Intuitive Physics
NIPS Workshop
09 December 2016
Barcelona, Spain
Despite recent progress, AI is still far away from achieving common sense reasoning. One area that is gathering a lot of interest is that of intuitive or naive physics. It concerns the ability that humans and, to a certain extent, infants and animals have to predict outcomes of physical interactions involving macroscopic objects. There is extensive experimental evidence that infants can predict the outcome of events based on physical concepts such as gravity, solidity, object permanence and conservation of shape and number, at an early stage of development, although there is also evidence that this capacity develops through time and experience. Recent work has attempted to build neural models that can make predictions about stability, collisions, forces and velocities from images or videos, or interactions with an environment. Such models could be both used to understand the cognitive and neural underpinning of naive physics in humans, but also to provide with AI applications more better inference and reasoning abilities.
This workshop will bring together researchers in machine learning, computer vision, robotics, computational neuroscience, and cognitive development to discuss artificial systems that capture or model intuitive physics by learning from footage of, or interactions with a real or simulated environment. There will be invited talks from world leaders in the fields, presentations and poster sessions based on contributed papers, and a panel discussion.
Organizers
- Jiajun Wu (MIT)
- Adam Lerer (Facebook)
- Josh Tenenbaum (MIT)
- Emmanuel Dupoux (LSCP)
- Rob Fergus (Facebook, NYU)
Invited Talks
Research Talks
Schedule
- 08:45 - 09:00: Josh Tenenbaum: Opening Remark
- 09:00 - 09:30: Josh Tenenbaum: Naive Physics 101
- 09:30 - 10:00: Poster Spotlights
- 10:00 - 10:30: Ali Farhadi
(Coffee / Posters)
- 11:00 - 11:30: Peter Battaglia: Intuitive Physics via Simulation
- 11:30 - 12:00: Pulkit Agrawal
(Lunch / Posters)
- 14:00 - 14:30: Abhinav Gupta
- 14:30 - 15:00: Bill Freeman
(Coffee / Posters)
- 15:30 - 15:50: Jess Hamrick: Imagination-Based Decision Making with Physical Models in Deep Neural Networks
- 15:50 - 16:10: Chelsea Finn: Deep Visual Foresight for Planning Robot Motion
- 16:10 - 16:30: Wenbin Li: Visual Stability Prediction and Its Application to Manipulation
- 16:30 - 17:30: Datasets, Methodology, and Challenges in Intuitive Physics: Adam Lerer, Emmanuel Dupoux, Ronan Riochet, Jiajun Wu, Josh Tenenbaum
- 17:30 - 18:30: Panel Discussion: Josh Tenenbaum, Peter Battaglia, Jess Hamrick, Wenbin Li, Chelsea Finn, Pulkit Agrawal, Abhinav Gupta, Bill Freeman