Development of a Stereo Vision-based Pick and Place System for Robotic Manipulators
Author:
Affiliation:

Sri Lanka Institute of Information Technology, Sri Lanka

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Conventional robotic manipulators consist of touch and vision sensors in order to pick and place differently shaped objects. Due to the technology development and degrading sensors over a long period, the stereo vision technique has become a promising alternative. In this study, a low-cost stereo vision-based system, and a gripper to be placed at the end of the robot arm (Fanuc M10iA/12) are developed for position and orientation estimation of robotic manipulators to pick and place different shaped objects. The stereo vision system developed in this research is used to estimate the position (X, Y, Z), orientation (𝞡y) of the Center of Volume of four standard objects (cube, cuboid, cylinder, and sphere) whereas the robot arm with the gripper is used to mechanically pick and place the objects. The stereo vision system is placed on the movable robot arm, and it consists of two cameras to capture two 2D views of a stationary object to derive 3D depth information in 3D space. Moreover, a graphical user interface is developed to train a linear regression model, live predict the coordinates of the objects, and check the accuracy of the predicted data. The graphical user interface can also send predicted coordinates and angles to the gripper and the robot arm. The project is facilitated with python programming language modules and image processing techniques. Identification of the stationary object and estimation of its coor-dinates is done using image processing techniques. The final product can be identified as a device that converts con-ventional robot arms without an image processing vision system into a highly precise and accurate robot arm with an image processing vision system. Experimental studies are performed to test the efficiency and effectiveness of used techniques and the gripper prototype. Necessary actions are taken to minimize the errors in position and orientation estimation. In addition, as a future implementation, an embedded system will be developed with a user-friendly software interface to install the vision system into the Fanuc M10iA/12robot arm and will upgrade the system to a device that can be implemented with any kind of customized robot arms available in the industry.

    Reference
    Related
    Cited by
Get Citation

Thakshila THILAKANAYAKE, Nirasha HERATH, Migara LIYANAGE.[J]. Instrumentation,2021,8(2):1-13

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:
  • Revised:
  • Adopted:
  • Online: December 28,2021
  • Published:
License
  • Copyright (c) 2023 by the authors. This work is licensed under a Creative
  • Creative Commons Attribution-ShareAlike 4.0 International License.