Acquisition of Ground Behavior on the Locust Model under the Virtual Physical Environment
We have studied about ground behavior on the locust model under the virtual physical environment. In the previous study, the locust model acquires jumping behavior by use of neuro-evolution. However, a real locust often uses the jumping and walking behavior more flexibility. In this study, we realize the jumping and walking behavior for the same locust model. Both of those behavior are trained by use of neuro-evolution which is composed of artificial neural network(ANN) and real-coded genetic algorithm(RCGA). We analyze the obtained jumping and walking behavior and show the possibility to acquire flexible behavior.
Unable to display preview. Download preview PDF.
- 1.McKinley, P.A., Smith, J.L., Gregor, R.J.: Responses of elbow extensors to landing forces during jump downs in cats. Experimental Brain Research 49 (1983)Google Scholar
- 2.Yong, C.: Jumping mechanism and simulation of the locust-like robot. In: 2010 2nd International Conference on Education Technology and Computer (ICETC), vol. 1, pp. V1 (2010)Google Scholar
- 3.Kikuchi, F., Ota, Y., Hirose, S.: Basic performance experiments for jumping quadruped. In: Intelligent Robots and Systems(IROS 2003), vol. 4, pp. 3378–3383 (2003)Google Scholar
- 4.Kovac, M., Schlegel, M., Zufferey, J.C., Floreano, D.: A miniature jumping robot with self-recovery capabilities. In: Intelligent Robots and Systems(IROS 2009), pp. 583–588 (2009)Google Scholar
- 7.Furukawa, M., Morinaga, M., Ooe, R., Watanabe, M., Suzuki, I., Yamamoto, M.: Behavior Composed for Artificial Flying Creature. In: Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent System, pp. 861–867 (2010)Google Scholar