Skip to main content
Yu Xiang

Yu Xiang

Assistant Professor - Computer Science

Professional Preparation

Ph.D. - Electrical Engineering: Systems
University of Michigan - 2016
M.S. - Computer Science
Fudan University - 2010
B.S. - Computer Science
Fudan University - 2007

Research Areas

Interdisciplinary research primarily focusing  on robotics and computer vision.
  • Intelligent system or a robot understand its 3D environment.
  • Perception between an intelligent system and the 3D world.
  • Integrating perception, planning and control systematically.
  • Deploying robots in the real world which are capable of accomplishing tasks for humans.
Intelligent Robotics and Vision Lab (IRVL)
  • Perception: Unseen Object Instance Segmentation, Object Pose Estimation, Hand-Object Interaction, Transparent Object Recognition, 6D Object Pose Estimation, Semantic Mapping, Multi-Object Tracking, Object Category Detection and Pose Estimation
  • Planning and Learning: Manipulation Trajectory Optimization, Deep Metric Learning
  • Manipulation and Navigation: 6D Robotic Grasping, Neural Autonomous Navigation, Topological Navigation
We are interested in  fundamental research in intelligent robotics and computer vision. The scientific question we would like to address is how can robots conduct tasks autonomously in the physical world  to assist humans? For example, we wish to build robots that can cook a meal or clean a kitchen table for people, or robots that can take instructions from people and execute them to assist people in home environments.

In order to deploy robots to perform complex tasks autonomously, we conduct original research to enable robots to learn various skills in perception, planning, control and learning. We employ vision as the main sensing modality for robots.  We build robotic systems that integrate various robot skills, and study mechanisms that enable robots to improve their skills in a life-long way.


Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction. Yangxiao Lu, Ninad Khargonkar, Zesheng Xu, Charles Averill, Kamalesh Palanisamy, Kaiyu Hang, Yunhui Guo, Nicholas Ruozzi, Yu Xiang. In Robotics: Science and Systems (RSS) 2023 - Publication
FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments. Jishnu Jaykumar P, Yu-Wei Chao, Yu Xiang. In International Conference on Robotics and Automation (ICRA)  2023 - Publication


Sony Research Award - Sony Corporation of America [2022]
One of the 12 Best Papers in ECCV Selected for a IJCV Special Issue - IJCV [2018]
University of Washington CSE Postdoc Research Award - Paul G. Allen School of Computer Science & Engineering [2016]
ICCV Doctoral Consortium Travel Award - ICCV [2015]
Outstanding Master’s Thesis Award of Shanghai - Fudan University [2012]


Assistant Professor
University of Texas at Dallas [2021–Present]
Senior Research Scientist
NVIDIA [2018–2021]

News Articles

Team’s New AI Technology Gives Robot Recognition Skills a Big Lift


Perceptually-enabled Task Guidance
- DARPA [2021/10–2025/09]
Sony Research Award
- Sony Corporation of America [2023/09–2024/08]