Details
| Original language | English |
|---|---|
| Title of host publication | 2024 IEEE International Conference on Robotics and Automation, ICRA 2024 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 17293-17299 |
| Number of pages | 7 |
| ISBN (electronic) | 9798350384574 |
| ISBN (print) | 979-8-3503-8458-1 |
| Publication status | Published - 2024 |
| Event | 2024 IEEE International Conference on Robotics and Automation, ICRA 2024 - Yokohama, Japan Duration: 13 May 2024 → 17 May 2024 |
Publication series
| Name | Proceedings - IEEE International Conference on Robotics and Automation |
|---|---|
| ISSN (Print) | 1050-4729 |
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.
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Engineering(all)
- Control and Systems Engineering
- Engineering(all)
- Electrical and Electronic Engineering
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2024 IEEE International Conference on Robotics and Automation, ICRA 2024. Institute of Electrical and Electronics Engineers Inc., 2024. p. 17293-17299 (Proceedings - IEEE International Conference on Robotics and Automation).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Physics-Informed Neural Networks for Continuum Robots
T2 - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
AU - Bensch, Martin
AU - Job, Tim David
AU - Habich, Tim Lukas
AU - Seel, Thomas
AU - Schappler, Moritz
N1 - Publisher Copyright: © 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85202441470&partnerID=8YFLogxK
U2 - 10.1109/ICRA57147.2024.10610742
DO - 10.1109/ICRA57147.2024.10610742
M3 - Conference contribution
AN - SCOPUS:85202441470
SN - 979-8-3503-8458-1
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 17293
EP - 17299
BT - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 13 May 2024 through 17 May 2024
ER -