A Compositional Object-Based Approach to Learning Physical Dynamics

Michael B. Chang, Joshua B. Tenenbaum, Antonio Torralba, Tomer Ullman
2016-12-01

SCID:  54.1/ygd74tzh
We present the Neural Physics Engine (NPE), a framework for learning simulators of intuitive physics that naturally generalize across variable object count and different scene configurations. We propose a factorization of a physical scene into composable object-based representations and a neural network architecture whose compositional structure factorizes object dynamics into pairwise interactions. Like a symbolic physics engine, the NPE is endowed with generic notions of objects and their interactions; realized as a neural network, it can be trained via stochastic gradient descent to adapt to specific object properties and dynamics of different worlds. We evaluate the efficacy of our approach on simple rigid body dynamics in two-dimensional worlds. By comparing to less structured architectures, we show that the NPE's compositional representation of the structure in physical interactions improves its ability to predict movement, generalize across variable object count and different scene configurations, and infer latent properties of objects such as mass.
Publication Details
Publication Date
2016-12-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Michael B. Chang
Joshua B. Tenenbaum
Antonio Torralba
Tomer Ullman
Explore More Research
Use the citation graph to discover related papers and expand your research horizons.
Click any node to explore
Download PDF
100%