Details
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE International Conference on Soft Robotics, RoboSoft 2023 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (electronic) | 9798350332223 |
| ISBN (print) | 979-8-3503-3223-0 |
| Publication status | Published - 2023 |
| Event | 2023 IEEE International Conference on Soft Robotics, RoboSoft 2023 - Singapore, Singapore Duration: 3 Apr 2023 → 7 Apr 2023 |
Publication series
| Name | IEEE International Conference on Soft Robotics |
|---|---|
| ISSN (Print) | 2769-4526 |
| ISSN (electronic) | 2769-4534 |
Abstract
Variable stiffness actuator (VSA) designs are manifold. Conventional model-based control of these nonlinear systems is associated with high effort and design-dependent assumptions. In contrast, machine learning offers a promising alternative as models are trained on real measured data and nonlinearities are inherently taken into account. Our work presents a universal, learning-based approach for position and stiffness control of soft actuators. After introducing a soft pneumatic VSA, the model is learned with input-output data. For this purpose, a test bench was set up which enables automated measurement of the variable joint stiffness. During control, Gaussian processes are used to predict pressures for achieving desired position and stiffness. The feedforward error is on average 11.5% of the total pressure range and is compensated by feedback control. Experiments with the soft actuator show that the learning-based approach allows continuous adjustment of position and stiffness without model knowledge.
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Engineering(all)
- Control and Systems Engineering
- Engineering(all)
- Mechanical Engineering
- Mathematics(all)
- Control and Optimization
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 IEEE International Conference on Soft Robotics, RoboSoft 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (IEEE International Conference on Soft Robotics).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Learning-based Position and Stiffness Feedforward Control of Antagonistic Soft Pneumatic Actuators using Gaussian Processes
AU - Habich, Tim Lukas
AU - Kleinjohann, Sarah
AU - Schappler, Moritz
N1 - Funding Information: ACKNOWLEDGMENT The authors acknowledge the support of this project by the German Research Foundation (Deutsche Forschungsge-meinschaft) under grant number 433586601.
PY - 2023
Y1 - 2023
N2 - Variable stiffness actuator (VSA) designs are manifold. Conventional model-based control of these nonlinear systems is associated with high effort and design-dependent assumptions. In contrast, machine learning offers a promising alternative as models are trained on real measured data and nonlinearities are inherently taken into account. Our work presents a universal, learning-based approach for position and stiffness control of soft actuators. After introducing a soft pneumatic VSA, the model is learned with input-output data. For this purpose, a test bench was set up which enables automated measurement of the variable joint stiffness. During control, Gaussian processes are used to predict pressures for achieving desired position and stiffness. The feedforward error is on average 11.5% of the total pressure range and is compensated by feedback control. Experiments with the soft actuator show that the learning-based approach allows continuous adjustment of position and stiffness without model knowledge.
AB - Variable stiffness actuator (VSA) designs are manifold. Conventional model-based control of these nonlinear systems is associated with high effort and design-dependent assumptions. In contrast, machine learning offers a promising alternative as models are trained on real measured data and nonlinearities are inherently taken into account. Our work presents a universal, learning-based approach for position and stiffness control of soft actuators. After introducing a soft pneumatic VSA, the model is learned with input-output data. For this purpose, a test bench was set up which enables automated measurement of the variable joint stiffness. During control, Gaussian processes are used to predict pressures for achieving desired position and stiffness. The feedforward error is on average 11.5% of the total pressure range and is compensated by feedback control. Experiments with the soft actuator show that the learning-based approach allows continuous adjustment of position and stiffness without model knowledge.
UR - http://www.scopus.com/inward/record.url?scp=85160556070&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2303.01840
DO - 10.48550/arXiv.2303.01840
M3 - Conference contribution
AN - SCOPUS:85160556070
SN - 979-8-3503-3223-0
T3 - IEEE International Conference on Soft Robotics
BT - 2023 IEEE International Conference on Soft Robotics, RoboSoft 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Soft Robotics, RoboSoft 2023
Y2 - 3 April 2023 through 7 April 2023
ER -