I am pursuing a Ph.D. degree in Control Science and Engineering at Harbin Engineering University. I am currently a jointly trained Ph.D. student in the School of Computer Science and Informatics at the University of Liverpool. I received my bachelor's degree from the College of Intelligent Systems Science and Engineering, Harbin Engineering University.
My recent research focuses on 3D scene representation and SLAM for multi-robot and embodied AI. I study how robots can build shared spatial memory by connecting geometric mapping, 3D Gaussian Splatting, semantic scene understanding, and foundation-model priors for navigation, manipulation, and collaboration.
I am recently visiting the Physical Intelligence Lab, in the Digital Innovation Facility at the University of Liverpool, working closely with Dr. Baoru Huang and Prof. Anh Nguyen.
I serve as a reviewer for journals including TPAMI, IJCV, TIP, TCSVT, T-RO, T-ASE, and TIM, and for conferences including CVPR, ICCV, ECCV, NeurIPS, ICLR, AAAI, ACM MM, ICRA, IROS, MICCAI, and ICASSP.
Joint Ph.D. training, Computer Science and Informatics
Ph.D. in Control Science and Engineering
B.Eng. in Measurement and Control Technology
Qi Shao*, Zhihao Cao*, Shuhao Zhai, Feng Tian, Anh Nguyen, Hesheng Wang, Baoru Huang
A collaborative monocular dense SLAM system that uses feed-forward 3D reconstruction priors to anchor scale across agents and verify inter-agent links, without depth sensors or known intrinsics.
arXiv / PDF / Project Page
Qi Shao*, Zhihao Cao*, Shuhao Zhai, Jing Zhang, Anh Nguyen, Hesheng Wang, Baoru Huang
An RGB-only multi-agent 3D Gaussian Splatting SLAM framework for collaborative scene reconstruction without active depth sensors.
arXiv / PDF / Project Page
Qi Shao*, Zhihao Cao*, Taoyu Wu, Shuhao Zhai, Anh Nguyen, Haoran Luo, Hong Liang, Baoru Huang
A dynamic-robust multi-camera Gaussian SLAM framework that uses the shared ego-motion of surround-view cameras to weight tracking and mapping against moving objects, and recovers occluded static regions from complementary views across cameras and time.
* Equal contribution.