english only
EPFL > STI > IMT > LASA > People > erden
LASA MENU
Home
Research
Publications
Teaching
People
Arriving to LASA
Videos / Photos
Press & News

GitHub Repository
Older Source Codes
The Blog
Intranet

Prospective Students

Member erden

Mustafa Suphi Erden (alumnus)

Postdoctoral fellow


Fields of Interest

  • Fields of Research Experience

    Human-robot interaction
    Physical human-robot interaction
    Assistive robotics
    Skill assitance for manufacturing
    Medical robotics
    Mechanical design
    Mechanisms for confocal microlaparoscopy
    Walking robots
    Reinforcement learning for walking
    Function modeling of complex mechatronics systems


Projects

  • Granted Fellowship:


    "Skill Assistance with Robot for Manual Welding"

    (clisk for the progect website)

    Marie Curie Intra European Fellowship: FP7-PEOPLE-2011-IEF


    Motivation

    This project targets the acquisition of manipulative skills required to perform complex tasks that are typical of manual welding in the industry. It aims at developing two robotic systems, one for training and one for assisting unskilled humans.

    We have only a partial understanding of “what” and “how” about skills acquired by humans. Similarly, in recent years, the questions of “what” and “how” to acquire skills have become key issues in robot learning by demonstration. This proposal aims at shedding light on these two questions in the particular framework of manual welding.

    Automated welding robots are widely used in industry. However, automation is not always possible due to the complexity and variety of welding tasks. Many industries still rely on manual welding. This project aims to link the human assistive robotics research with the industrial manufacturing, particularly with manual welding.

    Goal

    The goal of this project is to develop a quantifiable measurement of skill level in terms of arm-impedance parameters and to use this knowledge for developing a training and an assistance robotic system for welding. This project will measure and make comparative analysis of the impedance parameters of skilled and unskilled welders.

    1) Position and force data will be collected from skilled and unskilled welders both for nominal welding performance and for impedance measurements (with disturbance).

    2) Kinematic data (position/velocity/frequency content) will be analyzed to identify unskilled type movements.

    3) Arm-impedance profiles of the skilled and unskilled welders will be constructed and analysed.

    4) A training system will be developed. The training system will detect unskilled movements in real-time and provide notice-feedback to the welder instantaneously.

    5) A real-time welding assistant will be developed. The impedance of the robot will be controlled in order to modify the overall human-robot impedance in the direction of a skilled pattern




    Selected Results of My Background Research for this Project

    Analysis of Kinematic Data of Manual Welding

    graph_collecting_data(a) graph_skilled_unskilled_kinematics_data(b)

    Figure 1: (a) Data colllection of manual welding with motion capture system. (b) The position variation of the torch-tip in the direction of welding line (x) after passing through a high-pass filter with a cutoff frequency of 0.1Hz. Pink (light): unskilled performance data; blue (dark): skilled performance data. The two black lines represent the positive and negative thresholds of x-variation. These thresholds are used to distinguish between skilled and unskilled type movements

    Applying a high-pass filter with a cutoff frequency at 0.1Hz on the position signal of the torch allowed classifying across skilled and unskilled performances (see Figure above). The threshold-based classification was not influenced by other kinematic variables, such as the curvature of the welding path or the average speed of welding.

    Reference
    Erden, M.S. and Tomiyama, T., (2008), “Identifying welding skills for training and assistance with a robot”. Science and Technology of Welding and Joining, 14(6): 523-532.


    Assisting Manual Welding with Damping

    welding_haptic_master_photo (a) painting_haptic_master_photo (b)

    Figure 2: The HapticMaster used (a) for emulation of welding with air-brush-painting, (b) for actual welding with a TIG welding torch.

    Manual welding is assisted with a haptic robot by applying damping at the end effector. This damping suppressed the high frequency vibrations of the human arm. Variable impedance was applied by observing the manipulation speed, in order to provide easy replacement of the welding torch in the phases that no welding was performed.

    Reference Erden, M.S. and Maric, B., 2011. “Assisting manual welding with robot”. Robotics and Computer Integrated Manufacturing, 27: 818-828.


  • Activities



    • Co-Organizing Workshop at IROS 2013

      Cognitive Robotics Systems: Replicating Human Actions and Activities (CRS 2013), at IROS 2013, Tokyo, Japan, November 3

      LASA is co-organizing the CRS 2013 Workshop at IROS 2013, Tokyo, Japan, in collaboration with University of Bristol-UK, German Research Center for Artificial Intelligence (DFKI)-Germany, Willow Garage-USA, University of Liege-Belgium, and Aalborg University Copenhagen-Denmark.
      http://www.crs2013.org/

      Organizers

      Gabriele Bleser, German Research Center for Artificial Intelligence (DFKI), Germany
      Maya Cakmak, Willow Garage, USA
      Dima Damen, University of Bristol, UK
      Renaud Detry, University of Liege, Belgium
      Lazaros Nalpantidis, Aalborg University Copenhagen, Denmark
      Mustafa Suphi Erden, Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland




Publications



    Journals

  • Erden, M.S. and Billard, A. (2015) Robotic training for hand movements during manual welding with real-time alarm feedback. Industrial Robot: An International Journal, Vol. 42 Iss: 6, pp.554 - 564. [show abstract]
  • Erden, M.S. and Billard, A. (2015) Hand Impedance Measurements During Interactive Manual Welding With a Robot. in IEEE Transactions on Robotics, vol.31, no.1, pp.168-179, Feb. 2015. [show abstract]
  • Erden, M.S. and Billard, A. (2015) End-Point Impedance Measurements Across Dominant and Nondominant Hands and Robotic Assistance with Directional Damping. in IEEE Transactions on Cybernetics, vol. 45, num. 6, p. 1146 - 1157, 2015.. [show abstract]
  • Erden, M.S. and Billard, A. (2014) End-Point Impedance Measurements Across Dominant and Nondominant Hands and Robotic Assistance with Directional Damping. IEEE Transactions on Cybernetics. In press. [pdf]
  • Erden, M.S., Rosa, B., Szewczyk, J. and Morel, G. (2012) Understanding Soft Tissue Behavior for Application to Microlaparoscopic Surface Scan. IEEE Transactions on Biomedical Engineering. Accepted for publication.
  • Rosa, B., Erden, M.S., Vercauteren, T., Herman, B., Szewczyk, J. and Morel, G. (2012) Building large mosaics of confocal endomicroscopic images using visual servoing. IEEE Transactions on Biomedical Engineering. Accepted for publication.
  • Erden, M.S. and Jonkman, J.A. (2012) Physical human-robot interaction by observing actuator currents. International Journal of Robotics and Automation, 27 (3): 233-243.
  • Erden, M.S. and Maric, B. (2011) Assisting manual welding with robot. Robotics and Computer Integrated Manufacturing, 27: 818–828.
  • Erden, M.S. (2011) Optimal protraction of a biologically inspired robot leg. Journal of Intelligent and Robotic Systems, 64: 301-322.
  • Cabrera, A.A.A., Foeken, M.J., Tekin, O.A., Woestenenk, K., Erden, M.S., De Schutter, B., Van Tooren, M.J.L. and et al. (2010) Towards automation of control software: a review of challenges in mechatronicdesign. Mechatronics, 20 (8): 876-886.
  • van Beek, T., Erden, M.S. and Tomiyama, T. (2010) Modular Design of Mechatronic Systems with Function Modeling. Mechatronics, 20 (8): 850-863.
  • Erden, M.S. and Tomiyama, T. (2010) Human intent detection and physically-interactive control of a robot without force sensors. IEEE Transactions on Robotics, 26(2): 370-382.
  • Erden, M.S. and Tomiyama, T. (2009) Identifying welding skills for training and assistance with robot. Science and Technology of Welding and Joining, 14 (6): 523-532.
  • Erden, M.S., Komoto, H., van Beek, T.J., DAmelio, V., Echavarria, E. and Tomiyama, T. (2008) A review of function modeling: Approaches and applications. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 22: 147–169.
  • Erden, M.S. and Leblebicioğlu, K. (2008) Free gait generation with reinforcement learning for a six-legged robot. Robotics and Autonomous Systems, 56: 199-212.
  • Erden, M.S. and Leblebicioğlu, K. (2007) Torque distribution in a six-legged robot. IEEE Transactions on Robotics, 23 (1): 179-186.
  • Erden, M.S. and Leblebicioğlu, K. (2007) Analysis of wave gaits for energy efficiency. Autonomous Robots, 23 (3): 213-230.
  • Erden, M.S. (2004) The exchange of Greek and Turkish populations in the 1920s and its socio-economic impacts on life in Anatolia. Crime, Law & Social Change, 41: 261–282.
  • Erden, M.S., Leblebicioğlu, K. and Halıcı, U. (2004) Multi-agent system based fuzzy controller design with genetic tuning for a service mobile manipulator robot in the hand-over task. Journal of Intelligent and Robotic Systems, 38: 287-306.


  • Conference Proceedings

  • Erden, M.S. and Billard, A. (2014) End-point Impedance Measurements at Human Hand during Interactive Manual Welding with Robot. In Proceedings of 2014 IEEE International Conference on Robotics & Automation (ICRA). [ICRA2014] [pdf]




Last update: 11/03/08