Tianhao Wu
Computer Vision Engineer at Mujin US
Duluth, Georgia, United States
Summary
🤩
Rockstar🎓
Top SchoolTianhao Wu is a computer vision engineer with a decade of experience across research and industry, currently applying his expertise at Mujin US on perception and robotics problems. He holds an MS in Computer Science from the University of Virginia and has built a strong research track record at Honda Research Institute, Carnegie Mellon, and ByteDance focused on SLAM, point-cloud prediction, and equivariant graph neural networks for autonomous systems. Tianhao contributes to open-source robotics tooling—improving Lie group support in the pypose library—demonstrating attention to the mathematical foundations that power differentiable robotics. He blends rigorous academic methods with production-oriented development, consistently turning advanced research into usable solutions for autonomy and manipulation.
10 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Computer Software Engineering, Bachelor's degree, Computer Software Engineering at Nankai UniversityMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Virginia
Github Skills (6)
pytorch10
robotics10
python10
linear-algebra9
unit-testing8
optimization7
Programming languages (4)
Github contributions (5)
pypose/pypose
May 2022 - Sep 2022
A library for differentiable robotics.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 review, 23 commits, 4 PRs in 4 months
Contributions summary:Tianhao's commits primarily involve refactoring and enhancing the `pypose/lietensor` module, specifically focusing on converting matrices to Lie groups. They've added and documented functions for converting matrices to various LieTensor types such as SO3, SE3, Sim3, and RxSO3, including comprehensive unit tests. These changes suggest a focus on improving the usability and functionality of the core mathematical operations within the differentiable robotics library.
pytorchroboticspythongeometric-deep-learningcomputer-graphics
pypose/tutorials
Sep 2022 - Dec 2022
PyPose tutorials.
Contributions:29 commits, 4 PRs, 28 pushes in 3 months
python
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.