Where Industry Meets Innovation

  • Contact Us
  • sign in Sign In
  • Sign in with certificate
mit campus

Resources

Search News

  • View All
  • ILP News
  • MIT Research News
  • MIT Sloan Management Review
  • Technology Review
  • Startup Exchange

MIT Research News

December 2, 2019

Helping machines perceive some laws of physics

Model registers “surprise” when objects in a scene do something unexpected, which could be used to build smarter AI.

Rob Matheson | MIT News Office

Humans have an early understanding of the laws of physical reality. Infants, for instance, hold expectations for how objects should move and interact with each other, and will show surprise when they do something unexpected, such as disappearing in a sleight-of-hand magic trick.

Now MIT researchers have designed a model that demonstrates an understanding of some basic “intuitive physics” about how objects should behave. The model could be used to help build smarter artificial intelligence and, in turn, provide information to help scientists understand infant cognition.

The model, called ADEPT, observes objects moving around a scene and makes predictions about how the objects should behave, based on their underlying physics. While tracking the objects, the model outputs a signal at each video frame that correlates to a level of “surprise” — the bigger the signal, the greater the surprise. If an object ever dramatically mismatches the model’s predictions — by, say, vanishing or teleporting across a scene — its surprise levels will spike.