Unsupervised Intuitive Physics from Visual Observations

by   Sebastien Ehrhardt, et al.

While learning models of intuitive physics is an increasingly active area of research, current approaches still fall short of natural intelligences in one important regard: they require external supervision, such as explicit access to physical states, at training and sometimes even at test times. Some authors have relaxed such requirements by supplementing the model with an handcrafted physical simulator. Still, the resulting methods are unable to automatically learn new complex environments and to understand physical interactions within them. In this work, we demonstrated for the first time learning such predictors directly from raw visual observations and without relying on simulators. We do so in two steps: first, we learn to track mechanically-salient objects in videos using causality and equivariance, two unsupervised learning principles that do not require auto-encoding. Second, we demonstrate that the extracted positions are sufficient to successfully train visual motion predictors that can take the underlying environment into account. We validate our predictors on synthetic datasets; then, we introduce a new dataset, ROLL4REAL, consisting of real objects rolling on complex terrains (pool table, elliptical bowl, and random height-field). We show that in all such cases it is possible to learn reliable extrapolators of the object trajectories from raw videos alone, without any form of external supervision and with no more prior knowledge than the choice of a convolutional neural network architecture.


page 5

page 6

page 7

page 8


Occlusion resistant learning of intuitive physics from videos

To reach human performance on complex tasks, a key ability for artificia...

SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments

Recent advancements in deep learning, computer vision, and embodied AI h...

Unsupervised Intuitive Physics from Past Experiences

We are interested in learning models of intuitive physics similar to the...

Structured Object-Aware Physics Prediction for Video Modeling and Planning

When humans observe a physical system, they can easily locate objects, u...

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions

Common-sense physical reasoning is an essential ingredient for any intel...

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Given a visual scene, humans have strong intuitions about how a scene ca...

Adding Intuitive Physics to Neural-Symbolic Capsules Using Interaction Networks

Many current methods to learn intuitive physics are based on interaction...

Please sign up or login with your details

Forgot password? Click here to reset