Physics-Informed Neural Networks for Continuum Robots

Towards Fast Approximation of Static Cosserat Rod Theory

verfasst von

Martin Bensch, Tim David Job, Tim Lukas Habich, Thomas Seel, Moritz Schappler

Abstract

Sophisticated models can accurately describe deformations of continuum robots while being computationally demanding, which limits their application. Especially when considering sampling-based path planning, the model has to be evaluated frequently, which can lead to substantially increased computation times. We present a new approach to compute the entire shape of a tendon-driven continuum robot by a physics-informed neural network (PINN). The underlying physics is modelled with the Cosserat rod theory and incorporated into the PINN's loss function. The boundary values for the training are obtained from a reference model, solved by the shooting method. Our approach allows for a computation of the learned Cosserat rod model multiple orders of magnitude faster than a publicly available reference model. The median position deviation from the reference model lies below 1mm (0.5% of the simulated robot length) for each of the robot's 20 disks.

Organisationseinheit(en)

Institut für Mechatronische Systeme

Typ

Aufsatz in Konferenzband

Seiten

17293-17299

Anzahl der Seiten

7

Publikationsdatum

2024

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Software, Steuerungs- und Systemtechnik, Elektrotechnik und Elektronik, Artificial intelligence

Elektronische Version(en)

https://doi.org/10.1109/ICRA57147.2024.10610742 (Zugang: Geschlossen)