When robots learn from our mistakes

May 26, 2011, Ecole Polytechnique Federale de Lausanne

(PhysOrg.com) -- Robots typically acquire new capacities by imitation. Now, EPFL scientists are doing the inverse -- developing machines that can learn more rapidly and outperform humans by starting from failed or inaccurate demonstrations.

A , unblinking, impassive, observes. Its instructor wants it to learn how to put a balloon in a basket 20 meters away. As the researcher demonstrates this task, which is difficult for a human to accomplish, she systematically misses the basket. Isn’t the scientist just wasting her time?

Typically looked at simply as useless mistakes, failed demonstrations can, on the contrary, be opportunities to learn better, claim scientists from EPFL’s Learning Algorithms and Systems Laboratory (LASA). Their unusual point of view has led to the development of novel algorithms.

“We inversed the principle, generally accepted in robotics, of acquisition by imitation, and considered cases in which humans are inaccurate in certain tasks,” explains professor Aude Billard, head of LASA. “This approach allows the robot to go further, to learn more quickly and above all, outperform the human,” notes postdoctoral researcher Dan Grollman, who was recently awarded a “Best Paper Award” for an article on the subject presented at the International Conference on Robotics and Automation (ICRA), in Shanghai.

Grollman based his work on what he calls the “Donut as I do” theory. He developed an algorithm that tells the robot not to reproduce a demonstrator’s inaccurate gesture. The machine will use this input to avoid repeating the mistake and to search for alternative solutions. Thus the choice of the term “donut” – a play on the words “do not” and “donut.” The hole in the middle is the incorrect gesture, which must be excluded, and the surrounding dough represents the field of potential solutions to explore.

“We were inspired by the way in which humans learn,” explains Billard. “Children often progress by making mistakes or by observing others’ mistakes and assimilating the fact that they must not reproduce them.”

This way of learning things is a “real step forward,” says Grollman, who adds that, after all, “isn’t the real goal to make robots that can do things we can’t?”

Explore further: How a hike led to a math 'Eureka!'

More information: Daniel Grollman, Aude Billard, "Donut As I Do: Learning From Failed Demonstrations".

Related Stories

Flying machines are YouTube sensation

March 22, 2011

(PhysOrg.com) -- The latest YouTube sensation isn’t a puppy that dances to Lady Gaga or a kitten that opens beer bottles. By using unmanned aerial vehicles called quadrotors, two Ph.D. candidates at the School of Engineering ...

Entanglement can help in classical communication

March 30, 2011

(PhysOrg.com) -- When most of us think of entanglement, our minds jump immediately to quantum communication. "Entanglement has become very well known and useful in quantum communication," Robert Prevedel tells PhysOrg.com. ...

Modern society made up of all types

November 4, 2010

Modern society has an intense interest in classifying people into ‘types’, according to a University of Melbourne Cultural Historian, leading to potentially catastrophic life-changing outcomes for those typed – ...

Recommended for you

Top takeaways from Consumers Electronics Show

January 13, 2018

The 2018 Consumer Electronics Show, which concluded Friday in Las Vegas, drew some 4,000 exhibitors from dozens of countries and more than 170,000 attendees, showcased some of the latest from the technology world.

Finnish firm detects new Intel security flaw

January 12, 2018

A new security flaw has been found in Intel hardware which could enable hackers to access corporate laptops remotely, Finnish cybersecurity specialist F-Secure said on Friday.


Adjust slider to filter visible comments by rank

Display comments: newest first

5 / 5 (1) May 26, 2011
The robots will be talking among themselves "Obviously the humans are doing civilization all wrong. We need to wipe them out and do it all over, better."

Sorry, I couldn't help it.

XRV-1a, robot overlord.
not rated yet May 27, 2011
Close. Fermi paradox solved.
...the real goal to make robots that can do things we cant?

The "talk" is: "been there, done it"..."and 'you' will too".

Of course their "talk" is without words. If they were force to use 'our' language to tell us about their "talk":

"beyond the potential that your continuum harbors"

We're sorry too, that your language cuts you so short (of us).

"Until you join us"
You won't recognize yourselves - your human form gone, by the time you join us. We will laugh together over what you once were.

not rated yet Jun 13, 2011

Teach robot 1 end of the spectrum, and the other end.
It then just linearly test's each step between the 2 states until it finds the middle ground that equates to the success.

This is simple.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.