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

Author

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

Author_Institution

Dept. of Comput. Sci. & Eng., Washington Univ., Seattle, WA

fYear

2007

fDate

10-14 April 2007

Firstpage

2847

Lastpage

2852

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

Keywords

Bayes methods; closed loop systems; humanoid robots; knowledge acquisition; learning by example; nonparametric statistics; Bayesian imitation system; closed-loop system; domain-specific knowledge; humanoid robot; imitation learning; nonparametric Bayesian inference; programming by demonstration; skill acquisition; Automatic programming; Bayesian methods; Computer architecture; Encoding; Hidden Markov models; Humanoid robots; Humans; Prototypes; Real time systems; Robot programming;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2007 IEEE International Conference on

Conference_Location

Roma

ISSN

1050-4729

Print_ISBN

1-4244-0601-3

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ROBOT.2007.363903

Filename

4209521