Details
| Original language | English |
|---|---|
| Title of host publication | Mechanisms and Machine Science |
| Publisher | Springer Netherlands |
| Pages | 199-206 |
| Number of pages | 8 |
| Volume | 65 |
| Publication status | Published - 27 Sept 2018 |
Publication series
| Name | Mechanisms and Machine Science |
|---|---|
| Volume | 65 |
| ISSN (Print) | 2211-0984 |
| ISSN (electronic) | 2211-0992 |
Abstract
Especially the field of medical robotics is faced with the challenge that contact between a robotic structure is not only tolerated but at the very core of the application, for example in minimally invasive surgery. Therefore, high demands regarding safety need to be met when operating a robotic structure in such a delicate environment. Soft material robotic systems offer the potential to surpass their rigid counterparts in this area due to their material inherent compliance and adaptability. Nonetheless, soft structures can also exhibit challenging characteristics like highly nonlinear deformation. This effect is often neglected when setting up deformation models. Recent approaches tackle this challenge by applying machine learning methods to learn the nonlinear behaviour. In previous research, we gained promising results from learning the kinematics of a soft pneumatic actuator (SPA) via a feedforward artificial neural network (ANN). To overcome a trial and error approach when designing an ANN, in this article we introduce Bayesian optimization to find suitable hyperparameters. This way an ANN architecture is found that exceeds the accuracy of our previous studies by more than a factor of 20 [9].
Keywords
- Artificial neural networks, Hyperparameter optimization, Kinematic modeling, Soft material robotic systems, Soft pneumatic actuators
ASJC Scopus subject areas
- Engineering(all)
- Mechanics of Materials
- Engineering(all)
- Mechanical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Mechanisms and Machine Science. Vol. 65 Springer Netherlands, 2018. p. 199-206 (Mechanisms and Machine Science; Vol. 65).
Research output: Chapter in book/report/conference proceeding › Contribution to book/anthology › Research › peer review
}
TY - CHAP
T1 - Optimization of neural network hyperparameters for modeling of soft pneumatic actuators
AU - Wiese, Mats
AU - Runge-Borchert, Gundula
AU - Raatz, Annika
PY - 2018/9/27
Y1 - 2018/9/27
N2 - Especially the field of medical robotics is faced with the challenge that contact between a robotic structure is not only tolerated but at the very core of the application, for example in minimally invasive surgery. Therefore, high demands regarding safety need to be met when operating a robotic structure in such a delicate environment. Soft material robotic systems offer the potential to surpass their rigid counterparts in this area due to their material inherent compliance and adaptability. Nonetheless, soft structures can also exhibit challenging characteristics like highly nonlinear deformation. This effect is often neglected when setting up deformation models. Recent approaches tackle this challenge by applying machine learning methods to learn the nonlinear behaviour. In previous research, we gained promising results from learning the kinematics of a soft pneumatic actuator (SPA) via a feedforward artificial neural network (ANN). To overcome a trial and error approach when designing an ANN, in this article we introduce Bayesian optimization to find suitable hyperparameters. This way an ANN architecture is found that exceeds the accuracy of our previous studies by more than a factor of 20 [9].
AB - Especially the field of medical robotics is faced with the challenge that contact between a robotic structure is not only tolerated but at the very core of the application, for example in minimally invasive surgery. Therefore, high demands regarding safety need to be met when operating a robotic structure in such a delicate environment. Soft material robotic systems offer the potential to surpass their rigid counterparts in this area due to their material inherent compliance and adaptability. Nonetheless, soft structures can also exhibit challenging characteristics like highly nonlinear deformation. This effect is often neglected when setting up deformation models. Recent approaches tackle this challenge by applying machine learning methods to learn the nonlinear behaviour. In previous research, we gained promising results from learning the kinematics of a soft pneumatic actuator (SPA) via a feedforward artificial neural network (ANN). To overcome a trial and error approach when designing an ANN, in this article we introduce Bayesian optimization to find suitable hyperparameters. This way an ANN architecture is found that exceeds the accuracy of our previous studies by more than a factor of 20 [9].
KW - Artificial neural networks
KW - Hyperparameter optimization
KW - Kinematic modeling
KW - Soft material robotic systems
KW - Soft pneumatic actuators
UR - http://www.scopus.com/inward/record.url?scp=85054128819&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-00329-6_23
DO - 10.1007/978-3-030-00329-6_23
M3 - Contribution to book/anthology
AN - SCOPUS:85054128819
VL - 65
T3 - Mechanisms and Machine Science
SP - 199
EP - 206
BT - Mechanisms and Machine Science
PB - Springer Netherlands
ER -