Initialization of ILC based on a previously learned trajectory

Janssens, Pieter; Pipeleers, Goele; Swevers, Jan

doi:10.1109/acc.2012.6315432

Cited by 17 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cogging, which is independent of motion velocity, is more or less a periodic function of the position and the period corresponds to the distance between the magnetic poles of the linear motor. [19] discusses the identification of the disturbance d of this linear motor setup, the result of which is shown in Fig. 2.…”

Section: Numerical Validationmentioning

confidence: 99%

Offset-free energy-optimal model predictive control for point-to-point motions with high positioning accuracy

Wang

Swevers

2015

2015 IEEE International Conference on Mechatronics (ICM)

View full text Add to dashboard Cite

This paper discusses Offset-free Energy-optimal Model Predictive Control (offset-free EOMPC) which is a MPC algorithm to realize time-constrained energy-optimal point-topoint motion control with high positioning accuracy for linear time-invariant (LTI) systems. The offset-free EOMPC approach is developed based on our previous research -Energy-optimal Model Predictive Control (EOMPC) -which aims at performing energy-optimal point-to-point motions within a given motion time. A drawback of the EOMPC method is that it cannot achieve high positioning accuracy in the presence of unmodelled disturbances or model-plant mismatch. In order to cope with this problem, a 'disturbance model' strategy is adopted: the system state is augmented with disturbance variables. Based on the 'disturbance model', the disturbances are estimated and the effect of which is cancelled. Numerical validation of the offsetfree EOMPC using a model of a linear motor with coulomb friction and cogging disturbances has been performed and the results show that time-constrained energy-optimal pointto-point motion with high positioning accuracy is achieved.

show abstract

Section: Numerical Validationmentioning

confidence: 99%

Offset-free energy-optimal model predictive control for point-to-point motions with high positioning accuracy

Wang

Swevers

2015

2015 IEEE International Conference on Mechatronics (ICM)

View full text Add to dashboard Cite

show abstract

“…that usually exist in the training phase, particularly for the cases where the target robotic platform is more expensive or more hazardous to operate than the source robotic platform. The use of transfer learning in robotics can be classified into (i) multi-task transfer learning, in which the data gathered by a robot when learning a particular task is utilized to speed up the learning of the same robot in other similar tasks [2], [5], [7], [10]- [12], and (ii) multirobot transfer learning, where the data gathered by a robot is used by other similar robots [7]- [9], [13]- [17]. The latter is the main focus of this paper.…”

Section: Introductionmentioning

confidence: 99%

Multi-robot transfer learning: A dynamical system perspective

Helwa

Schoellig

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Multi-robot transfer learning allows a robot to use data generated by a second, similar robot to improve its own behavior. The potential advantages are reducing the time of training and the unavoidable risks that exist during the training phase. Transfer learning algorithms aim to find an optimal transfer map between different robots. In this paper, we investigate, through a theoretical study of single-input singleoutput (SISO) systems, the properties of such optimal transfer maps. We first show that the optimal transfer learning map is, in general, a dynamic system. The main contribution of the paper is to provide an algorithm for determining the properties of this optimal dynamic map including its order and regressors (i.e., the variables it depends on). The proposed algorithm does not require detailed knowledge of the robots' dynamics, but relies on basic system properties easily obtainable through simple experimental tests. We validate the proposed algorithm experimentally through an example of transfer learning between two different quadrotor platforms. Experimental results show that an optimal dynamic map, with correct properties obtained from our proposed algorithm, achieves 60-70% reduction of transfer learning error compared to the cases when the data is directly transferred or transferred using an optimal static map.

show abstract

“…In [31] an initial input selection for ILC is proposed. This method can be used to re-initialize the ILC after a reference change, see the related results in [32]. The re-initialization mapping is static and model-based, hence modeling errors directly affect the extrapolation capabilities.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Flatbed Printer Accuracy and Throughput: Optimal Rational Feedforward Controller Tuning Via Iterative Learning Control

Bolder

Zundert

Koekebakker³

et al. 2017

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

show abstract

Initialization of ILC based on a previously learned trajectory

Cited by 17 publications

References 9 publications

Offset-free energy-optimal model predictive control for point-to-point motions with high positioning accuracy

Offset-free energy-optimal model predictive control for point-to-point motions with high positioning accuracy

Multi-robot transfer learning: A dynamical system perspective

Enhancing Flatbed Printer Accuracy and Throughput: Optimal Rational Feedforward Controller Tuning Via Iterative Learning Control

Contact Info

Product

Resources

About