Robot Manipulator Programming Via Demonstrative-Kinesthetic Teaching for Efficient Industrial Material Handling Applications

Griffin Pilot Mabong; Emmanuel A. E. Osore; Peter T. Cherop

doi:10.51867/Asarev.Engineering.1.1.9

Authors

Griffin Pilot Mabong Department of Mechanical and Industrial Engineering, Masinde Muliro University of Science and Technology, Kenya Author
Emmanuel A. E. Osore Department of Mechanical and Industrial Engineering, Masinde Muliro University of Science and Technology, Kenya Author https://orcid.org/0000-0002-0943-0512
Peter T. Cherop Department of Mechanical and Industrial Engineering, Masinde Muliro University of Science and Technology, Kenya Author https://orcid.org/0000-0002-8991-1972

DOI:

https://doi.org/10.51867/Asarev.Engineering.1.1.9

Keywords:

Dobot Magician

Abstract

The Fourth Industrial Revolution (4IR) is on course for onboarding by the various manufacturing industries. The fluctuating nature of consumer needs has made it necessary to renovate existing industry approaches to industrial activities. This is an attempt to hold a competitive edge over conventional manufacturing activities. The development of cyber-physical systems (CPS), technological advancements, and the integration of computers in manufacturing processes have seen the introduction of robotized systems to aid in the processes. This has led to the start of smart factories, hence smart manufacturing. Today, robots are deployed in social places for entertainment, hospitals for telemedicine, industries for various activities, and fields of exploration. The robot programming techniques have significantly advanced from traditional text-based language programming (TLP) and offline programming (OLP) to various paradigms of programming by demonstration (PbD), such as tele-kinesthetic teaching (TKT) and demonstrative-kinesthetic teaching (DKT). This paper aimed to program a robotic manipulator using DKT and contrasted it against programming using structured text for industrial material handling applications. The study was validated via palletizing and contour path welding experiments. The materials for the experiments were a robotic manipulator (Dobot Magician), a laptop, USB cables, and stopwatches. A control platform for the arm was created using Microsoft Visual Studio code. The platform allowed arm manipulation, demonstratively using the hand-held trigger button on the forearm to capture motions. The palletizing and contour path weld experiments used the DKT and structured texts as programming modes. The results showed a shorter DKT reaction time than structured texts when conducting the palletizing experiment. The palletizing experimental time was lesser than when performed over the structured texts. The contour path welding indicated an equal reaction time for both programming modes but comparable experimental times. The efficiency of the DKT was taken on account of comparison of the reaction and experimental time to the structured texts, which served as the control experiment. The conclusion was that DKT was more efficient as a manipulator programming method than structured texts. Future works aimed at actual contour path welding and improvement of the control platform to a more user-friendly interface.

References

Bartoš, M., Bulej, V., Bohušík, M., et al. (2021) An overview of robot applications in automotive industry. Transportation Research Procedia. 55: p. 837-844. https://doi.org/10.1016/j.trpro.2021.07.052 DOI: https://doi.org/10.1016/j.trpro.2021.07.052

Jahnavi, K. and Sivraj, P.(2017) Teaching and learning robotic arm model. 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT).1570-1575. IEEE. https://doi.org/10.1109/ICICICT1.2017.8342804 DOI: https://doi.org/10.1109/ICICICT1.2017.8342804

Abdelaal, M.(2019) A study of robot control programing for an industrial robotic arm. 2019 6th International Conference on Advanced Control Circuits and Systems (ACCS) and 2019 5th International Conference on New Paradigms in Electronics and information Technology (PEIT).23-28. IEEE.

https://doi.org/10.1109/ACCS-PEIT48329.2019.9062878 DOI: https://doi.org/10.1109/ACCS-PEIT48329.2019.9062878

Kohrt, C., Stamp, R., Pipe, A., et al. (2013) An online robot trajectory planning and programming support system for industrial use. Robotics and Computer-Integrated Manufacturing. 29(1): p. 71-79

https://doi.org/10.1016/j.rcim.2012.07.010 DOI: https://doi.org/10.1016/j.rcim.2012.07.010

Kohrt, C., Pipe, A., Schiedermeier, G., et al.(2008) A robot manipulator communications and control framework. 2008 IEEE International Conference on Mechatronics and Automation.846-851. IEEE.

https://doi.org/10.1109/ICMA.2008.4798867 DOI: https://doi.org/10.1109/ICMA.2008.4798867

Amar, R.H.E., Benchikh, L., Dermeche, H., et al. (2020) Efficient trajectory reconstruction for robot programming by demonstration. Rev. Roum. Sci. Techn.-Électrotechn. et Énerg. 65: p. 1-2

Zhou, Z., Xiong, R., Wang, Y., and Zhang, J. (2020) Advanced robot programming: A review. Current Robotics Reports. 1: p. 251-258. https://doi.org/10.1007/s43154-020-00023-4 DOI: https://doi.org/10.1007/s43154-020-00023-4

Mosavi, A. and Varkonyi, A. (2017) Learning in robotics. International Journal of Computer Applications. 157(1): p. 8-11. https://doi.org/10.5120/ijca2017911661 DOI: https://doi.org/10.5120/ijca2017911661

Orendt, E.M., Fichtner, M., and Henrich, D.(2016) Robot programming by non-experts: Intuitiveness and robustness of one-shot robot programming. 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).192-199. IEEE. https://doi.org/10.1109/ROMAN.2016.7745110 DOI: https://doi.org/10.1109/ROMAN.2016.7745110

Zieliński, C.(1995) Robot programming methods. Oficyna Wydawnicza Politechniki Warszawskiej.

Villani, V., Pini, F., Leali, F., et al. (2018) Survey on human-robot interaction for robot programming in industrial applications. Ifac-PapersOnline. 51(11): p. 66-71. https://doi.org/10.1016/j.ifacol.2018.08.236 DOI: https://doi.org/10.1016/j.ifacol.2018.08.236

Calinon, S. (2018) Learning from demonstration (programming by demonstration). Encyclopedia of robotics: p. 1-8. https://doi.org/10.1007/978-3-642-41610-1_27-1 DOI: https://doi.org/10.1007/978-3-642-41610-1_27-1

Ravichandar, H., Polydoros, A.S., Chernova, S., and Billard, A. (2020) Recent advances in robot learning from demonstration. Annual review of control, robotics, and autonomous systems. 3: p. 297-330. https://doi.org/10.1146/annurev-control-100819-063206 DOI: https://doi.org/10.1146/annurev-control-100819-063206

Tykal, M., Montebelli, A., and Kyrki, V.(2016) Incrementally assisted kinesthetic teaching for programming by demonstration. 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).205-212. IEEE. https://doi.org/10.1109/HRI.2016.7451753 DOI: https://doi.org/10.1109/HRI.2016.7451753

Eiband, T., Liebl, J., Willibald, C., and Lee, D. (2023) Online task segmentation by merging symbolic and data-driven skill recognition during kinesthetic teaching. Robotics and Autonomous Systems. 162: p. 104367. https://doi.org/10.1016/j.robot.2023.104367 DOI: https://doi.org/10.1016/j.robot.2023.104367

Heimann, O. and Guhl, J.(2020) Industrial robot programming methods: A scoping review. 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA).696-703. IEEE. https://doi.org/10.1109/ETFA46521.2020.9211997 DOI: https://doi.org/10.1109/ETFA46521.2020.9211997

Landi, C.T., Ferraguti, F., Sabattini, L., et al.(2017) Admittance control parameter adaptation for physical human-robot interaction. 2017 IEEE international conference on robotics and automation (ICRA).2911-2916. IEEE. https://doi.org/10.1109/ICRA.2017.7989338 DOI: https://doi.org/10.1109/ICRA.2017.7989338

Neto, P., Pires, J.N., and Moreira, A.P.(2009) Accelerometer-based control of an industrial robotic arm. RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication.1192-1197. https://doi.org/10.1109/ROMAN.2009.5326285 DOI: https://doi.org/10.1109/ROMAN.2009.5326285

Tanwani, A.K. and Calinon, S. (2016) Learning robot manipulation tasks with task-parameterized semitied hidden semi-Markov model. IEEE Robotics and Automation Letters. 1(1): p. 235-242. https://doi.org/10.1109/LRA.2016.2517825 DOI: https://doi.org/10.1109/LRA.2016.2517825

Hersch, M., Guenter, F., Calinon, S., and Billard, A. (2008) Dynamical system modulation for robot learning via kinesthetic demonstrations. IEEE Transactions on Robotics. 24(6): p. 1463-1467. https://doi.org/10.1109/TRO.2008.2006703 DOI: https://doi.org/10.1109/TRO.2008.2006703

Zhu, Z., Hu, H., and Gu, D.(2018) Robot performing peg-in-hole operations by learning from human demonstration. 2018 10th Computer Science and Electronic Engineering (CEEC).30-35. IEEE. https://doi.org/10.1109/CEEC.2018.8674203 DOI: https://doi.org/10.1109/CEEC.2018.8674203

Valdivia, A.A., Habibian, S., Mendenhall, C.A., et al. (2023) Wrapping Haptic Displays Around Robot Arms to Communicate Learning. IEEE Transactions on Haptics. 16(1): p. 57-72. https://doi.org/10.1109/TOH.2023.3240400 DOI: https://doi.org/10.1109/TOH.2023.3240400

Shenzhen Yuejiang Technology Co., L. Dobot Magician User Manual Available from: https://www.dobot-robots.com/service/download-center[cited 2023 18-07]