Learning Transferable Friction Models and LuGre Identification via Physics Informed Neural Networks
This work addresses the sim-to-real gap in robotics and control by providing a scalable and interpretable method for friction modeling, though it is incremental as it builds on existing friction models with learnable enhancements.
The paper tackles the challenge of accurately modeling friction in robotics by developing a physics-informed friction estimation framework that integrates established models with learnable components, requiring minimal data; it demonstrates that learned models, trained on small, noisy datasets, reduce the sim-to-real gap and are transferable to untrained systems.
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 and interpretable path toward bridging the sim-to-real gap in robotics and control.