Real-time and Robust Collaborative Robot Motion Control with Microsoft Kinect ® v2

Burak Teke, Minna Lanz, Joni-Kristian Kämäräinen, Antti Hietanen

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    5 Citations (Scopus)
    79 Downloads (Pure)

    Abstract

    Recent development in depth sensing provide various opportunities for the development of new methods for Human Robot Interaction (HRI). Collaborative robots (co-bots) are redefining HRI across the manufacturing industry. However, little work has been done yet in the field of HRI with Kinect sensor in this industry. In this paper, we will present a HRI study using nearest-point approach with Microsoft Kinect v2 sensor's depth image (RGB-D). The approach is based on the Euclidean distance which has robust properties against different environments. The study aims to improve the motion performance of Universal Robot-5 (UR5) and interaction efficiency during the possible collaboration using the Robot Operating System (ROS) framework and its tools. After the depth data from the Kinect sensor has been processed, the nearest points differences are transmitted to the robot via ROS.

    Original languageEnglish
    Title of host publication2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2018
    PublisherIEEE
    Number of pages6
    ISBN (Print)9781538646434
    DOIs
    Publication statusPublished - 27 Aug 2018
    Publication typeA4 Article in a conference publication
    EventIEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications - Oulu, Finland
    Duration: 2 Jul 20184 Jul 2018

    Conference

    ConferenceIEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications
    CountryFinland
    CityOulu
    Period2/07/184/07/18

    Keywords

    • collaborative robots
    • human-robot collaboration
    • Human-robot interaction
    • Microsoft Kinect v2
    • ROS
    • trajectory planning

    Publication forum classification

    • Publication forum level 1

    ASJC Scopus subject areas

    • Control and Optimization
    • Computer Science Applications
    • Electrical and Electronic Engineering
    • Mechanical Engineering
    • Instrumentation

    Fingerprint Dive into the research topics of 'Real-time and Robust Collaborative Robot Motion Control with Microsoft Kinect ® v2'. Together they form a unique fingerprint.

    Cite this