Details
| Translated title of the contribution | Eine auf Gauß-Prozessen basierende Kompensation der Nichtlinearitäten für weiche pneumatische Aktuatoren |
|---|---|
| Original language | English |
| Pages (from-to) | 440-448 |
| Number of pages | 9 |
| Journal | At-Automatisierungstechnik |
| Volume | 72 |
| Issue number | 5 |
| Early online date | 7 May 2024 |
| Publication status | Published - 27 May 2024 |
Abstract
Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation in situ. We utilize a short interaction maneuver, recorded a priori, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25-50 s of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.
Keywords
- feedforward control, Gaussian process, hysteresis modeling, pneumatic soft actuator, reference tracking, soft robotics
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Computer Science Applications
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: At-Automatisierungstechnik, Vol. 72, No. 5, 27.05.2024, p. 440-448.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Gaussian process-based nonlinearity compensation for pneumatic soft actuators
AU - Pawluchin, Alexander
AU - Meindl, Michael
AU - Weygers, Ive
AU - Seel, Thomas
AU - Boblan, Ivo
N1 - Publisher Copyright: © 2024 Walter de Gruyter GmbH, Berlin/Boston.
PY - 2024/5/27
Y1 - 2024/5/27
N2 - Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation in situ. We utilize a short interaction maneuver, recorded a priori, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25-50 s of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.
AB - Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation in situ. We utilize a short interaction maneuver, recorded a priori, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25-50 s of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.
KW - feedforward control
KW - Gaussian process
KW - hysteresis modeling
KW - pneumatic soft actuator
KW - reference tracking
KW - soft robotics
UR - http://www.scopus.com/inward/record.url?scp=85192832543&partnerID=8YFLogxK
U2 - 10.1515/auto-2023-0237
DO - 10.1515/auto-2023-0237
M3 - Article
AN - SCOPUS:85192832543
VL - 72
SP - 440
EP - 448
JO - At-Automatisierungstechnik
JF - At-Automatisierungstechnik
SN - 0178-2312
IS - 5
ER -