Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

28

ICRA
2007
IEEE

favoriteEmaildiscussreport

134views Robotics» more ICRA 2007»

Towards a Real-Time Bayesian Imitation System for a Humanoid Robot

14 years 5 months ago

Towards a Real-Time Bayesian Imitation System for a Humanoid Robot

Download www.cs.washington.edu

Abstract— Imitation learning, or programming by demonstration (PbD), holds the promise of allowing robots to acquire skills from humans with domain-speciﬁc knowledge, who nonetheless are inexperienced at programming robots. We have prototyped a real-time, closed-loop system for teaching a humanoid robot to interact with objects in its environment. The system uses nonparametric Bayesian inference to determine an optimal action given a conﬁguration of objects in the world and a desired future conﬁguration. We describe our prototype implementation, show imitation of simple motor acts on a humanoid robot, and discuss extensions to the system.

Aaron P. Shon, Joshua J. Storz, Rajesh P. N. Rao

Real-time Traffic

Humanoid Robot | ICRA 2007 | Nonparametric Bayesian Inference | Robotics | Simple Motor Acts |

claim paper

Related Content

» Task Space Behavior Learning for Humanoid Robots using Gaussian Mixture Models

» Tasklevel imitation learning using variancebased movement optimization

» Movement Imitation with Nonlinear Dynamical Systems in Humanoid Robots

» Modeling affordances using Bayesian networks

» VisionBased Walking Parameter Estimation for Biped Locomotion Imitation

» Using Bayesian Dynamical Systems for Motion Template Libraries

» HumanCentered Robotics and Interactive Haptic Simulation

Post Info
More Details (n/a)

Added	03 Jun 2010
Updated	03 Jun 2010
Type	Conference
Year	2007
Where	ICRA
Authors	Aaron P. Shon, Joshua J. Storz, Rajesh P. N. Rao

Comments (0)