Interaction Networks for Learning about Objects, Relations and Physics

12/01/2016
by   Peter W. Battaglia, et al.
0

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object- and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body problems, rigid-body collision, and non-rigid dynamics. Our results show it can be trained to accurately simulate the physical trajectories of dozens of objects over thousands of time steps, estimate abstract quantities such as energy, and generalize automatically to systems with different numbers and configurations of objects and relations. Our interaction network implementation is the first general-purpose, learnable physics engine, and a powerful general framework for reasoning about object and relations in a wide variety of complex real-world domains.

READ FULL TEXT
research
12/01/2016

A Compositional Object-Based Approach to Learning Physical Dynamics

We present the Neural Physics Engine (NPE), a framework for learning sim...
research
02/12/2022

Neural NID Rules

Abstract object properties and their relations are deeply rooted in huma...
research
05/09/2021

Simulated Data Generation Through Algorithmic Force Coefficient Estimation for AI-Based Robotic Projectile Launch Modeling

Modeling of non-rigid object launching and manipulation is complex consi...
research
09/05/2018

Modeling human intuitions about liquid flow with particle-based simulation

Humans can easily describe, imagine, and, crucially, predict a wide vari...
research
04/27/2021

The Role of General Intelligence in Mathematical Reasoning

Objects are a centerpiece of the mathematical realm and our interaction ...
research
09/09/2019

Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects

In recent years, graph neural networks have been successfully applied fo...
research
02/21/2020

Learning to Simulate Complex Physics with Graph Networks

Here we present a general framework for learning simulation, and provide...

Please sign up or login with your details

Forgot password? Click here to reset