International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Balancing a seesaw with reinforcement learning

  • Tengis, Ts. (Mongolian University of Science and Technology, School of Information and Communication Technology) ;
  • Uurtsaikh, L. (Mongolian University of Science and Technology, School of Information and Communication Technology) ;
  • Batminkh, A. (Mongolian University of Science and Technology, School of Information and Communication Technology)
  • Received : 2020.09.28
  • Accepted : 2020.10.26
  • Published : 2020.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A propeller-based seesaw system is a system that can represent one of axis of four propeller drones and its stabilization has been replaced by intelligent control system instead of often used control methods such as PID and state space. Today, robots are increasingly use machine learning methods to adapt to their environment and learn to perform the right actions. In this article, we propose a Q-learning-based approach to control the stability of a seesaw system with a propeller. From the experimental results that it is possible to fully learn the balance control of a seesaw system by correctly defining the state of the system, the actions to be performed, and the reward functions. Our proposed method solves the seesaw stabilization.

Keywords

References

  1. J Kober, JA Bagnell, J Peters, "Reinforcement learning in robotics: A survey", The International Journal of Robotics Research Journal, pp 1238-1274, 2013
  2. Shayegan Omidshafiei, "Reinforcement learning-based quadcopter control", 2013
  3. Amar Batmunkh, Tserendondog Tengis "State feedback control simulation of quadcopter model" IFOST 2016,
  4. Ц. Тэнгис, А.Батмөнх "Disturbance Rejection Control for Unbalanced Double-Propeller System on Single Axis" Хүрэлтогоот 2017,
  5. WD Smart, LP Kaelbling, "Effective reinforcement learning for mobile robots", Proceedings 2002 IEEE International Conference on Robotics and Automation
  6. WD Smart, LP Kaelbling, "Practical reinforcement learning in continuous spaces", PICML, 903-910, 2000
  7. A. D. Dubey1 , R. B. Mishra2 and A. K. Jha, "Path Planning Of Mobile Robot Using Reinforcement Based Artificial Neural Network" International Journal of Advances in Engineering & Technology, May 2013. ISSN: 2231-1963
  8. Jemin Hwangbo1 , Inkyu Sa2 , Roland Siegwart2 and Marco Hutter1, "Control of a Quadrotor with Reinforcement Learning", IEEE robotics and automation, june, 2017
  9. W Koch, R Mancuso, R West, A Bestavros, "Reinforcement Learning for UAV Attitude Control", ACM Transactions on Cyber-Physical Systems, 2019
  10. C Gaskett, L Fletcher, A Zelinsky, "Reinforcement learning for a vision based mobile robot", Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots
  11. A El Assad, E Fournier-Bidoz, P Lachevre, J Sagastuy, "Inverted Pendulum on a Quadcopter: A Reinforcement Learning Approach", CS229 - Final Report, 2017
  12. M Asada, S Noda, S Tawaratsumida, "Vision-based reinforcement learning for purposive behavior acquisition", Proceedings of 1995 IEEE International Conference on Robotics and Automation
  13. MG Lagoudakis, "Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm", Duke University, 1999
  14. F Amigoni, A Bonarini, G Fontana, M Matteucci, V Schiaffonati, "Batch reinforcement learning for controlling a mobile wheeled pendulum robot", IFIP International Conference on Artificial Intelligence in Theory and Practice, pp 156-160, 2008
  15. T Hester, M Quinlan, P Stone, "RTMBA: A real-time model-based reinforcement learning architecture for robot control", 2012 IEEE International Conference on Robotics and Automation, pp 85-90
  16. Mohammad Abdel Kareem Jaradat, Mohammad Al-Rousan, Lara Quadan, "Reinforcement based mobile robot navigation in dynamic environment", Robotics and Computer-Integrated Manufacturing, pp 135-149, 2011
  17. R Figueroa, A Faust, P Cruz, L Tapia, R Fierro, "Reinforcement learning for balancing a flying inverted pendulum", Proceeding of the 11th World Congress on Intelligent Control and Automation, pp 1787-1793, 2014