Dynamic gait pattern generation with reinforcement learning


IFAC Proceedings Volumes (IFAC-PapersOnline), vol.16, pp.151-156, 2005 (Refereed Journals of Other Institutions) identifier

  • Publication Type: Article / Abstract
  • Volume: 16
  • Publication Date: 2005
  • Doi Number: 10.3182/20050703-6-cz-1902.01295
  • Title of Journal : IFAC Proceedings Volumes (IFAC-PapersOnline)
  • Page Numbers: pp.151-156
  • Keywords: Gait pattern, Radial basis function neural network, Reinforcement learning, Six-legged robot, Walking


This paper presents the gait pattern generation work performed for the sixlegged robot EA308 developed in our laboratory. The aim is to achieve a dynamically developing gait pattern generation structure using reinforcement learning. For the six legged robot a simplified simulative model is constructed. The algorithm constructs a radial basis function neural network (RBFNN) to command proper leg configurations to the simulative robot. The weights of the RBFNN are learned using reinforcement learning. The developed structure succeeded in learning gait patterns compatible with different speeds of the robot. Copyright © 2005 IFAC.