Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV) |
| Seiten | 1213-1218 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 979-8-3315-1849-3 |
| Publikationsstatus | Veröffentlicht - 12 Dez. 2024 |
| Veranstaltung | 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024 - Dubai, Vereinigte Arabische Emirate Dauer: 12 Dez. 2024 → 15 Dez. 2024 |
Publikationsreihe
| Name | International Conference on Control, Automation, Robotics, and Vision |
|---|---|
| ISSN (Print) | 2474-2953 |
| ISSN (elektronisch) | 2474-963X |
Abstract
This work presents a body velocity control strategy for quadruped robots. Such control typically requires accurate kinematic and dynamic model knowledge, which is very challenging because of the multidimensional input-output system and the ground contact. Based on the inverse kinematics, we propose a Proportional-Derivative controlled robot that uses Iterative Learning Control to learn discrete body velocities, which are then generalized using the Gaussian Process Regression model for each joint separately. This controller design enables onboard control and learning in real-time without any simulation. This study illustrates the effectiveness of the proposed methodology over a range of velocities while emphasizing the minimal computational effort associated with its application in a practical context.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
- Mathematik (insg.)
- Steuerung und Optimierung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV). 2024. S. 1213-1218 (International Conference on Control, Automation, Robotics, and Vision).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Learning of a Rapid Prototyping Gait Library for a Quadruped Robot Using PD-ILC and Gaussian Processes
AU - Weiss, Manuel
AU - Pawluchin, Alexander
AU - Seel, Thomas
AU - Boblan, Ivo
N1 - Publisher Copyright: © 2024 IEEE.
PY - 2024/12/12
Y1 - 2024/12/12
N2 - This work presents a body velocity control strategy for quadruped robots. Such control typically requires accurate kinematic and dynamic model knowledge, which is very challenging because of the multidimensional input-output system and the ground contact. Based on the inverse kinematics, we propose a Proportional-Derivative controlled robot that uses Iterative Learning Control to learn discrete body velocities, which are then generalized using the Gaussian Process Regression model for each joint separately. This controller design enables onboard control and learning in real-time without any simulation. This study illustrates the effectiveness of the proposed methodology over a range of velocities while emphasizing the minimal computational effort associated with its application in a practical context.
AB - This work presents a body velocity control strategy for quadruped robots. Such control typically requires accurate kinematic and dynamic model knowledge, which is very challenging because of the multidimensional input-output system and the ground contact. Based on the inverse kinematics, we propose a Proportional-Derivative controlled robot that uses Iterative Learning Control to learn discrete body velocities, which are then generalized using the Gaussian Process Regression model for each joint separately. This controller design enables onboard control and learning in real-time without any simulation. This study illustrates the effectiveness of the proposed methodology over a range of velocities while emphasizing the minimal computational effort associated with its application in a practical context.
KW - Iterative learning control
KW - Nonlinear Systems
KW - Real-time Control
KW - Robotics
UR - http://www.scopus.com/inward/record.url?scp=85217412650&partnerID=8YFLogxK
U2 - 10.1109/ICARCV63323.2024.10821620
DO - 10.1109/ICARCV63323.2024.10821620
M3 - Conference contribution
AN - SCOPUS:85217412650
SN - 979-8-3315-1850-9
T3 - International Conference on Control, Automation, Robotics, and Vision
SP - 1213
EP - 1218
BT - 2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV)
T2 - 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024
Y2 - 12 December 2024 through 15 December 2024
ER -