Yulin Li

I am currently a Postdoctoral Fellow at the National University of Singapore NUS, working with Prof. Fan Shi.

I received my Ph.D. degree in Robotics and Autonomous Systems from the Hong Kong University of Science and Technology (HKUST), where I was jointly supervised by Prof. Jun Ma and Prof. Michael Yu Wang. Prior to my doctoral studies, I earned the M.Sc. degree in Mechanical and Aerospace Engineering from the University of California, San Diego (UCSD) with a major in robot control and motion planning, and the B.Eng. degree in Mechatronic Engineering from Tongji University.

My research is driven by a long-term goal of enabling robots to interact with the physical world in a safe, capable, and intelligent manner — knowing when to avoid contact and when to exploit it. Over the past years, I have built up expertise in generating motion policies for mobile manipulators in complex scenarios, combining optimization-based planning with learning-based methods, with an emphasis on safe and adaptive behavior grounded in physical models and principled reasoning — from collision-free navigation in cluttered environments to contact reasoning during interaction. In my current postdoctoral research, I am pursuing a more general foundation for both: physics-driven world models that combine differentiable high-fidelity physics simulators with learnable components, yielding models that are physically consistent, end-to-end differentiable, and broadly applicable across the full spectrum of robot–environment interaction.

During my Ph.D. studies, I collaborated with Prof. Xindong Tang on the theory and application of Moment and Polynomial Optimization. I also visited the Computational Robotics Lab at Harvard University, where I worked with Prof. Heng Yang on high-performance numerical solvers for Contact-Implicit Motion Planning.