MIT Technology Review October 19, 2021
They show how intelligence and body plans are closely linked—and could unlock AI for robots.
An endless variety of virtual creatures scamper and scuttle across the screen, struggling over obstacles or dragging balls toward a target. They look like half-formed crabs made of sausages—or perhaps Thing, the disembodied hand from The Addams Family. But these “unimals” (short for “universal animals”) could in fact help researchers develop more general-purpose intelligence in machines.
Agrim Gupta of Stanford University and his colleagues (including Fei-Fei Li, who co-directs the Stanford Artificial Intelligence Lab and led the creation of ImageNet) used these unimals to explore two questions that often get overlooked in AI research: how intelligence is tied to the way bodies are laid out,...
Today's Sponsors
Today's Sponsor