Karen Liu is a professor and researcher with 15+ years building computational frameworks for realistic whole-body movement in digital agents and robots, currently leading work at Stanford's TML lab. Her group blends perception, decision-making, and low-level control to produce naturalistic motor behaviors in complex ecological environments, spanning computer graphics, biomechanics, and robotics. She has a long academic trajectory from UW to USC, Georgia Tech, and Stanford, and has translated research into practice as Chief Scientist at Activate3D. Beyond theory, she contributes to core robotics tooling—working on DART’s core model and rendering/kinematics code—bridging simulator fidelity with control algorithms. Her expertise covers numerical simulation, optimal control, and learning-based controllers for humanoids and assistive robots, with a rare focus on end-to-end “motion intelligence.” Based in Palo Alto, she combines deep academic rigor (PhD, University of Washington) with sustained open-source and systems-level impact.
15 years of coding experience
6 years of employment as a software developer
PhD, Computer Science, PhD, Computer Science at University of Washington
Contributions:95 commits, 12 PRs, 30 pushes in 4 years 8 months
Contributions summary:Karen appears to be working on the core model3d classes within the DART (Dynamic Animation and Robotics Toolkit) repository. They modified the `BodyNode`, `Dof`, and `C3D` classes, suggesting changes related to the representation and manipulation of 3D models and their data. The changes involve updating the `draw`, `drawHandles`, and other functions that would impact the rendering pipeline. These edits are likely part of improving the toolkit's ability to handle the dynamics and kinematics of robotic systems.
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.