Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Evolutionary Optimization of Neurocontroller for Physically Simulated Compliant-Wing Ornithopter

  • Shim, Yoonsik (Institute of Computer, Information and Communication, Korea University)
  • Received : 2019.12.02
  • Accepted : 2019.12.26
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a novel evolutionary framework for optimizing a bio-inspired fully dynamic neurocontroller for the maneuverable flapping flight of a simulated bird-sized ornithopter robot which takes advantage of the morphological computation and mechansensory feedback to improve flight stability. In order to cope with the difficulty of generating robust flapping flight and its maneuver, the wing of robot is modelled as a series of sub-plates joined by passive torsional springs, which implements the simplified version of feathers attached to the forearm skeleton. The neural controller is designed to have a bilaterally symmetric structure which consists of two fully connected neural network modules receiving mirrored sensory inputs from a series of flight navigation sensors as well as feather mechanosensors to let them participate in pattern generation. The synergy of wing compliance and its sensory reflexes gives a possibility that the robot can feel and exploit aerodynamic forces on its wings to potentially contribute to the agility and stability during flight. The evolved robot exhibited target-following flight maneuver using asymmetric wing movements as well as its tail, showing robustness to external aerodynamic disturbances.

본 논문은 목표한 방향으로 자유롭게 기동할 수 있는 새 크기의 물리기반 날갯짓 비행로봇 시뮬레이션을 위한 동역학적 신경망 컨트롤러를 생성하는 통합적인 진화연산 방법을 제시한다. 제안된 진화로봇 시스템은 날갯짓 비행의 추가적인 민첩성과 안정성을 위하여 Morphological Computation 개념을 응용한 간단한 날개 순응성 모델과 그와 통합된 Mechanosensory 정보를 활용한다. 역학적으로 불안정한 날갯짓 기동의 안정성 개선을 위해 로봇의 날개는 회전스프링으로 팔의 골격에 연결된 여러개의 패널들로 모델링되어, 새의 깃털에서 영감을 받은 단순한 형태의 날개 유연성을 시뮬레이션 하도록 설계되었다. 신경망 컨트롤러 역시 생물학적으로 의미있는 좌우대칭적 연결구조를 가짐과 동시에 최대의 진화연산 탐색 가능성을 위해 두 개의 fully-connected 신경망 모듈로 이루어지며, 이를 위한 센서정보로서 항법센서와 더불어 각 날개패널의 움직임 보들이 입력되어진다. 이러한 설계는 각 패널센서로 하여금 잠재적으로 신경망의 날갯짓 패턴 생성에 관여하게 함과 동시에, 날개에 가해지는 힘의 감지와 패널의 굽어짐으로 인한 날개 순응성으로부터 얻을 수 있는 비행의 민첩성과 안정성 향상을 동시에 유도할 수 있다. 본 시스템으로 진화된 날갯짓 로봇은 실시간으로 주어지는 목표방향으로의 효과적인 기동과 함께, 외부의 공기역학적 섭동에 대하여도 더욱 안정적인 비행을 유지함을 보여준다.

Keywords

References

  1. D.D. Chin, and D. Lentink, "Flapping Wing Aerodynamics: From Insects to Vertebrates," Journal of Experimental Biology, Vol. 219, pp. 999-999, 2016.
  2. C. Chen, and T. Zhang, "A Review of Design and Fabrication of the Bionic Flapping Wing Micro Air Vehicles," Micromachines, Vol. 10, No. 144, pp. 1-20, 2019.
  3. J. Gerdes, H.A. Bruck, S.K. Gupta, "A Simulation-based Approach to Modeling Component Interactions during Design of Flapping Wing Aerial Vehicles," International Journal of Micro Air Vehicles, Vol. 11, 2019.
  4. J. Wu, and Z. Popovi\'{c}, "Realistic Modeling of Bird Flight Animations," ACM Transactions on Graphics, Vol. 22, No. 3, pp. 888-895, 2003. https://doi.org/10.1145/882262.882360
  5. Y.S. Shim, and C.H. Kim, "Evolving Physically Simulated Flying Creatures for Efficient Cruising," Artificial Life, Vol. 12, No. 4, pp. 561-591, 2006. https://doi.org/10.1162/artl.2006.12.4.561
  6. Y.S. Shim, S.J. Kim, C.H. Kim, "Evolving Flying Creatures with Path-following Behavior," The 9th International Conference on the Simulation and Synthesis of Living Systems (ALIFE IX), Boston, MA, pp. 125-132, 2004.
  7. J. Won, J. Park, K. Kim, J. Lee, "How to Train Your Dragon: Example-Guided Control of Flapping Flight," ACM Transactions on Graphics, Vol. 36, No. 4, 2017.
  8. J. Won, J. Park, J. Lee, "Aerobatics Control of Flying Creatures via Self-Regulated Learning," ACM Transactions on Graphics, Vol. 37, No. 6, 2018.
  9. F.P. Such, V. Madhavan, E. Conti, J. Lehman, K.O. Stanley, J. Clune, "Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning," NIPS Deep Reinforcement Learning Workshop, 2018.
  10. K.O. Stanley, J. Clune, J. Lehman, R. Miikkulainen, "Designing Neural Networks through Neuroevolution," Nature Machine Intelligence, Vol. 1, No. 1, pp. 24-35, 2019. https://doi.org/10.1038/s42256-018-0006-z
  11. J.B. Mouret, S. Doncieux, J.A. Meyer, "Incremental Evolution of Target-following Neuro-controllers for Flapping-wing Animats," SAB 06, LNCS (LNAI), Vol. 4095, pp. 606-618, 2006.
  12. E. de Margerie, J.B. Mouret, S. Doncieux, J.A. Meyer, "Artificial evolution of the morphology and kinematics in a flapping-wing mini UAV," Bioinspiration & Biomimetics, Vol. 2, pp. 65-82, 2007. https://doi.org/10.1088/1748-3182/2/4/002
  13. D.R. Warrick, M.W. Bundle, K.P. Dial, "Bird Maneuvering Flight: Blurred Bodies, Clear Heads," Integrative and Comparative Biology, Vol. 41, No. 1, pp. 141-148, 2002.
  14. R. Pfeifer, and F. Iida, "Morphological Computation: Connecting Body, Brain and Environment," Japanese Scientific Monthly, Vol. 58, pp. 48-54, 2005.
  15. E.H. Burtt Jr., and J.M. Ichida, "Selection for Feather Structure," Acta Zoologica Sinica, Vol. 52, pp. 131-135, 2006.
  16. M. Gewecke, and M. Woike, "Breast Feathers as an Air‐current Sense Organ for the Control of Flight Behaviour in a Songbird (Carduelis Spinus)," Zeitschrift fur Tierpsychologie, Vol. 47, No. 3, pp. 293-298, 1978.
  17. R. Necker, "Somatosensory System," Physiology and Behavior of the Pigeon, pp. 169-192. Academic Press, London (1983)
  18. R.E. Brown, and M.R. Fedde, "Airflow Sensors in the Avian Wing," Journal of Experimental Biology, Vol. 179, No. 1, pp. 13-30, 1993. https://doi.org/10.1242/jeb.179.1.13
  19. A.L.R. Thomas, and G.K. Taylor, "Animal Flight Dynamics I. Stability in Gliding Flight," Journal of Theoretical Biology, Vol. 212, No. 3, pp. 399-424, 2001. https://doi.org/10.1006/jtbi.2001.2387
  20. T. Weis-Fogh, and M. Jensen, "Biology and Physics of Locust Flight I: Basic Principles in Insect Flight. A Critical Review," Philosophical Transactions of the Royal Society of London B, Vol. 239, No. 667, pp. 415-458, 1956. https://doi.org/10.1098/rstb.1956.0007
  21. R. Smith, "Intelligent Motion Control with an Artificial Cerebellum," Doctoral Dissertation, University of Auckland, New Zealand, 1998, http://ode.org/
  22. R.D. Beer, "On the Dynamics of Small Continuous-Time Recurrent Neural Networks," Adaptive Behavior, Vol. 3, No. 4, pp. 469-509, 1995. https://doi.org/10.1177/105971239500300405
  23. P. Husbands, "Distributed Coevolutionary Genetic Algorithms for Multi-criteria and Multi-constraint Optimisation," Evolutionary Computing. LNCS, Vol. 865, pp. 150-165, 1994.
  24. P.J. Clark, and F.C. Evans, "Distance to Nearest Neighbor as a Measure of Spatial Relationship in Populations," Ecology, Vol. 35, No. 4, pp. 445-453, 1954. https://doi.org/10.2307/1931034