https://bura.brunel.ac.uk/handle/2438/8631 2026-10-22T04:06:58Z 2026-10-22T04:06:58Z Zheng, Yu Wang, Kezhi Du, Zhicheng Xi, Wenji Yu, Gang Hou, Jinbo Hu, Haonan Zhang, Jie https://bura.brunel.ac.uk/handle/2438/34068 2026-10-22T02:00:38Z 2026-10-12T00:00:00Z

Title: Point Cloud for Wireless Communications: A Comprehensive Survey on Fundamentals, Techniques, and Applications Authors: Zheng, Yu; Wang, Kezhi; Du, Zhicheng; Xi, Wenji; Yu, Gang; Hou, Jinbo; Hu, Haonan; Zhang, Jie Abstract: Point cloud has recently emerged as a promising technology for next-generation wireless communication systems, offering precise geometric representations of complex environments. Despite growing interest, a comprehensive survey on its integration with wireless communications remains lacking. To bridge this gap, this survey provides a thorough review of state-of-the-art methods and applications of the point cloud across various wireless communication tasks over the last six years. We first introduce the fundamentals of point cloud for wireless communications, including acquisition techniques, preprocessing and representation methods, as well as open datasets and simulation tools. Subsequently, we investigate how point cloud effectively enhances key wireless communication tasks such as propagation channel modeling, blockage management, beam management, and proactive handoff. Additionally, emerging applications are extensively reviewed, including point cloud-enabled semantic wireless communications, wireless localization, metasurface coverage optimization, and digital-twin systems. Alongside these opportunities, we identify key challenges such as real-time processing of large-scale point clouds, robustness to environmental variations, multimodal fusion and calibration, generalization across diverse scenarios, the extension from single-user to multi-user wireless settings, the need for standardized benchmarking and open datasets, and associated privacy and security risks. We also outline promising research directions to guide the development of point cloud–enabled wireless networks.

2026-10-12T00:00:00Z Jiang, Feibo Pan, Xitao Dong, Li Wang, Kezhi Li, Xiaolong Li, Ruidong Wang, Changhong Pan, Cunhua https://bura.brunel.ac.uk/handle/2438/33978 2026-10-11T02:00:30Z 2026-04-06T00:00:00Z

Title: Agentic AI-Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks Authors: Jiang, Feibo; Pan, Xitao; Dong, Li; Wang, Kezhi; Li, Xiaolong; Li, Ruidong; Wang, Changhong; Pan, Cunhua Abstract: This study proposes a novel Agentic Retrieval-augmented generation with Mamba-Attention Integrated Transformer (ARMAIT) framework for multi-Uncrewed Aerial Vehicle (UAV) trajectory optimization. The framework is built upon Large Language Models (LLMs), incorporating Retrieval-Augmented Generation (RAG) empowered by Agentic AI and integrated with a UAV-specific knowledge base. Through the Agentic RAG, the LLM autonomously interprets high-level task requirements and identifies the key components necessary for trajectory optimization, including model inputs and outputs, network architecture, reward functions, and task constraints. To support efficient modeling across different system scales, we introduce the Mamba-Attention Integrated Transformer (MAIT), a hybrid neural architecture that combines the long-range dependency modeling capability of attention mechanisms with the efficient temporal dynamic representation of Mamba. Furthermore, a Trajectory-Group Relative Policy Optimization (T-GRPO) method is proposed to achieve unified policy gradient optimization in both discrete and continuous trajectory spaces for MAIT training. Extensive experimental results validate the feasibility and effectiveness of the proposed ARMAIT framework.

2026-04-06T00:00:00Z Hirtopanu, Tudor Wang, Zidong Serrano, Alan Liu, Weibo https://bura.brunel.ac.uk/handle/2438/33966 2026-10-10T02:00:40Z 2026-05-28T00:00:00Z

Title: Uncertainty-Gated Mixture Modeling for Anomaly Detection in Human-in-the-Loop Vehicle Systems Authors: Hirtopanu, Tudor; Wang, Zidong; Serrano, Alan; Liu, Weibo Abstract: Anomaly detection in human-driven vehicle telemetry is complicated by mixed uncertainty: nominal deviations may arise either from stochastic driver behavior or from genuine departures from learned vehicle dynamics. Conventional forecastingbased detectors typically treat both as predictive error, which can produce heavytailed anomaly-score distributions and elevated false-positive rates under unseen driver behavior. To address this limitation, we propose the Uncertainty-Gated Mixture Model (U-GMM), a feature-wise anomaly-scoring framework that combines conditional probabilistic forecasting with marginal plausibility estimation through an uncertaintyaware gating mechanism. The conditional component captures temporal consistency with recent history, while the marginal component evaluates whether an observation remains plausible under the broader nominal feature distribution. The learned gate then uses predictive uncertainty to adaptively balance these two sources of anomaly evidence, reducing undue score inflation in nominally stochastic channels while preserving sensitivity to dynamically inconsistent or globally implausible deviations. Experiments on real-world vehicle telemetry datasets show that the proposed framework improves threshold transfer under unseen-driver evaluation, achieving up to a 2.5× reduction in extreme false-positive rate while maintaining competitive fault detection performance under injected anomalies. These results indicate that reliable anomaly detection in human-in-the-loop systems depends not only on predictive model capacity, but also on uncertainty-aware score construction that distinguishes difficult-to-predict nominal behavior from genuinely abnormal system dynamics. Description: Data Availability Statement: The datasets used in this study are publicly available from the corresponding original sources. The HCRL dataset is available from [27], the Sonata dataset is available from IEEE DataPort [39], and the Automotive OBD-II dataset is available from RADAR4KIT [40]. Synthetic fault injections and derived experimental results were generated by the authors as part of this study.

2026-05-28T00:00:00Z Duan, Xiaoyou Ma, Guijun Liu, Weibo Fang, Kaiqi Wang, Yuzhe https://bura.brunel.ac.uk/handle/2438/33965 2026-10-09T06:50:09Z 2026-06-29T00:00:00Z

Title: Residual Reinforcement Learning for Robotic Assembly of Large-Scale Aerospace Components Authors: Duan, Xiaoyou; Ma, Guijun; Liu, Weibo; Fang, Kaiqi; Wang, Yuzhe Editors: Paszynski, Maciej; Barnard, Amanda S; Zhang, Yongjie Jessica Abstract: Robotic assembly of large-scale aerospace components demands millimeter-level accuracy under intermittent contacts, while collecting rich interaction data remains costly and risky. This paper presents a demonstration-guided residual reinforcement learning framework for precision assembly. A diffusion-based action-chunking policy trained from limited teleoperated demonstrations generates long-horizon nominal trajectories at a low frequency. A closed-loop residual policy optimized with PPO then adds per-step pose corrections to compensate for distribution shift and contact dynamics during the final mating phase. An action-hold sparse reward is introduced to promote stable mating rather than transient contact. Simulation experiments on KUKA KR210 industrial robot demonstrate that the proposed approach improves assembly success rate and efficiency compared with baselines, validating the effectiveness of combining imitation-based priors with closed-loop residual refinement.

2026-06-29T00:00:00Z