A computer model simulating how objects react to physical forces approximates how babies understand...
These fundamental properties of physical objects seem intuitive to us.
"It's so striking that as much as AI technologies have advanced, we still don't have AI systems with anything like human common sense," says Joshua Tenenbaum, a professor of cognitive sciences at the Massachusetts Institute of Technology, who has done researched in this area.
To tackle the trickier challenge presented by intuitive physics, the researchers developed a model called PLATO to focus on whole objects instead of individual pixels.
PLATO, like an infant, exhibited "Surprise" when it, say, viewed an object that moved through another one without ricocheting backward upon impact.
It performed significantly better at distinguishing physically possible versus impossible scenes than a traditional AI system that was trained on the same videos but had not been imbued with an inherent knowledge of objects.
"Psychologists think that people use objects to understand the physical world, so maybe if we build a system like that, we're going to maximize our likelihood of actually understanding the physical world," said Luis Piloto, a research scientist at DeepMind who led the study, during a press conference.
Previous efforts to teach intuitive physics to AI by incorporating varying degrees of built-in or acquired physical knowledge into the system have achieved mixed success.
The new study attempted to obtain an understanding of intuitive physics in the same manner that developmental psychologists think an infant does by first displaying an inborn awareness of what an object is.
The child then learns the physical rules that govern the object's behavior by watching it move about the world.
The model they developed will need substantially more training on objects involved in real-world scenarios before it can be incorporated into AI systems.