Predicting the Physical Dynamics of Unseen 3D Objects

TL;DR

This paper presents a neural network model that predicts the physical dynamics of unseen 3D objects after impulsive forces, generalizing to new shapes and initial conditions for improved robotic and virtual environment interactions.

Contribution

The approach uniquely combines shape features and recurrent neural networks to predict dynamics of unseen objects, supporting training with both simulated and real-world data.

Findings

Accurately predicts state changes for unseen geometries

Generalizes to new initial velocities and shapes

Supports training with real-world and simulated data

Abstract

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. In particular, we predict the changes in state - 3D position, rotation, velocities, and stability. Different from previous work, our approach can generalize dynamics predictions to object shapes and initial conditions that were unseen during training. Our method takes the 3D object's shape as a point cloud and its initial linear and angular velocities as input. We extract shape features and use a recurrent neural network to predict the full change in state at each time step. Our model can support training with data from both a physics engine or the real world. Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.