federated learning, Servers, Synchronization, Training, Wireless networks},
pubstate = {published},
tppubtype = {article}
}
The emerging field of federated learning (FL) holds significant promise for advancing edge intelligence while preserving data privacy. However, as FL systems scale or become more heterogeneous, challenges such as spectrum scarcity and the straggler problem arise. To address these issues, this paper proposes SA-AirFed, a semi-asynchronous FL architecture compatible with Over-the-Air Computation (AirComp). We develop an efficient scheduling scheme that meets AirComp’s requirements and analyze the factors affecting convergence under the Lipschitz-Smooth condition. Building on insights from the convergence analysis, we design an adaptive algorithm that mitigates staleness from semi-asynchronous aggregation and noise from AirComp by dynamically adjusting aggregation weights, formulated as a convex quadratic programming problem. Experimental results on MNIST and CIFAR-10 demonstrate that SA-AirFed significantly reduces wall-clock training time while achieving greater robustness compared to baseline models.