Shaozu CAO

Shaozu CAO | 曹绍祖

I am a PhD graduate of HKUST Aerial Robotics Group, supervised by Prof. Shaojie SHEN.

During PhD I mainly focused on high-precision and globally consistent SLAM with multiple low-cost sensors. By fusing the information from various low-cost and small-footprint sensors, I aim to design versatile, robust and accurate localization solutions for general spatial-aware applications.

Email / Google Scholar / Github

Research

I am interested in multi-sensor fusion SLAM, 3D perception, semantic-level scene modelling and understanding in real-world environments.

	GVINS: Tightly Coupled GNSS-Visual-Inertial Fusion for Smooth and Consistent State Estimation Shaozu Cao, Xiuyuan Lu, Shaojie Shen IEEE Transactions on Robotics (TRO), 2022 paper / video / code GVINS significantly improves the global consistency of the visual-inertial odometry for long-range estimation.
	VINS-Fusion: A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors Tong Qin, Shaozu Cao, Jie Pan, Peiliang Li, Shaojie Shen Arxiv, 2019 paper / video / code VINS-Fusion achieves accurate localization for autonomous applications with multiple sensor modelities support.
	A-LOAM: An Advanced Implementation of LOAM Tong Qin, Shaozu Cao, Shaojie Shen code A-LOAM is an advanced implementation of LOAM (J. Zhang and S. Singh.), which greatly simplifies the code structure and provides an easy reference for SLAM researchers.
	RNNVis: Understanding Hidden Memories of Recurrent Neural Networks Yao Ming, Shaozu Cao, Ruixiang Zhang Zhen Li Yuanzhe Chen Yangqiu Song Huamin Qu project page / paper / video / code RNNVis enables visual analytics on understanding and comparing recurrent neural networks (RNNs) for text-based applications.