RESEARCH GROUP

“Theory is when you know everything but nothing works. Practice is when everything works but no one knowns why. In our lab, theory and practice are combined: nothing works and no one knows why.” – Unknown Quotes

NEWS | 团队动态

截止2026-05-09, 刀毅、谭海阳、刘晧、肖佳妮四位同学顺利完成硕士答辩。

SPOTLIGHT WORK | 团队工作

Human Motion Tracking via WiFi Signals (Sponsored by ChingMu Co. Ltd.)

WiFlow: Continuous Human Pose Estimation via WiFi Signals

Related Publications:

[1] Yi Dao*, Haiwei Zhang, Shaohan Feng, Jinxiang Fang and Wenbo Wang, “ProbSparse Attention with Stacked Group Convolution for Wireless Signal-Based Human Activity Recognition,” 2024 16th International Conference on Wireless Communications and Signal Processing (WCSP 2024), Hefei, China, 2024, pp. 1349-1354, doi: 10.1109/WCSP62071.2024.10827307. [Source Code]

[2] Haiyang Tan*, Yi Dao*, Haiwei Zhang, Tingting Guo and Wenbo Wang, “WiFi Signal-based Human Activity Recognition using Bidirectional Mamba Models,” 2025 IEEE 11th World Forum on Internet of Things (WF-IoT), Chengdu, China, 2025, pp. 1-6, doi: 10.1109/WF-IoT64238.2025.11270783. [Source Code]

[3] Yi Dao*, Lankai Zhang*, Hao Liu*, Haiwei Zhang and Wenbo Wang, “WiFlow: A Lightweight WiFi-based Continuous Human Pose Estimation Network with Spatio-Temporal Feature Decoupling,” arxiv preprint arxiv:2602.08661, 2026. [Source Code]

Sim2Real Strategy Adaptation for Autonomous Drones (Sponsored by Qingjia Aviation Co. Ltd.)

Drone trajectory learning — Drone trajectory exploration based on visual reinforcement learning

Related Publications:

[1] Simin Zhang*, Chunxi Yang, Xiufeng Zhang and Wenbo Wang, “An End-to-End UAV Obstacle Avoidance Approach Fusing Wavelet Convolution and KAN Networks,” 2025 44th Chinese Control Conference (CCC 2025), Chongqing, China, 2025, pp. 4828-4833, doi: 10.23919/CCC64809.2025.11178342 (Poster Paper Award) [Poster].

[2] Hao Liu*, Guomeng Chen*, Shuyi Dong*, Zhiqiang Zhou and Wenbo Wang, “MambaSOD: Small Object Detection from Drone Perspective in a Mamba-based Query-Feature Interaction Framework,” accepted by Unmanned Systems, 2026. [Source Code]

AI Agent-driven Decision Making for IIoTs and Intelligent Production (Sponsored by NSFC)

World Model-driven Process Industry Operations: An Offline Reinforcement Learning

Related Publications:

[1] Yang Zhao, J. Yang, Wenbo Wang, H. Yang and D. Niyato, “TranDRL: A Transformer-driven deep reinforcement learning enabled prescriptive maintenance framework”, in IEEE Internet of Things Journal (IoTJ-3), vol. 11, no. 21, pp. 35432 - 35444, 2024, arXiv:2309.16935, 2024. [IEEEXplore]

[2] Yanlei Yin*, Lihua Wang, Dinh Thai Hoang, Wenbo Wang, and Dusit Niyato, “Sparse Attention-driven Quality Prediction for Production Process Optimization in Digital Twins”, in IEEE Internet of Things Journal (IoTJ-4), vol. 11, no. 23, pp. 38569 - 38584, 2024. [IEEEXplore]

[3] Yanlei Yin*, Raymond Chiong, Chao Deng, Lihua Wang, Dusit Niyato and Wenbo Wang, “World Model-driven Process Industry Operations: An Offline Reinforcement Learning Solution based on Conditional Diffusion,” in Computers in Industry (CII-1), vol. 177, pp. 104442, 17 Feb., 2026, doi: 10.1016/j.compind.2026.104442. [Sciencedirect] [Code & Demonstration Dataset]

[4] Jie Li, Xingyu Liu, Wenbo Wang and Xiaodong Fu, “A Strategy-Proof Mechanism for Fair Allocation of Multiple Resources with Access Constraints in Mobile Edge Computing,” accepted by IEEE Transactions on Vehicular Technology (TVT-1), 2026.