University of Sussex
Browse
TASE_sILC_Vision.pdf (16.04 MB)

Spatial iterative learning control with human guidance and visual detection for path learning and tracking

Download (16.04 MB)
journal contribution
posted on 2023-06-10, 04:03 authored by Xia Jingkang, Yanan LiYanan Li, Deqing Huang, Jinlong Yang, Yueyan Xing, Lei Ma
A popular path learning method is to use off-line programming by demonstration (PbD) to plan a rough path, but it is subjected to uncertainties in the environment so needs to be updated during the task execution. For this purpose, a spatial iterative learning control (sILC) is developed to learn an accurate path through intuitive online correction based on human-robot interaction (HRI). To improve the efficiency and accuracy of the path learning, a visual assistance system is added to HRI, which helps the robot to find the initial path point and complement the correction of the learning error. This method mitigates the requirement on classic ILC that the time period should be consistent in the repetitive interaction task and utilizes the complementary advantages of vision and force sensing, thus addressing the limitations of the vision-based or HRI methods. The rigorous proof of learning convergence and the results of the simulation and experiments on a 7-degree-of-freedom (DoF) Sawyer robot platform illustrate the significance and advantages of the proposed method.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

IEEE Transactions on Automation Science and Engineering

ISSN

1042-296X

Publisher

Institute of Electrical and Electronics Engineers

Page range

1-13

Department affiliated with

  • Engineering and Design Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2022-06-23

First Open Access (FOA) Date

2022-06-23

First Compliant Deposit (FCD) Date

2022-06-22

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC