Yulin Li

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.

During my Ph.D. studies, I collaborated with Prof. Xindong Tang on the theory and application of moment and polynomial optimization, with an emphasis on polynomial formulations and sums-of-squares methods for collision avoidance and trajectory optimization. I also visited the Computational Robotics Lab in the John A. Paulson School of Engineering and Applied Sciences, Harvard University, where I worked with Prof. Heng Yang on numerical optimization and the development of high-performance numerical solvers for contact-rich motion planning.

I was a Postdoctoral Fellow at the National University of Singapore (NUS), where I worked with Prof. Fan Shi. My postdoctoral research explored physics-driven world models that combine differentiable high-fidelity physics simulators with learnable components, with the goal of building physically consistent, end-to-end differentiable models across a broad range of robot–environment interactions.

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.