Advertisement

Adaptation to environmental change using reinforcement learning for robotic salamander

  • Younggil Cho
  • Sajjad Manzoor
  • Youngjin ChoiEmail author
Original Research Paper
  • 1 Downloads

Abstract

In the paper, a reinforcement learning technique is applied to produce a central pattern generation-based rhythmic motion control of a robotic salamander while moving toward a fixed target. Since its action spaces are continuous and there are various uncertainties in an environment that the robot moves, it is difficult for the robot to apply a conventional reinforcement learning algorithm. In order to overcome this issue, a deep deterministic policy gradient among the deep reinforcement learning algorithms is adopted. The robotic salamander and the environments where it moves are realized using the Gazebo dynamic simulator under the robot operating system environment. The algorithm is applied to the robotic simulation for the continuous motions in two different environments, i.e., from a firm ground to a mud. Through the simulation results, it is verified that the robotic salamander can smoothly move toward a desired target by adapting to the environmental change from the firm ground to the mud. The gradual improvement in the stability of learning algorithm is also confirmed through the simulations.

Keywords

Reinforcement learning Adaptation to environmental change Central pattern generator (CPG) 

Notes

Supplementary material

Supplementary material 1 (mp4 9960 KB)

References

  1. 1.
    Zhou X, Bi S (2012) A survey of bio-inspired compliant legged robot designs. Bioinspir Biomim 7(4):041001CrossRefGoogle Scholar
  2. 2.
    Raj A, Thakur A (2016) Fish-inspired robots: design, sensing, actuation, and autonomy—a review of research. Bioinspir Biomim 11(3):031001CrossRefGoogle Scholar
  3. 3.
    Hirose S, Yamada H (2009) Snake-like robots [tutorial]. IEEE Robot Autom Mag 16(1):88–98CrossRefGoogle Scholar
  4. 4.
    Koh J-S, Cho K-J (2013) Omega-shaped inchworm-inspired crawling robot with large-index-and-pitch (LIP) SMA spring actuators. IEEE/ASME Trans Mechatron 18(2):419–429CrossRefGoogle Scholar
  5. 5.
    Paranjape AA, Chung S-J, Kim J (2013) Novel dihedral-based control of flapping-wing aircraft with application to perching. IEEE Trans Robot 29(5):1071–1084CrossRefGoogle Scholar
  6. 6.
    Chen Y et al (2015) Hybrid aerial and aquatic locomotion in an at-scale robotic insect. In: IEEE/RSJ international conference on intelligent robots and systems (IROS)Google Scholar
  7. 7.
    Marder E, Bucher D (2001) Central pattern generators and the control of rhythmic movements. Curr Biol 11(23):R986–R996CrossRefGoogle Scholar
  8. 8.
    Ijspeert AJ (2008) Central pattern generators for locomotion control in animals and robots: a review. Neural Netw 21(4):642–653CrossRefGoogle Scholar
  9. 9.
    Yu J et al (2014) A survey on CPG-inspired control models and system implementation. IEEE Trans Neural Netw Learn Syst 25(3):441–456CrossRefGoogle Scholar
  10. 10.
    Manzoor S, Choi Y (2016) A unified neural oscillator model for various rhythmic locomotions of snake-like robot. Neurocomputing 173(3):1112–1123CrossRefGoogle Scholar
  11. 11.
    Frolich LM, Biewener AA (1992) Kinematic and electromyographic analysis of the functional role of the body axis during terrestrial and aquatic locomotion in the salamander Ambystoma tigrinum. J Exp Biol 162(1):107–130Google Scholar
  12. 12.
    Ashley-Ross MA, Bechtel BF (2004) Kinematics of the transition between aquatic and terrestrial locomotion in the newt Taricha torosa. J Exp Biol 207(3):461–474CrossRefGoogle Scholar
  13. 13.
    Delvolve I, Bem T, Cabelguen J-M (1997) Epaxial and limb muscle activity during swimming and terrestrial stepping in the Adult Newt, Pleurodeles waltl. J Neurophysiol 78(2):638–650CrossRefGoogle Scholar
  14. 14.
    Ijspeert AJ et al (2007) From swimming to walking with a salamander robot driven by a spinal cord model. Science 315(5817):1416–1420CrossRefGoogle Scholar
  15. 15.
    Cohen AH (1988) Evolution of the vertebrate central pattern generator for locomotion. In: Cohen AH, Rossignol S, Grillner S (eds) Neural control of rhythmic movements in vertebrates. WileyGoogle Scholar
  16. 16.
    Gao K-Q, Shubin H (2001) Late Jurassic salamanders from northern China. Nature 410(6828):574CrossRefGoogle Scholar
  17. 17.
    Crespi A et al (2013) Salamandra robotica II: an amphibious robot to study salamander-like swimming and walking gaits. IEEE Tran Robot 29(2):308–320CrossRefGoogle Scholar
  18. 18.
    Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, CambridgezbMATHGoogle Scholar
  19. 19.
    Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3–4):279–292zbMATHGoogle Scholar
  20. 20.
    Lillicrap TP et al (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv: 1509.02971
  21. 21.
    Silver D et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484–489CrossRefGoogle Scholar
  22. 22.
    Mnih V et al (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602
  23. 23.
    Mnih V et al (2015) Human-level control through deep reinforcement learning. Nature. https://doi.org/10.1038/nature14236
  24. 24.
    Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
  25. 25.
    Koenig N, Howard A (2004) Design and use paradigms for gazebo, an open-source multi-robot simulator. In: Proceedings of 2004 IEEE/RSJ international conference on intelligent robots and systemsGoogle Scholar
  26. 26.
    Silver D et al. (2014) Deterministic policy gradient algorithms. In: Proceedings of the international conference on machine learningGoogle Scholar
  27. 27.
    Konda VR, Tsitsiklis JN (2000) Actor-critic algorithms. In: Conference on neural information processing systems (NIPS), pp 1008–1014Google Scholar
  28. 28.
    Hooper SL (2000) Central pattern generators. Curr Biol 10(5):R176–R179CrossRefGoogle Scholar
  29. 29.
    Bishop CM (2006) Pattern recognition and machine learning (information science and statistics). Springer, BerlinzbMATHGoogle Scholar
  30. 30.
    Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the international conference on machine learningGoogle Scholar
  31. 31.
    Choi Y, Chung WK (2004) PID trajectory tracking control for mechanical systems. Springer, BerlinCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Korea Institute of Science and Technology (KIST)SeoulSouth Korea
  2. 2.Faculty of EngineeringMirpur University of Science and Technology (MUST)MirpurPakistan
  3. 3.Department of Electrical and Electronic EngineeringHanyang UniversityAnsanSouth Korea

Personalised recommendations