Interpretable Intuitive Physics Model

Abstract

Humans have a remarkable ability to use physical commonsense and predict the effect of collisions. But do they understand the underlying factors? Can they predict if the underlying factors have changed? Interestingly, in most cases humans can predict the effects of similar collisions with different conditions such as changes in mass, friction, etc. It is postulated this is primarily because we learn to model physics with meaningful latent variables. This does not imply we can estimate the precise values of these meaningful variables (estimate exact values of mass or friction). Inspired by this observation, we propose an interpretable intuitive physics model where specific dimensions in the bottleneck layers correspond to different physical properties. In order to demonstrate that our system models these underlying physical properties, we train our model on collisions of different shapes (cube, cone, cylinder, spheres etc.) and test on collisions of unseen combinations of shapes. Furthermore, we demonstrate our model generalizes well even when similar scenes are simulated with different underlying properties.

References in corpus (12)

• Unsupervised Learning of Video Representations using LSTMs
• Generating Videos with Scene Dynamics
• Deep Convolutional Inverse Graphics Network
• Deep multi-scale video prediction beyond mean square error
• Unsupervised Learning for Physical Interaction through Video Prediction
• A Compositional Object-Based Approach to Learning Physical Dynamics
• Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
• Learning to Poke by Poking: Experiential Learning of Intuitive Physics
• Learning Visual Predictive Models of Physics for Playing Billiards
• Visual Interaction Networks
• To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction
• A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding