Online Learning of Danger Avoidance for Complex Structures of Musculoskeletal Humanoids and Its Applications

-- The complex structure of musculoskeletal humanoids makes it difficult to model them, and the inter-body interference and high internal muscle force are unavoidable. Although various safety mechanisms have been developed to solve this problem, it is important not only to deal with the dangers when they occur but also to prevent them from happening. In this study, we propose a method to learn a network outputting danger probability corresponding to the muscle length online so that the robot can gradually prevent dangers from occurring. Applications of this network for control are also described. The method is applied to the musculoskeletal humanoid, Musashi, and its effectiveness is verified. I. INTRODUCTION The musculoskeletal humanoid [1]-[4] has various biomimetic advantages such as variable stiffness using redundant muscles, spherical joints without singular points, underactuated and flexible fingers, etc. At the same time, its complex musculoskeletal structure is difficult to model and various learning control methods have been developed [5]- [8].