A nervous system model for direct dynamics animation control based on evolutionary computation

In this paper, we approach the relevant problem of controlling locomotion of articulated figures taking Physics into account. The model proposed in this work determines the forces that actuate the articulated figure in order to obtain a desired locomotion goal. The controller developed for that purpose is based on some of the works on control of neuro-musculoskeletal representations of articulated figures and on neural oscillators encountered in the literature. Our model, however, takes a more generic approach using evolutionary computation and is capable of automatically generating motion gaits while maintaining stability independently of the environment and of the controlled articulated figure. The limitations of the proposed controller are also discussed.

[1]  Kazunori Hase,et al.  Evolutionary generation of human-like bipedal locomotion , 2003 .

[2]  Hiroshi Shimizu,et al.  Self-organized control of bipedal locomotion by neural oscillators in unpredictable environment , 1991, Biological Cybernetics.

[3]  Atsuo Kato,et al.  A model of neuro-musculo-skeletal system for human locomotion under position constraint condition. , 2003, Journal of biomechanical engineering.

[4]  Gentaro Taga,et al.  A model of the neuro-musculo-skeletal system for anticipatory adjustment of human locomotion during obstacle avoidance , 1998, Biological Cybernetics.

[5]  Phil Husbands,et al.  Evolution of central pattern generators for bipedal walking in a real-time physics environment , 2002, IEEE Trans. Evol. Comput..

[6]  Joe Laszlo,et al.  CONTROLLING BIPEDAL LOCOMOTION FOR COMPUTER ANIMATION , 1996 .

[7]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[8]  Sooyol Ok,et al.  Evolution of the CPG with Sensory Feedback for Bipedal Locomotion , 2005, ICNC.

[9]  W. Sellers,et al.  Stride lengths, speed and energy costs in walking of Australopithecus afarensis: using evolutionary robotics to predict locomotion of early human ancestors , 2005, Journal of The Royal Society Interface.

[10]  Akinori Nagano,et al.  Neuromusculoskeletal computer modeling and simulation of upright, straight-legged, bipedal locomotion of Australopithecus afarensis (A.L. 288-1). , 2005, American journal of physical anthropology.

[11]  Michiel van de Panne,et al.  Virtual Wind-up Toys for Animation , 1993 .

[12]  S. Grillner.  Control of Locomotion in Bipeds, Tetrapods, and Fish , 1981 .

[13]  John R. Koza,et al.  Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems , 1990 .

[14]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[15]  Kiyotoshi Matsuoka,et al.  Sustained oscillations generated by mutually inhibiting neurons with adaptation , 1985, Biological Cybernetics.

[16]  Kazunori Hase,et al.  Computational evolution of human bipedal walking by a neuro-musculo-skeletal model , 1999, Artificial Life and Robotics.

[17]  Arthur Prochazka,et al.  The man-machine analogy in robotics and neurophysiology , 2002 .

[18]  Matthew M. Williamson.  Designing rhythmic motions using neural oscillators , 1999, Proceedings 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human and Environment Friendly Robots with High Intelligence and Emotional Quotients (Cat. No.99CH36289).

[19]  Kazunori Hase,et al.  Human gait simulation with a neuromusculoskeletal model and evolutionary computation , 2003, Comput. Animat. Virtual Worlds.

[20]  Krister Wolff,et al.  Learning Biped Locomotion from First Principles on a Simulated Humanoid Robot Using Linear Genetic Programming , 2003, GECCO.

[21]  Oussama Khatib,et al.  Simulating the task-level control of human motion: a methodology and framework for implementation , 2005, The Visual Computer.