Design and Analysis Techniques in Iterative Learning Control

Submission Deadline:  31 July 2019

IEEE Access invites manuscript submissions in the area of Design and Analysis Techniques in Iterative Learning Control.

Recently, great progress has been witnessed in both theory developments and practical applications of iterative learning control (ILC). ILC has been widely used in industry, for example, in chemical processes, robotic manipulators, hard disk drives, milling and laser cutting, traffic flow control systems, and rehabilitation robotic systems. With its rapid development, ILC has also encountered many theoretical and practical challenges including new system applications such as fractional-order systems, new operation environments such as networked structure and complex networks, and new technical innovations such as convergence analysis methods. Therefore, ILC is at a significant stage for making fundamental breakthroughs, which motivates this Special Section in IEEE Access.

Since the proposal of its original concept by Arimoto, et al., in 1984, ILC has developed rapidly over the last three decades. A survey by Bristow, Tharayil, and Alleyne, in IEEE Control Systems provided a comprehensive review of the fundamental framework of ILC and common design and analysis techniques. A comprehensive review was presented in another survey published by Ahn, Chen, and Moore, in IEEE Transactions on Systems, Man, and Cybernetics, Part C, which covered the field from 1998 to 2004. Later surveys reported on other directions of ILC. From these surveys and the references therein, it is observed that the exploration of ILC in various directions has been a mainstream in the past few decades. These explorations have greatly enriched the system of ILC and established the advantages of ILC compared with other traditional control methodologies. However, we are facing a bottleneck in developing ILC due to the lack of current growth.

Scholars in the community have reached a consensus that ILC requires an in-depth review of the past contributions as well as an exciting look at the future directions for ILC. It is necessary to collect fresh ideas from the community to contribute to an understanding of the future developments of ILC. In other words, while exploring ILC for more system and operation conditions, we should also explore the essential advantages of ILC so that we can establish a comprehensive system of ILC. In particular, three major directions should be explored. First, we can apply ILC to new systems, especially newly formed system formulation. This extension can help broaden the potential application range and promote associated research. Second, we should pay attention to new operation environments, especially the emerging conditions. For example, Cyber Physical Systems (CPS) has gained attention from the community; how to implement ILC in CPS is interesting, but security issues should also be considered. Third, we must propose new design and analysis techniques, to carry forward the merits of ILC.

This Special Section in IEEE Access invites original articles addressing both design and analysis techniques in the area of learning control, including novel applications, design frameworks, analysis tools, essential performance improvements, and other related topics in learning control. It aims to provide an in-depth review of the recent advances and a comprehensive outlook of the development trends in learning control.

The topics of interest include, but are not limited to:

  • Learning control for new types of systems
  • Nonlinear design framework of learning control
  • Novel convergence and performance analysis techniques
  • Learning control with new operation conditions
  • New applications
  • Integration with artificial intelligence
  • Big data driven learning control

We also highly recommend the submission of multimedia with each article as it significantly increases the visibility, downloads, and citations of articles.


Associate Editor:  Youqing Wang, Shandong University of Science and Technology, China

Guest Editors:

  1. Dong Shen, Beijing University of Chemical Technology, China
  2. Wojciech Paszke, University of Zielona Gora, Poland
  3. YangQuan Chen, University of California, Merced, USA


Relevant IEEE Access Special Sections:

  1. Cyber-Physical Systems
  2. Trends, Perspectives and Prospects of Machine Learning Applied to Biomedical Systems in Internet of Medical Things
  3. Big Data Learning and Discovery

IEEE Access Editor-in-Chief:
  Prof. Derek Abbott, University of Adelaide

Paper submission: Contact Associate Editor and submit manuscript to:

For inquiries regarding this Special Section, please contact: