Incremental Learning of Gestures by Imitation in a Humanoid

This video shows how a humanoid robot can learn incrementally new
skills by interacting with a human instructor. By using active
teaching methods that puts the human teacher "in the loop" of the
robot's learning, this video shows that a skill can be efficiently
transferred by interacting socially with the robot. In a first
phase, the robot observes the user demonstrating how to lift a
foam dice while wearing motion sensors. The motion of his/her two
arms and head are recorded by the robot and encoded
probabilistically in a Gaussian Mixture Model. The robot then
tries to reproduce the skill while the user observes the imitation
attempt. Due to the different embodiment between the robot and the
user, the robot first fails at reproducing correctly the task. In
a second phase, the user helps the robot refine its skill by
kinesthetic teaching, i.e. by grabbing and moving its arms
throughout the task to provide the appropriate scaffolds. The
model of the skill is then updated by an incremental
Expectation-Maximization learning algorithm. After three
demonstrations, the robot finally reproduces perfectly the skill
on its own.

Category:

Entertainment

Tags:

• humanoid
• robot
• interaction
• learning
• imitation
• teaching

[AtheriasLeader]

this is so cool.

isn't that the same robot that they tried to teach how to make an omelet?

[sylvaincalinon]

Yes it is! It's also the one which is drawing portraits (Salvador DaBot the portraitist robot).

[ByteBin]

I have an RoboSapien RS Media from WowWee that has a "puppet mode" where you can move it's arms, legs, etc. and then the robot plays it back.

[AtheriasLeader]

this is so cool, the whole concept gets me excited!

[DanielleT01]

I, for one, welcome our new robot overlords.

[deadbeatprodux]

its the rise of the machines!!!!

[GalilxG3]

woah!

[OghamTheBold]

Hope it was getting environmental feedback - otherwise you might as well build a CNC lathe