A framework for cognitive robots to learn behaviors through imitation and interaction with humans

Author

Tan, Huan ; Du, Qian ; Wu, Na

Author_Institution

Electr. Eng. & Comput. Sci. Dept., Vanderbilt Univ., Nashville, TN, USA

fYear

2012

fDate

6-8 March 2012

Firstpage

235

Lastpage

238

Abstract

This paper proposes a general learning framework for robots to learn behaviors through imitation and interaction. A modified codebook based method is used for robots to segment and recognize new objects in the environment. Task related semantic information is learned by robots through the speech communication with humans. Dynamic Movement Primitive method is used to generate similar behaviors to complete similar but slightly different tasks. Experimental results are given to verify the effectiveness of this framework.

Keywords

cognitive systems; human-robot interaction; intelligent robots; learning (artificial intelligence); mobile robots; object recognition; robot vision; behavior learning framework; codebook based method; cognitive robots; dynamic movement primitive method; human-robot interaction; imitation learning; object recognition; object segmentation; speech communication; task related semantic information; Cognitive robotics; Humanoid robots; Humans; Learning systems; Semantics; USA Councils; Imitation learning; Interaction; Segmentation; Semantic Learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Cognitive Methods in Situation Awareness and Decision Support (CogSIMA), 2012 IEEE International Multi-Disciplinary Conference on

Conference_Location

New Orleans, LA

Print_ISBN

978-1-4673-0343-9

Type

conf

DOI

10.1109/CogSIMA.2012.6188390

Filename

6188390