Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

TL;DR

This work proposes local coordinate frames per node-object to induce roto-translation invariance to the geometric graph of the interacting dynamical system and demonstrates that the proposed approach comfortably outperforms the recent state-of-the-art.

Abstract

Modelling interactions is critical in learning complex dynamical systems, namely systems of interacting objects with highly non-linear and time-dependent behaviour. A large class of such systems can be formalized as $\textit{geometric graphs}$, $\textit{i.e.}$, graphs with nodes positioned in the Euclidean space given an $\textit{arbitrarily}$ chosen global coordinate system, for instance vehicles in a traffic scene. Notwithstanding the arbitrary global coordinate system, the governing dynamics of the respective dynamical systems are invariant to rotations and translations, also known as $\textit{Galilean invariance}$. As ignoring these invariances leads to worse generalization, in this work we propose local coordinate frames per node-object to induce roto-translation invariance to the geometric graph of the interacting dynamical system. Further, the local coordinate frames allow for a natural definition of anisotropic filtering in graph neural networks. Experiments in traffic scenes, 3D motion capture, and colliding particles demonstrate that the proposed approach comfortably outperforms the recent state-of-the-art.

Figures (1)

• Figure 1: In (a), objects positioned in an arbitrary global 2D coordinate frame; arrows represent orientations. In (b)-(e), objects in the canonicalized local coordinate frames, translated to match the target object's position and rotated to match its orientation