Reductive Mapping for Sequential Patterns of Humanoid Body Motion
Reductive Mapping for Sequential Patterns of Humanoid Body Motion
复制标题
人形身体运动序列模式的还原映射
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Yoshihiko Nakamura
中科院分区：
文献类型：
--
作者：
K. Tatani;Yoshihiko Nakamura
由于类人机器人具有人类的形态，用户在试图作为飞行员进行控制时会直观地期望他们可以自由地操纵类人的四肢，然而，它不是真实的，因为它很难同时向整个身体发出多个控制输入。另一方面，少量的控制输入，例如发条机械娃娃中的凸轮，可以产生各种运动模式，从这个意义上说，对于运动模式生成，在对人形机器人的大量控制输入和用户可以有意操作的少量控制输入之间双向地获得映射函数是有用的。从多变量分析的观点来看，通过在关节角空间中执行主成分分析PCA，运动模式被转换为低维变量。本文利用层次非线性主成分分析（NLPCA），给出了维数输入可以产生近似的步行模式，维数输入可以产生运动模式类型的结果。
Since a humanoid robot takes the morphology of human users will intuitively expect that they can freely manipulate the humanoid extremities when try to control as pilots However it is not real ized with simple devices because it is di cult to simultaneously issue multiple control inputs to the whole body On the other hand a small number of control inputs such as a cam in a wind up me chanical doll can generate various motion patterns of extremities In this sense it is useful for mo tion pattern generation to get mapping functions bidirectionally between a large number of control inputs to a humanoid robot and a small number of control inputs that a user can intentionally op erate From a standpoint of multivariate analysis by executing principal component analysis PCA in joint angle space motion patterns are converted into low dimensional variables The problem is to nd such convenient variables not only for speci c motion like walk but also multiple whole body mo tion patterns This paper presents the results that dimensional inputs can generate an approximate walking pattern and dimensional inputs does types of motion patterns with hierarchical nonlin ear PCA NLPCA