Evolved Controllers for Simulated Locomotion

  • Brian F. Allen
  • Petros Faloutsos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5884)


We present a system for automatically evolving neural networks as physics-based locomotion controllers for humanoid characters. Our approach provides two key features: (a) the topology of the neural network controller gradually grows in size to allow increasingly complex behavior, and (b) the evolutionary process requires only the physical properties of the character model and a simple fitness function. No a priori knowledge of the appropriate cycles or patterns of motion is needed.


Central Pattern Generator Neural Network Controller Bipedal Walking Biped Locomotion Walk Cycle 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    van de Panne, M., Kim, R., Fiume, E.: Virtual wind-up toys for animation. In: Proceedings of Graphics Interface 1994, Banff, Alberta, Canada, pp. 208–215 (1994)Google Scholar
  2. 2.
    Raibert, M.H., Hodgins, J.K.: Animation of dynamic legged locomotion. In: SIGGRAPH 1991: Proceedings of the 18th annual conference on Computer graphics and interactive techniques, pp. 349–358. ACM Press, New York (1991)CrossRefGoogle Scholar
  3. 3.
    Hodgins, J.K., Wooten, W.L., Brogan, D.C., O’Brien, J.F.: Animating human athletics. In: SIGGRAPH 1995: Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, pp. 71–78. ACM Press, New York (1995)CrossRefGoogle Scholar
  4. 4.
    Faloutsos, P., van de Panne, M., Terzopoulos, D.: The virtual stuntman: dynamic characters with a repertoire of autonomous motor skills. Computers and Graphics 25(6), 933–953 (2001)CrossRefGoogle Scholar
  5. 5.
    Yin, K., Loken, K., van de Panne, M.: Simbicon: Simple biped locomotion control. In: Proceedings of the 2007 SIGGRAPH conference, vol. 26. ACM, New York (2007)Google Scholar
  6. 6.
    da Silva, M., Abe, Y., Popović, J.: Interactive simulation of stylized human locomotion. In: International Conference on Computer Graphics and Interactive Techniques. ACM, New York (2008)Google Scholar
  7. 7.
    Shapiro, A., Chu, D., Allen, B., Faloutsos, P.: A dynamic controller toolkit. In: Sandbox 2007: Proceedings of the 2007 ACM SIGGRAPH Symposium on Video Games, pp. 15–20. ACM, New York (2007)CrossRefGoogle Scholar
  8. 8.
    Witkin, A., Kass, M.: Spacetime constraints. Computer Graphics 22(4), 159–168 (1988)CrossRefGoogle Scholar
  9. 9.
    Liu, C.K., Hertzmann, A., Popovic, Z.: Learning physics-based motion style with nonlinear inverse optimization. ACM Transactions on Graphics (TOG) 24(3), 1071–1081 (2005)CrossRefGoogle Scholar
  10. 10.
    van de Panne, M.: Sensor-actuator networks. In: SIGGRAPH 1993: Proceedings of the 20th annual conference on Computer graphics and interactive techniques, pp. 335–342. ACM Press, New York (1993)CrossRefGoogle Scholar
  11. 11.
    Sims, K.: Evolving virtual creatures. In: SIGGRAPH 1994: Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pp. 15–22. ACM Press, New York (1994)CrossRefGoogle Scholar
  12. 12.
    Koza, J.: Genetic Programming: On the Programming of Computers by means of Natural Selection. MIT Press, Cambridge (1992)zbMATHGoogle Scholar
  13. 13.
    Gritz, L.: Evolutionary Controller Synthesis for 3-D Character Animation. PhD thesis, George Washington University (1999)Google Scholar
  14. 14.
    Laszlo, J., van de Panne, M., Fiume, E.: Limit cycle control and its application to the animation of balancing and walking. In: Computer Graphics. Annual Conference Series, vol. 30, pp. 155–162 (1996)Google Scholar
  15. 15.
    Nolfi, S., Floreano, D.: Evolutionary Robotics. In: Intelligent Robots and Autonomous Agents. MIT Press, Cambridge (2000)Google Scholar
  16. 16.
    Reil, T., Husbands, P.: Evolution of central pattern generators for bipedal walking in a real-time physics environment. IEEE Trans. Evolutionary Computation 6(2), 159–168 (2002)CrossRefGoogle Scholar
  17. 17.
    Reil, T., Massey, C.: Morpho-Functional Machines: The New Species: Designing Embodied Intelligence. Springer, Heidelberg (2003)Google Scholar
  18. 18.
    Golubitsky, M., Stewart, I., Buono, P.L., Collins, J.: Symmetry in locomotor central pattern generators and animal gaits. Nature 401, 693–695 (1999)CrossRefGoogle Scholar
  19. 19.
    Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87, 1423–1447 (1999)CrossRefGoogle Scholar
  20. 20.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  21. 21.
    Paul, C.: Bilateral decoupling in the neural control of biped locomotion. In: Proc. 2nd International Symposium on Adaptive Motion of Animals and Machines (2003)Google Scholar
  22. 22.
    Paul, C.: Sensorimotor control of biped locomotion based on contact information. In: Proc. International Symposium on Intelligent Signal Processing and Robotics (2004)Google Scholar
  23. 23.
    McHale, G., Husbands, P.: From Animals to Animats 8. In: Proceedings of the 8th International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge (2005)Google Scholar
  24. 24.
    Vaughan, E.D., Paolo, E.D., Harvey, I.R.: The evolution of control and adaptation in a 3d powered passive dynamic walker. In: Proceedings of the 9th International Conference on the Simulation and Synthesis of Living Systems (Alife9). MIT Press, Cambridge (2004)Google Scholar
  25. 25.
    Stanley, K.: Efficient Evolution of Neural Networks Through Complexification. PhD thesis, University of Texas, Austin (2004)Google Scholar
  26. 26.
    Hornby, G.S., Pollack, J.B.: Creating high-level components with a generative representation for body-brain evolution. Artificial Life 8(3), 223–246 (2002)CrossRefGoogle Scholar
  27. 27.
    Gruau, F.: Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm. PhD thesis, Laboratoire de l’Informatique du Parallilisme, Ecole Normale Supirieure de Lyon, France (1994)Google Scholar
  28. 28.
    Hornby, G.S.: Shortcomings with tree-structured edge encodings for neural networks. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 495–506. Springer, Heidelberg (2004)Google Scholar
  29. 29.
    Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. Journal of Artificial Intelligence Research (21), 63–100 (2004)Google Scholar
  30. 30.
    Department of Defense, U.S.o.A.: Anthropometry of U.S. Military Personnel (DOD-HDBK-743A). Department of Defense, United States of America (1991)Google Scholar
  31. 31.
    Bodenheimer, B., Shleyfman, A., Hodgins, J.: The effects of noise on the perception of animated human running. Computer Animation and Simulation (1999)Google Scholar
  32. 32.
    DJ, D.: Neuromuscular control system. IEEE Transactions on Biomedical Engineering 3, 167–171 (1967)Google Scholar
  33. 33.
    Zordan, V.B., Majkowska, A., Chiu, B., Fast, M.: Dynamic response for motion capture animation. ACM Trans. Graph. 24(3), 697–701 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Brian F. Allen
    • 1
  • Petros Faloutsos
    • 1
  1. 1.University of CaliforniaLos AngelesUSA

Personalised recommendations