Learning-based augmentation of physics-based models: an industrial robot use case

Retzler, András and Tóth, Roland and Schoukens, Maarten and Beintema, Gerben I. and Weigand, Jonas and Noël, Jean-Philippe and Kollár, Zsolt and Swevers, Jan (2024) Learning-based augmentation of physics-based models: an industrial robot use case. DATA-CENTRIC ENGINEERING, 5. No.-e12. ISSN 2632-6736

Preview

Text learningbased_augmentation_of_physicsbased_models_an_industrial_robot_use_case.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

In a Model Predictive Control (MPC) setting, the precise simulation of the behavior of the system over a finite time window is essential. This application-oriented benchmark study focuses on a robot arm that exhibits various nonlinear behaviors. For this arm, we have a physics-based model with approximate parameter values and an open benchmark dataset for system identification. However, the long-term simulation of this model quickly diverges from the actual arm’s measurements, indicating its inaccuracy. We compare the accuracy of black-box and purely physics-based approaches with several physics-informed approaches. These involve different combinations of a neural network’s output with information from the physics-based model or feeding the physics-based model’s information into the neural network. One of the physics-informed model structures can improve accuracy over a fully black-box model.

Actions (login required)

Edit Item