경로 제어가 가능한 가상생명체를 위한 2단계 진화 알고리즘

Two-Stage Evolutionary Algorithm for Path-Controllable Virtual Creatures

  • 발행 : 2005.12.01

초록

본 논문은 사용자의 제어가 가능한 3차원 물리 기반 가상생명체를 생성하는 2단계 진화 시스템을 제안한다. 기존의 방법은 가상생명체의 형상과 기동, 그리고 목표지점추적(target-following)과 같은 상위 레벨의 행위를 한꺼번에 하나의 진화 시스템으로 생성해냄으로 인하여 진화 단계에서의 사용자의 개입을 허용하지 않았다. 본 논문은 하나로 묶여있던 시스템을 다루기 용이한 두 개의 서브시스템으로 분리함으로써 사용자의 개입을 허용한다. 첫 번째 단계로 가상생명체의 몸체와 직진 기동을 위한 하위 레벨 모터 컨트롤러가 진화 알고리즘(evolutionary algorithm)으로 동시에 생성된다. 두 번째 단계에는 생성된 기본 생명체 위에 주어진 경로를 따라가기 위한 상위 레벨 컨트롤러가 인공 신경망을 사용하여 탑재된다. 경로제어(path-following)를 위한 신경망의 연결 가중치는 유전자 알고리즘(genetic algorithm)을 사용하여 최적화되며 한번 진화된 신경망 컨트롤러는 어떠한 임의의 경로도 잘 따라감을 보여준다. 이로써 사용자는 모든 진화과정이 끝나지 않고도 중간단계에서 기호에 맞는 생명체를 골라내거나 버릴 수 있으며, 동일한 기본 생명체 위에 또 다른 형태의 상위레벨 행위를 생성하는 것도 가능해진다. 본 논문은 이러한 2단계 알고리즘과 함께 직진기동을 위한 새로운 분절 삼각 함수(Piecewise sinusoidal) 컨트롤러를 제안하고 마개 실린더(capped-cylinder)를 기본 요소로 하는 가상생명체에 대한 효율적인 실시간 수중역학 모델링 기법도 함께 소개한다.

We present a two-step evolution system that produces controllable virtual creatures in physically simulated 3D environment. Previous evolutionary methods for virtual creatures did not allow any user intervention during evolution process, because they generated a creature's shape, locomotion, and high-level behaviors such as target-following and obstacle avoidance simultaneously by one-time evolution process. In this work, we divide a single system into manageable two sub-systems, and this more likely allowsuser interaction. In the first stage, a body structure and low-level motor controllers of a creature for straight movement are generated by an evolutionary algorithm. Next, a high-level control to follow a given path is achieved by a neural network. The connection weights of the neural network are optimized by a genetic algorithm. The evolved controller could follow any given path fairly well. Moreover, users can choose or abort creatures according to their taste before the entire evolution process is finished. This paper also presents a new sinusoidal controller and a simplified hydrodynamics model for a capped-cylinder, which is the basic body primitive of a creature.

키워드

참고문헌

  1. Ijspeert, A.J., Hallam, J. and Willshaw, D. (1998) From lampreys to salamanders: evolving neural controllers for swimming and walking, From Animals to Animats, Proceedings of the Fifth International Conference on the Simulation of Adaptive Behavior(SAB98), R. Pfeifer, B. Blumberg, J.-A. Meyer and S.W. Wilson (eds), MIT Press, pp. 390-399
  2. Reeve, R. and Hallam, J. (2005) An Analysis of Neural Models for Walking Control. IEEE Transactions on Neural Networks, vol. 16, no. 3 https://doi.org/10.1109/TNN.2005.844901
  3. Sims, K. 1994. Evolving Virtual Creatures, ACM Computer Graphics (SIGGRAPH '94), pp. 15-22 https://doi.org/10.1145/192161.192167
  4. Sims, K. 1994. Evolving 3D Morphology and Behavior by Competition. R Brooks, & P. Maes, (eds.) Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, pp. 28-39, MIT Press
  5. Ventrella, J. 1998. Attractiveness vs. Efficiency: How Mate Preference Affects Locomotion in the Evolution of Artificial Swimming Organisms. Adami, C. et al. (eds.) Artificial Life VI: Proceedings of the Sixth International Conference on Artificial Life. pp. 178-186: MIT Press
  6. Komosinski, M and Ulatowski, S. 1999. Framsticks: Towards a Simulation of a Nature-Like World, Creatures and Evolution. Floreano, D. et al. (eds.) Advances in Artificial Life: Proceedings of the Fifth European Conference on Artificial Life, pp. 261-265: Springer Verlag
  7. Ray, T. S. 2000. Aesthetically Evolved Virtual Pets. Maley, C.C. & Boudreau, E. (eds.) Artificial Life VII Workshop Proceedings. pp. 158-161
  8. Lipson, H. and Pollack, J. B. 2000. Automatic Design and Manufacture of Robotic Lifeforms. Nature 406, pp. 974-978 https://doi.org/10.1038/35023115
  9. Grzeszczuk, R, and Terzopoulos, D. Automated learning of muscleactuated locomotion through control abstraction. In Proceedings of SIGGRAPH 95 (Los Angeles, Aug. 6.11). ACM Press, New York, 1995, pp. 63.70
  10. Smith, R. 1998. Intelligent Motion Control with an Artificial Cerebellum. PhD Thesis, Dept of Electrical and Electronic Engineering, University of Auckland, New Zealand. (Available online including ODE engine at http://onende.sourceforge.net)
  11. Anitescu, M. and Potra, F. A. 1997. Formulating rigid multi-body dynamics with contact and friction as solvable linear complementarity problems, Nonlinear Dynamics 14, 231.247 https://doi.org/10.1023/A:1008292328909
  12. Stewart, D. E. and Trinkle, J. C. 1996. An implicit time-stepping scheme for rigid-body dynamics with inelastic collisions and Coulomb friction, International J. Numerical Methods in Engineering 39, 2673-2691 https://doi.org/10.1002/(SICI)1097-0207(19960815)39:15<2673::AID-NME972>3.0.CO;2-I
  13. Wejchert, J. and Haumann, D. 1991. Animation aerodynamics. SIGGRAPH 91 Proceedings. volume 25, number 4 https://doi.org/10.1145/122718.122719
  14. Fox, R. W. and McDonald, A. T. 1976. Introduction to fluid mechanics. fifth edition, Wiley
  15. Wu, X. C. and Popovic, Z. 2003. Realistic Modeling of Bird Flight Animations. in Proceeding of SIGGRAPH '87, pp. 888-895
  16. Rivals, I., Personnaz, L., Dreyfus, G., and Canas, D. 1993. Real-time Control of an Autonomous Vehicle : A Neural Network Approach to the Path Following Problem. in 5th International Conference on Neural Networks and their Applications (NeuroNimes93)