Communications of the ACM
Robots Learn to Take a Proper Handoff By Following Digitized Human Examples
A new method with which a humanoid robot can receive an object handed to it by a human uses a database of motion-capture data that allows the robot to recognize the gesture.
Credit: Sandia National Laboratory
Researchers at Disney Research, Carnegie Mellon University, and the Karlsruhe Institute of Technology have developed a method that allows a humanoid robot to receive an object handed to it by a person with something similar to natural, human-like motion.
The researchers used motion-capture data with two people to create a database of human motion. The robot quickly searches the database and recognizes what the person is doing to make a reasonable estimate of where the person is likely to extend their hand.
However, the researchers say it is not enough to develop a technique that enables the robot to efficiently find and grasp the object. "If a robot just sticks out its hand blindly, or uses motions that look more robotic than human, a person might feel uneasy working with that robot or might question whether it is up to the task," says Disney's Katsu Yamane.
The researchers developed a hierarchical data structure that enables a robot to access a library of human-to-human passing motions with the speed necessary for robot-human interaction.
Yamane says additional work is necessary to expand the database for a wider variety of passing motions and distances.
From Disney Research
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found