Robot Learning Manipulation Action Plans by “Watching” Unconstrained Videos from the World Wide Web
有两个CNN 流程:
一个用来做对象识别;
一个用来做hand grasp type 分类。
架构图:
Robot Learning Manipulation Action Plans by “Watching” Unconstrained Videos from the World Wide Web
有两个CNN 流程:
一个用来做对象识别;
一个用来做hand grasp type 分类。
架构图: