Robots learn to complete tasks by watching ‘how-to’ videos

YouTube offers 1,80,000 videos on “How to make an omelette” and 2,81,000 on

“How to tie a bowtie.” Photo used for representative purposes only.
The researchers at the Cornell University in New York call their project "RoboWatch."

Scientists are teaching robots to watch how-to videos and derive a series of step-by-step instructions
to perform a task, an advance that may help future ‘personal robots’ to do everyday housework
such as cooking and washing dishes.

The researchers at the Cornell University in New York call their project “RoboWatch.”

There is a common underlying structure to most how—to videos and there is plenty of
source material available, researchers said.

YouTube offers 1,80,000 videos on “How to make an omelette” and 2,81,000 on “How to tie a bowtie.”

By scanning multiple videos on the same task, a computer can find what they all have in
common and reduce that to simple step-by-step instructions in natural language.

People post all these videos “to help people or maybe just to show off,” said graduate student Ozan Sener, lead author of a paper on the method presented at the International Conference on
Computer Vision in Chile.

The work is aimed at a future when we may have “personal robots” to perform everyday
housework — cooking, washing dishes, doing the laundry, feeding the cat — as well as to
assist the elderly and people with disabilities, researchers said. A key feature of the system
is that it is “unsupervised,” said Sener who collaborated with colleagues at Stanford University.

In most previous work, robot learning is accomplished by having a human explain
what the robot is observing.