Dec 3 (Wed) @9:00am: "Improving Friction Modeling for Robotics via Physics Informed Neural Networks," Asutay Ozmen, ECE PhD Defense

Location: Harold Frank Hall (HFH), Room 4110B (ECE Conf. Rm.)

Abstract

Accurately modeling friction in robotics remains a core challenge, as robotics simulators like Mujoco and PyBullet use simplified friction models or heuristics to balance computational efficiency with accuracy, where these simplifications and approximations can lead to substantial differences between simulated and physical performance. In this paper, we present a physics-informed friction estimation framework that enables the integration of well-established friction models with learnable components-requiring only minimal, generic measurement data. Our approach enforces physical consistency yet retains the flexibility to adapt to real-world complexities. We demonstrate, on an underactuated and nonlinear system, that the learned friction models, trained solely on small and noisy datasets, accurately simulate dynamic friction properties and reduce the sim-to-real gap. Crucially, we show that our approach enables the learned models to be transferable to systems they are not trained on. This ability to generalize across multiple systems streamlines friction modeling for complex, underactuated tasks, offering a scalable path toward bridging the sim-to-real gap in robotics and control.

Bio

Asutay Ozmen is a Ph.D. candidate in Electrical and Computer Engineering at the University of California, Santa Barbara, advised by Professor Katie Byl. His research focuses physics informed neural networks with an emphasis on improving friction modeling and reducing simulation to real world discrepancies. As a teaching assistant, Asutay received the Outstanding ECE Teaching Assistant Award twice. After completing his Ph.D., he will join Hitachi America R&D to develop develop learning based digital twins for increasing the sustainability of existing industrial systems and processes. He holds a B.S. in Electrical Engineering from Bilkent University in Turkey and an M.S. in Electrical and Computer Engineering from UCSB.

Hosted By: ECE Professor Katie Byl

Submitted By: Asutay Ozmen <ozmen@ucsb.edu>