Learning to Predict 3D Rotational Dynamics from Images of a Rigid Body with Unknown Mass Distribution

arXiv:2308.14666v2 Announce Type: replace-cross
Abstract: In many real-world settings, image observations of freely rotating 3D rigid bodies may be available when low-dimensional measurements are not. However, the high-dimensionality of image data precludes the use of classical estimation techniques to learn the dynamics. The usefulness of standard deep learning methods is also limited, because an image of a rigid body reveals nothing about the distribution of mass inside the body, which, together with initial angular velocity, is what determines how the …

abstract arxiv cs.ce cs.cv cs.lg data dimensionality distribution dynamics however image image data images learn low type world