Equivariant Deep Dynamical Model for Motion Prediction
This addresses motion prediction tasks by incorporating symmetry awareness, though it appears incremental as it builds on existing deep dynamical models with equivariant networks.
The paper tackled the problem of motion prediction by proposing an SO(3) equivariant deep dynamical model (EqDDM) that learns structured representations informed by symmetries, resulting in superior predictive performance on various motion data.
Learning representations through deep generative modeling is a powerful approach for dynamical modeling to discover the most simplified and compressed underlying description of the data, to then use it for other tasks such as prediction. Most learning tasks have intrinsic symmetries, i.e., the input transformations leave the output unchanged, or the output undergoes a similar transformation. The learning process is, however, usually uninformed of these symmetries. Therefore, the learned representations for individually transformed inputs may not be meaningfully related. In this paper, we propose an SO(3) equivariant deep dynamical model (EqDDM) for motion prediction that learns a structured representation of the input space in the sense that the embedding varies with symmetry transformations. EqDDM is equipped with equivariant networks to parameterize the state-space emission and transition models. We demonstrate the superior predictive performance of the proposed model on various motion data.