To read the full version of this content please select one of the options below:

Visual trajectory tracking of industrial manipulator with iterative learning control

Bingxi Jia (Department of Control Science and Engineering, Zhejiang University, Hangzhou, China)
Shan Liu (Department of Control Science and Engineering, Zhejiang University, Hangzhou, China)
Yi Liu (Department of Control Science and Engineering, Zhejiang University, Hangzhou, China)

Industrial Robot

ISSN: 0143-991x

Article publication date: 19 January 2015

Abstract

Purpose

The purpose of this paper is to propose a more efficient strategy, which is easier to implement, i.e. the engineer can directly operate the target object without the robot to do a demonstration, and the manipulator is regulated to track the trajectory using vision feedback repetitively. Generally, the applications of industrial robotic manipulators are based on teaching playback strategy, i.e. the engineer should directly operate the manipulator to perform a demonstration and then the manipulator uses the recorded driving signals to perform repetitive tasks.

Design/methodology/approach

In the teaching process, the engineer grasps the object with a camera on it to do a demonstration, during which a series of images are recorded. The desired trajectory is defined by the homography between the images captured at current and final poses. Tracking error is directly defined by the homography matrix, without 3D reconstruction. Model-free feedback-assisted iterative learning control strategy is used for repetitive tracking, where feed-forward control signal is generated by iterative learning control strategy and feedback control signal is generated by direct feedback control.

Findings

The proposed framework is able to perform precise trajectory tracking by iterative learning, and is model-free so that the singularity problem is avoided which often occurs in conventional Jacobean-based visual servo systems. Besides, the framework is robust to image noise, which is shown in simulations and experiments.

Originality/value

The proposed framework is model-free, so that it is more flexible for industrial use and easier to implement. Satisfactory tracking performance can be achieved in the presence of image noise. System convergence is analyzed and experiments are provided for evaluation.

Keywords

Citation

Jia, B., Liu, S. and Liu, Y. (2015), "Visual trajectory tracking of industrial manipulator with iterative learning control", Industrial Robot, Vol. 42 No. 1, pp. 54-63. https://doi.org/10.1108/IR-09-2014-0392

Publisher

:

Emerald Group Publishing Limited

Copyright © 2015, Emerald Group Publishing Limited