Yu-ming Chen
Roboticist- Applied Scientist at The AI Institute
Cambridge, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolYu-ming Chen is a roboticist and applied scientist with nine years of experience building reinforcement-learning policies and model-based controllers that run on real robots, currently at the Robotics and AI Institute in Cambridge. He specializes in sim-to-real transfer for high-energy behaviors, having developed battery–motor circuit models to capture voltage sag and power limits that tighten simulation fidelity. His work spans reduced-order modeling, motion planning, and control for legged platforms, and he has shipped capabilities like landing recovery from aerial states and a unified hopping–wheelie–driving policy. A UPenn Ph.D. from the GRASP Lab and an MS in Robotics from Michigan, he blends rigorous academic foundations with hands-on system integration. Yu-ming is also an active contributor to the Drake robotics library, improving accelerometer calculations and solver robustness through bug fixes, feature enhancements, and testing. He is driven to push mobile robots’ physical capabilities while keeping their interactions safe and useful outside the lab.
9 years of coding experience
1 year of employment as a software developer
Master’s Degree, Robotics, Master’s Degree, Robotics at University of MichiganBachelor’s Degree, Physics, Bachelor’s Degree, Physics at National Taiwan UniversityDoctor of Philosophy - PhD, Robotics, Doctor of Philosophy - PhD, Robotics at University of Pennsylvania
Github Skills (7)
robotics10
c-language10
cprogramming-language10
drake10
testing10
mathematical-optimization9
python4
Programming languages (4)
Github contributions (5)
RobotLocomotion/drake
Jul 2019 - Jan 2022
Model-based design and verification for robotics.
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:4 reviews, 6 commits, 6 PRs in 2 years 6 months
Contributions summary:Yu-ming primarily focused on bug fixes and feature enhancements within the Drake robotics library, specifically concerning the accelerometer and the OSQP solver. They corrected accelerometer calculations, implemented a variable scaling feature for the SNOPT solver, and integrated time limit constraints in the OSQP solver, including related unit tests. The user also contributed to refactoring existing tests and adding new test cases to validate the functionality of the solvers, including error margins and status codes.
model-basedmodel-based-designroboticsdrakeverification
mposa/MEAM517
Aug 2020 - Oct 2020
Public Repository for MEAM 517 at the University of Pennsylvania
Contributions:68 commits, 12 PRs, 67 pushes in 1 month
pennsylvaniapublic-repositoryuniversity-of-pennsylvaniamongodb
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.