Learning from Animal and Human Videos
Abstract:
Animals and humans can learn from the billions of years of life on Earth and the evoluNon that has
shaped it. If robots can borrow from that wealth of experience, they too could be enabled to learn from
the experience, instead of learning through brute force trial-and-error. Learning from internet-scale
videos, such as the RGB videos on YouTube, would serve as an especially promising method; humans
view the world through the visible light spectrum. Robots using a similar band would interface through
the world, a world designed by and shaped for humans, and could be especially valuable by interfacing
through common visual language.
Committee:
Abhinav Gupta (chair)
Shubham Tulsiani
Homanga Bharadhwaj