Details
| Original language | English |
|---|---|
| Article number | 105879 |
| Number of pages | 8 |
| Journal | Control engineering practice |
| Volume | 145 |
| Early online date | 10 Feb 2024 |
| Publication status | Published - Apr 2024 |
Abstract
This work proposes Autonomous Iterative Motion Learning (AI-MOLE), a method that enables systems with unknown, nonlinear dynamics to autonomously learn to solve reference tracking tasks. The method iteratively applies an input trajectory to the unknown dynamics, trains a Gaussian process model based on the experimental data, and utilizes the model to update the input trajectory until desired tracking performance is achieved. Unlike existing approaches, the proposed method determines necessary parameters automatically, i.e., AI-MOLE works plug-and-play and without manual parameter tuning. Furthermore, AI-MOLE only requires input/output information, but can also exploit available state information to accelerate learning. While other approaches are typically only validated in simulation or on a single real-world testbed using manually tuned parameters, we present the unprecedented result of validating the proposed method on three different real-world robots and a total of nine different reference tracking tasks without requiring any a priori model information or manual parameter tuning. Over all systems and tasks, AI-MOLE rapidly learns to track the references without requiring any manual parameter tuning at all, even if only input/output information is available.
Keywords
- Autonomous systems, Iterative learning control, Nonlinear systems, Reference tracking, Reinforcement learning, Robot learning
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Computer Science Applications
- Engineering(all)
- Electrical and Electronic Engineering
- Mathematics(all)
- Applied Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Control engineering practice, Vol. 145, 105879, 04.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - AI-MOLE
T2 - Autonomous Iterative Motion Learning for unknown nonlinear dynamics with extensive experimental validation
AU - Meindl, Michael
AU - Bachhuber, Simon
AU - Seel, Thomas
PY - 2024/4
Y1 - 2024/4
N2 - This work proposes Autonomous Iterative Motion Learning (AI-MOLE), a method that enables systems with unknown, nonlinear dynamics to autonomously learn to solve reference tracking tasks. The method iteratively applies an input trajectory to the unknown dynamics, trains a Gaussian process model based on the experimental data, and utilizes the model to update the input trajectory until desired tracking performance is achieved. Unlike existing approaches, the proposed method determines necessary parameters automatically, i.e., AI-MOLE works plug-and-play and without manual parameter tuning. Furthermore, AI-MOLE only requires input/output information, but can also exploit available state information to accelerate learning. While other approaches are typically only validated in simulation or on a single real-world testbed using manually tuned parameters, we present the unprecedented result of validating the proposed method on three different real-world robots and a total of nine different reference tracking tasks without requiring any a priori model information or manual parameter tuning. Over all systems and tasks, AI-MOLE rapidly learns to track the references without requiring any manual parameter tuning at all, even if only input/output information is available.
AB - This work proposes Autonomous Iterative Motion Learning (AI-MOLE), a method that enables systems with unknown, nonlinear dynamics to autonomously learn to solve reference tracking tasks. The method iteratively applies an input trajectory to the unknown dynamics, trains a Gaussian process model based on the experimental data, and utilizes the model to update the input trajectory until desired tracking performance is achieved. Unlike existing approaches, the proposed method determines necessary parameters automatically, i.e., AI-MOLE works plug-and-play and without manual parameter tuning. Furthermore, AI-MOLE only requires input/output information, but can also exploit available state information to accelerate learning. While other approaches are typically only validated in simulation or on a single real-world testbed using manually tuned parameters, we present the unprecedented result of validating the proposed method on three different real-world robots and a total of nine different reference tracking tasks without requiring any a priori model information or manual parameter tuning. Over all systems and tasks, AI-MOLE rapidly learns to track the references without requiring any manual parameter tuning at all, even if only input/output information is available.
KW - Autonomous systems
KW - Iterative learning control
KW - Nonlinear systems
KW - Reference tracking
KW - Reinforcement learning
KW - Robot learning
UR - http://www.scopus.com/inward/record.url?scp=85184837982&partnerID=8YFLogxK
U2 - 10.1016/j.conengprac.2024.105879
DO - 10.1016/j.conengprac.2024.105879
M3 - Article
AN - SCOPUS:85184837982
VL - 145
JO - Control engineering practice
JF - Control engineering practice
SN - 0967-0661
M1 - 105879
ER -