Guanang Su
Guanang Su

Ph.D. Student

University of Minnesota, Twin City

Welcome to my workspace!

šŸ‘‹ Hi, Iā€™m Guanang Su @xxs90, you can also call me Shirley.

šŸ‘€ Iā€™m interested in Robotics, snowboarding and reading.

šŸŒ± I’m a Ph.D. student in Robotics: Perception and Manipulation (RPM) Lab with Professor Karthik Desingh at University of Minnesota, Twin City. The research topic is robot learning and manipulation.

šŸŽ“ Before that, I was a research assistant advised by Professor Robert Platt in THe Helping Hands Lab. I am working on robot manipulation and learning with equivariant symmetric.

Willing to be a robotic scientist!

Download CV
Interests
  • Learning in Robotics
  • Geometric Understanding of Environment
  • Biomendical Applications
Education

  • Ph.D. in Computer Science

    University of Minnesota, Twin City

  • M.S. in Robotics

    Northeastern University

  • B.S. in Computer Engineering

    Virginia Polytechnic Institute and State University, Blacksburg, U.S.A.

Recent Publications
Dian Wang, Xupeng Zhu, Jung Yeon Park, Mingxi Jia, Guanang Su, Robert Platt, Robin Walters (2023). A General Theory of Correct, Incorrect, and Extrinsic Equivariance. In NeurIPS 2023.
PDF Cite Code Video Source Document
Mingxi Jia*, Dian Wang*, Guanang Su, David Klee, Xupeng Zhu, Robin Walters, Robert Platt (2023). SEIL: Simulation-augmented Equivariant Imitation Learning. In ICRA 2023, (Also CoRL 2022 Workshop).
PDF Cite Code Video Source Document
Xupeng Zhu, Dian Wang, Ondrej Biza, Guanang Su, Robin Walters, Robert Platt (2022). Sample Efficient Grasp Learning Using Equivariant Models. In RSS 2022, (Also RLDM 2022 & ICRA 2022 Workshop).
PDF Cite Code Video Source Document
Xupeng Zhu, Dian Wang, Guanang Su, Ondrej Biza, Robin Walters, Robert Platt (2013). On Robot Grasp Learning Using Equivariant Models. In Autonomous Robots 2023.
PDF Cite Code Video Source Document
Selected Projects
ORB-SLAM3 on iPhone
Visual SLAM

ORB-SLAM3 on iPhone

ORB-SLAM3 is a state-of-the-art visual SLAM. This feature-based SLAM creates a sparse mapping and gives accurate localization. Also, it contains modules such as place recognition, loop detection, bundle adjustment, etc. The process is divided into three phases: short-term phase, medium-phase, and long-term phase. However, it is hard to access ORB-SLAM for users who are not familiar with Linux, computer vision, and Github. At the same time, the hardware like Realsense camera and IMU that ORBSLAM requires are hard to access. We create a streaming layer between iPhone and ORBSLAM on Ubuntu, so that everyone can play with the state-of-the-art SLAM via iPhone and a PC with pre-installed ORB-SLAM. This is a final project for course EECE5554: Robotics: Navigation and Sensing in Northeastern University. It is developed by Chenghao Wang, Meishan Li, Mingxi Jia and Me. More about this project is in this GitLab Page. Link Here.

Improving Sample Efficiency of Robot Grasping
Reinforcement Learning

Improving Sample Efficiency of Robot Grasping

In goal-conditioned reinforcement learning problems, the sample efficiency is often a drawback that most of the explorations are not consider as very useful experience because they are failure episodes, which makes low sample efficiency. In this paper, we implemented a module of Hindsight Experience Replay (HER) in several goal-conditioned environments, to discover its utility of improving sample efficiency. Based on Deep Deterministic Policy Gradient (DDPG), the experiments showed that the HER module helps the agent learn much faster with more robustness. We then discussed about the limitation of HER and how hyper parameters effects its performance. This is a final project for course CS5180: Reinforcement Learning and Sequential Decision Making in Northeastern University. It is developed by me and Mingxi Jia. More details could be viewed in our pdf report.

News
Example Talk
Blogs