FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning

arXiv:2402.13820v1 Announce Type: new
Abstract: Motion trajectories offer reliable references for physics-based motion learning but suffer from sparsity, particularly in regions that lack sufficient data coverage. To address this challenge, we introduce a self-supervised, structured representation and generation method that extracts spatial-temporal relationships in periodic or quasi-periodic motions. The motion dynamics in a continuously parameterized latent space enable our method to enhance the interpolation and generalization capabilities of motion learning algorithms. The motion learning controller, informed by the motion parameterization, …

abstract arxiv challenge coverage cs.ai cs.lg cs.ro cs.sy data dynamics eess.sp eess.sy fourier physics relationships representation sparsity spatial temporal type