Robot programming through demonstration: Building Ikea furniture

During his internship at Willow Garage, Scott Niekum from the University of Massachusetts Amherst developed a learning from demonstration system that allows users to show the PR2 how to perform complex, multi-step tasks, which the robot can then generalize to new situations.  Our main test application was the autonomous assembly of simple IKEA furniture.

First, the user provides several kinesthetic demonstrations of the task in various situations, demonstrations in which the user physically moves the arms of the robot to complete the task.  A series of algorithms are then used to discover repeated structure across the demonstraions, resulting in the creation of reusable skills that can be used to reproduce the task.

The robot is then able to sequence these skills in an intelligent, adaptive way by using classifiers learned from the demonstration data.  If the robot happens to make a mistake during execution of the task, the user can stop the robot at any time and provide an interactive correction, showing the robot how to fix the mistake.  This information is then integrated into the robot's knowledge base, so that it can deal with similar situations in the future.

For more informaton see:

Scott Niekum, Sachin Chitta, Andrew Barto, Bhaskara Marthi, Sarah Osentoski,  Incremental Semantically Grounded Learning from Demonstration. Robotics: Science and Systems 9, June 2013. 

For more information please visit:

 

http://www.ros.org/wiki/ar_track_alvar

http://www.ros.org/wiki/dmp

http://www.ros.org/wiki/ml_classifiers