Wugang MENG

I am a PhD candidate in the Department of Electronic and Computer Engineering at the Hong Kong University of Science and Technology, under the guidance of Professor Fumin Zhang. I earned a Master of Science in Computer Science from the Georgia Institute of Technology in 2023 and my bachelor’s degree from Harbin Institute of Technology in 2019.

My research interests are lie in translating sensory information into effective robot action policies . Previously, I focused on intelligent perception and radar SLAM. Looking forward, I am enthusiastic about developing novel scene representations from vision signals and creating robot policies that effectively use these representations to perform high-level tasks.

News

May 06, 2025	Our new work BEINGS in the area of searching in 3D reconstruction map has been accepted by ICRA2025.
Sep 16, 2024	Our series of new works, namely NuRF and BEINGS, are now available for viewing on arXiv.
Sep 16, 2024	The blog.mwg.ink will not be supplied anymore, pls use www.mwg.ink to find me.
Dec 28, 2023	Our work about Gaussian Process Space Angle in DOA Estimation has been published.
Oct 10, 2023	Our work about ELM-DOA has been published.

Selected publications

Nurf: Nudging the particle filter in radiance fields for robot visual localization

Wugang Meng, Tianfu Wu, Huan Yin, and 1 more author

IEEE Transactions on Cognitive and Developmental Systems, 2025

HTML
A Hybrid Controller Design for Human-Assistive Piloting of an Underactuated Blimp

Wugang Meng, Tianfu Wu, Qiuyang Tao, and 1 more author

In 2024 36th Chinese Control and Decision Conference (CCDC), 2024

HTML
Identification of Time Delay in Pointing Tasks for Human-Blimp Interactions

Tianfu Wu, Wugang Meng, Sungjin Cho, and 1 more author

In 2024 9th International Conference on Automation, Control and Robotics Engineering (CACRE), 2024

HTML
Application of multi-angle millimeter-wave radar detection in human motion behavior and micro-action recognition

Zhaolin Zhang, Wugang Meng, Mingqi Song, and 4 more authors

Measurement Science and Technology, Jul 2022

Abs HTML

Millimeter-wave radar is widely used in family safety, rehabilitation, and assisted living due to its ability to operate in all weathers and all day. To address the problem whereby the radar detection angle significantly impacts human behavior recognition, a recognition method based on multi-angle radar observation is adopted. We proposed a novel radar selection method called the energy domain ratio method to choose a radar with more sensitive features. Then, local tangent space alignment and an adaptive extreme learning machine (ELM) are presented to enhance the recognition rate of the model in a high-noise environment. A multi-angle entropy feature and an improved ELM are developed to identify human micro-motion in a low-noise indoor environment. The effect of observation distance on the recognition effect was also explored. The experimental results show that the proposed model has a more than 86% recognition rate for human behavior in outdoor scenes and a recognition accuracy of more than 98% for indoor micro-action.