We are recruiting Ph.D. and master's students in Artificial Intelligence, Electronic Information, and Information and Communication Engineering. See admissions

36 camera poses around a basketball court and the resulting sparse point cloud
Sparse reconstruction of a court from 36 surrounding views, about 17,600 3D points.

Spatial intelligence

From point-cloud deep learning and self-supervised point-cloud understanding to city-scale 3D reconstruction, we turn images and point clouds into computable spatial structure. We also study video object tracking, person re-identification and perception for autonomous driving.

  • Point-cloud deep learning and self-supervised understanding
  • City-scale 3D reconstruction
  • Video object tracking, person re-identification and perception for autonomous driving
Research questionHow can city-scale 3D reconstruction maintain both rendering speed and robustness in complex scenes within the memory of consumer-grade GPUs?

Led by Guanghua Yang, with Di Wang and Haozhi Huang

Selected papers

2022

Improving deep learning on point cloud by maximizing mutual information across layers

Pattern Recognition, 2022

Lab authors: Di Wang

2022

Self-supervised point cloud understanding via mask transformer and contrastive learning

IEEE Robotics and Automation Letters, 2022

Lab authors: Di Wang

2021

Looking around in the neighbourhood: location estimation of outdoor urban images

IET Image Processing, 2021

Lab authors: Haozhi Huang

Framework of the UAV passive sensing testbed
UAV passive sensing testbed. A mmWave antenna and USRP form the transmitter; surveillance and reference antennas form the receiver.

Intelligent communication and low-altitude networks

We study URLLC, integrated sensing and communication (ISAC) and semantic communication for 6G, robust beamforming with reconfigurable antennas and intelligent surfaces, and airspace planning and vision-and-language navigation for low-altitude ISAC networks.

  • 6G URLLC and integrated sensing and communication
  • Semantic communication and information security
  • Low-altitude ISAC networks, airspace planning, vision-and-language navigation
Research questionHow can distributed low-altitude ISAC networks stay reliable and robust under cross-layer non-ideal conditions?

Led by Zheng Shi, with Xu Wang and Jintao Wang

Selected papers

2024

Joint beamforming optimization and mode selection for RDARS-aided MIMO systems

IEEE Transactions on Wireless Communications, 2024

Lab authors: Jintao Wang

2023

RIS-aided MIMO systems with hardware impairments: robust beamforming design and analysis

IEEE Transactions on Wireless Communications, 2023

Lab authors: Jintao Wang

2023

Smoothed noise contrastive mutual information neural estimation

Journal of the Franklin Institute, 2023

Lab authors: Xu Wang

2022

Smoothed InfoNCE: breaking the log N curse without overshooting

IEEE International Symposium on Information Theory (ISIT), 2022

Lab authors: Xu Wang

Quadruped robot carrying a LiDAR and several cameras
Quadruped platform with LiDAR and multiple cameras.

Embodied intelligence

We study 6D object pose estimation, point-cloud processing, vision foundation models and SLAM so that robots can locate themselves and objects in real environments. On top of this we work on multimodal tactile sensing, high-resolution tactile reconstruction and touch-driven dexterous hand control.

  • 6D pose estimation, point-cloud processing and SLAM
  • Multimodal tactile sensing and high-resolution 3D force reconstruction
  • Touch-driven dexterous hand perception and control
Research questionHow can visual pose estimation and tactile feedback work together within a single manipulation task on real workpieces?

Led by Deping Li, with Xiaohua Wu

Selected papers

2026

A bio-inspired proximity-tactile sensor array with tunable detection depth for embodied intelligenceCover article

International Journal of Extreme Manufacturing (IJEM), 2026

Lab authors: Xiaohua Wu

2025

Deep learning-assisted fingerprint-inspired flexible pressure sensor for tension monitoring in carbon fiber production

Advanced Science, 2025

Lab authors: Xiaohua Wu

Platforms and equipment

Our capture equipment covers aerial, ground and tabletop scales, plus a mmWave testbed for low-altitude sensing.

Multi-sensor capture kit

Multi-sensor capture kit

LiDAR, multi-camera array and IMU in one unit, used handheld or mounted on drones and robots.

Drone capture platform

Drone capture platform

Carries cameras and LiDAR for aerial capture of campuses and other large sites.

Quadruped platform

Quadruped platform

Carries LiDAR and cameras up stairs, through narrow passages and into indoor spaces, and is also used for SLAM experiments.

Mobile robot platform

Mobile robot platform

A lifting mast with multiple sensors for layered capture of facades and interiors.

Object scanning box

Object scanning box

A camera, lighting and a turntable work together to capture 3D data of single objects.

mmWave ISAC testbed

mmWave ISAC testbed

The transmitter uses a mmWave antenna and a USRP software-defined radio. The receiver uses surveillance and reference antennas with a second USRP. The system is used for UAV passive sensing experiments.

Admissions and collaboration

Whether you are applying for graduate study, joining undergraduate research or proposing a collaboration, tell us about your background, the direction you are interested in, and the question you want to work on.