CaltechAUTHORS
  A Caltech Library Service

Causal Discovery in Physical Systems from Videos

Li, Yunzhu and Torralba, Antonio and Anandkumar, Animashree and Fox, Dieter and Garg, Animesh (2020) Causal Discovery in Physical Systems from Videos. In: Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020). Advances in Neural Information Processing Systems . https://resolver.caltech.edu/CaltechAUTHORS:20201109-123525639

[img] PDF - Published Version
See Usage Policy.

4MB
[img] PDF - Submitted Version
See Usage Policy.

7MB
[img] Archive (ZIP) - Supplemental Material
See Usage Policy.

47MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20201109-123525639

Abstract

Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ from our previous experiences. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure. In particular, our goal is to discover the structural dependencies among environmental and object variables: inferring the type and strength of interactions that have a causal effect on the behavior of the dynamical system. Our model consists of (a) a perception module that extracts a semantically meaningful and temporally consistent keypoint representation from images, (b) an inference module for determining the graph distribution induced by the detected keypoints, and (c) a dynamics module that can predict the future by conditioning on the inferred graph. We assume access to different configurations and environmental conditions, i.e., data from unknown interventions on the underlying system; thus, we can hope to discover the correct underlying causal graph without explicit interventions. We evaluate our method in a planar multi-body interaction environment and scenarios involving fabrics of different shapes like shirts and pants. Experiments demonstrate that our model can correctly identify the interactions from a short sequence of images and make long-term future predictions. The causal structure assumed by the model also allows it to make counterfactual predictions and extrapolate to systems of unseen interaction graphs or graphs of various sizes.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://proceedings.neurips.cc/paper/2020/hash/6822951732be44edf818dc5a97d32ca6-Abstract.htmlPublisherArticle
https://arxiv.org/abs/2007.00631arXivDiscussion Paper
https://yunzhuli.github.io/V-CDNRelated ItemProject page
ORCID:
AuthorORCID
Garg, Animesh0000-0003-0482-4296
Record Number:CaltechAUTHORS:20201109-123525639
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20201109-123525639
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106512
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:09 Nov 2020 21:42
Last Modified:09 Nov 2020 21:42

Repository Staff Only: item control page