Please help transcribe this video using our simple transcription tool. You need to be logged in to do so.
This paper examines the extent to which nonlinear dimension reduction techniques from machine learning can be exploited to determine dynamically optimal motions for high degree-of-freedom systems. Using the Gaussian Process Latent Variable Model (GPLVM) to learn the low-dimensional embedding, and a density function that provides a nonlinear mapping from the low-dimensional latent space to the full-dimensional pose space, we determine optimal motions by optimizing the latent space, and mapping the optimal trajectory in the latent space to the pose space. The notion of variance tubes are developed to ensure that kinematic constraints and other are appropriately satisfied without sacrificing naturalness or richness of the motions. Case studies of a 62-dof humanoid performing two sports motions---a golf swing and throwing a baseball---demonstrate that our method can be a highly effective, computationally efficient method for generating dynamically optimal motions.
Questions and AnswersYou need to be logged in to be able to post here.