Reasoning about physical interactions with object-oriented prediction and planning
Name
o2p2_iclr.pdf
Description
Accepted version
Size
15.19 MB
Format
Adobe PDF
Checksum (MD5)
2a8a572eea50d4a6f0e3d2da9f5cc7f3
Author(s)
Janner, Michael
Levine, Sergey
Freeman, William T
Tenenbaum, Joshua B
Finn, Chelsea
Wu, Jiajun
Date Issued
May 2019
Journal
ICLR 2019: International Conference on Learning Representations
Publisher
International Conference on Learning Representations
Citation
Janner, Michael et al. "Reasoning about physical interactions with object-oriented prediction and planning." ICLR 2019: 7th International Conference on Learning Representations, May 6-9, 2019, New Orleans, Louisiana:
https://openreview.net/forum?id=HJx9EhC9tQ ©2019 Author(s)
Version
Author's final manuscript
Abstract
Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a paradigm for learning object-centric representations for physical scene understanding without direct supervision of object properties. Our model, Object-Oriented Prediction and Planning (O2P2), jointly learns a perception function to map from image observations to object representations, a pairwise physics interaction function to predict the time evolution of a collection of objects, and a rendering function to map objects back to pixels. For evaluation, we consider not only the accuracy of the physical predictions of the model, but also its utility for downstream tasks that require an actionable representation of intuitive physics. After training our model on an image prediction task, we can use its learned representations to build block towers more complicated than those observed during training.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://openreview.net/forum?id=HJx9EhC9tQ¬eId=HJx9EhC9tQ
