首页>
外国专利>
Methods of learning parameters of a neural network, generating a trajectory of an exoskeleton and setting the exoskeleton in motion
Methods of learning parameters of a neural network, generating a trajectory of an exoskeleton and setting the exoskeleton in motion
展开▼
机译:神经网络的学习参数方法,产生外骨骼的轨迹并在运动中设置外骨骼
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to a method of learning parameters of a neural network for generating trajectories of an exoskeleton (1), the method comprising the implementation by data processing means (11a) of a first server (10a), steps of: (a) Learning of the parameters of a first neural network capable of generating periodic elementary trajectories of the exoskeleton (1) each for a given walk of the exoskeleton (1) defined by an n-tuple of walking parameters, as a function of a first learning database of periodic trajectories for a set of possible steps of the exoskeleton (1); (b) Learning, from the parameters of the first neural network, of the parameters of a second neural network capable of generating periodic elementary trajectories of the exoskeleton (1) and of the transitions of a periodic elementary trajectory of the exoskeleton (1) to another periodic elementary trajectory of the exoskeleton (1), as a function of a second learning database of elementary periodic trajectories and transitions for a set of possible exoskeleton steps (1) . Abstract figure: Fig 1
展开▼