conference paper · TU/e Research Portal · 2020
On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control
Poot, M.M., Jim Portegies, Tom Oomen, Raffaella Carloni, Bayu Jayawardhana, Erjen Lefeber
Cited by 6Open access
Abstract
Learning from data of past tasks can substantially improve the accuracy of mechatronic systems. Often, for fast and safe learning a model of the system is required. The aim of this paper is to develop a model-free approach for fast and safe learning for mechatronic systems. The developed actor-critic iterative learning control (ACILC) framework uses a feedforward parameterization with basis functions. These basis functions encode implicit model knowledge and the actor-critic algorithm learns the feedforward parameters without explicitly using a model. Experimental results on a printer setup demonstrate that the developed ACILC framework is capable of achieving the same feedforward signal as preexisting model-based methods without using explicit model knowledge.
Cite this paper
Poot, M., Portegies, J., Oomen, T., Carloni, R., Jayawardhana, B., & Lefeber, E. (2020). On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control. TU/e Research Portal.
Poot, M.M., et al. “On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control.” TU/e Research Portal, 2020.
Poot, M.M., Jim Portegies, Tom Oomen, Raffaella Carloni, Bayu Jayawardhana, and Erjen Lefeber. 2020. “On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control.” TU/e Research Portal.
Poot, M. et al. (2020) ‘On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control’, TU/e Research Portal.
@article{poot2020role,
title = {{On the Role of Models in Learning Control: Actor-Critic Iterative Learning Control}},
author = {Poot, M.M. and Portegies, Jim and Oomen, Tom and Carloni, Raffaella and Jayawardhana, Bayu and Lefeber, Erjen},
journal = {TU/e Research Portal},
year = {2020}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.
Related papers
Model-free iterative learning control for LTI systems
Pieter Janssens, Goele Pipeleers, Jan Swevers · 2011
Cited by 0
Model-free iterative learning control for LTI systems and experimental validation on a linear motor test setup
Pieter Janssens, Goele Pipeleers, Jan Swevers · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · 2011
Cited by 22Open access
Learning in Machines
Tom Oomen · Mikroniek · 2018
Cited by 8Open access
Model-free iterative learning control for LTI systems with actuator constraints
Pieter Janssens, Goele Pipeleers, Jan Swevers · IFAC Proceedings Volumes · 2011
Cited by 4Open access
Learning Control Without Prior Models: Multi-Variable Model-Free IIC, with application to a Wide-Format Printer
Robin de Rozario, Tom Oomen · IFAC-PapersOnLine · 2019
Cited by 5Open access
Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control Framework
Ugo Rosolia, Francesco Borrelli · IEEE Transactions on Automatic Control · 2017
Cited by 365Open access
Model-Free Adaptive Iterative Learning Control for Nonlinear Systems Using Partial Model Knowledge
Wei Yu, Zhongkui Li · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · 2026
Cited by 0Open access