Perceiving Physical Equation by Observing Visual Scenarios

TL;DR

This paper introduces a novel approach for machines to infer invariant physical laws from visual data by mimicking human observation and reasoning, demonstrated through experiments on synthetic videos.

Contribution

It proposes a new pipeline with observer and physicist engines that derive interpretable physical equations from visual scenarios, advancing AI's understanding of physical laws.

Findings

Successfully infers physical laws from synthetic videos

Produces interpretable mathematical equations of object dynamics

Works across different visual appearances of physical worlds

Abstract

Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such that we introduce a new challenging problem of inferring invariant physical equation from visual scenarios. For instance, teaching a machine to automatically derive the gravitational acceleration formula by watching a free-falling object. To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world. Generally, the Observer Engine watches the visual scenarios and then extracting the physical properties of objects. The Physicist Engine analyses these data and then summarizing the inherent laws of object dynamics. Specifically, the learned laws are expressed by mathematical equations such that they are more interpretable than the results given by common probabilistic models. Experiments on synthetic videos have shown that our pipeline is able to discover physical equations on various physical worlds with different visual appearances.