Learning of object identification by robots commanded by natural language

Chandimal Jayawardena; Keigo Watanabe; Kiyotaka Izumi

Learning of object identification by robots commanded by natural language

Chandimal Jayawardena, Keigo Watanabe, Kiyotaka Izumi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Natural language communication is very important in Human-Robot cooperative systems. As a part of natural language communication, learning to identify natural language references such as "small red cube" is very useful. This paper proposes a method of learning object identification in which the meanings of references such as above can be inferred. The proposed method is demonstrated with an experiment conducted with a PA-10 redundant manipulator and a set of objects. The robot manipulator is issued commands like "pick the big red cube" to identify and pick objects placed on a table. The robot learns to interpret the meaning of this type of natural commands by learning individual lexical symbols in the vocabulary and their corresponding object features.

Original language	English
Title of host publication	Intelligent Autonomous Systems 9, IAS 2006
Pages	913-920
Number of pages	8
Publication status	Published - Dec 1 2006
Externally published	Yes
Event	9th International Conference on Intelligent Autonomous Systems, IAS 2006 - Tokyo, Japan Duration: Mar 7 2006 → Mar 9 2006

Publication series

Name	Intelligent Autonomous Systems 9, IAS 2006

Other

Other	9th International Conference on Intelligent Autonomous Systems, IAS 2006
Country/Territory	Japan
City	Tokyo
Period	3/7/06 → 3/9/06

Keywords

Lexical symbols
Natural language commands
Object features
Object identification

ASJC Scopus subject areas

Computer Science(all)
Computational Mechanics
Control and Systems Engineering

Cite this

@inproceedings{45fc6f104c1a4380847d5d61f50dea95,

title = "Learning of object identification by robots commanded by natural language",

abstract = "Natural language communication is very important in Human-Robot cooperative systems. As a part of natural language communication, learning to identify natural language references such as {"}small red cube{"} is very useful. This paper proposes a method of learning object identification in which the meanings of references such as above can be inferred. The proposed method is demonstrated with an experiment conducted with a PA-10 redundant manipulator and a set of objects. The robot manipulator is issued commands like {"}pick the big red cube{"} to identify and pick objects placed on a table. The robot learns to interpret the meaning of this type of natural commands by learning individual lexical symbols in the vocabulary and their corresponding object features.",

keywords = "Lexical symbols, Natural language commands, Object features, Object identification",

author = "Chandimal Jayawardena and Keigo Watanabe and Kiyotaka Izumi",

year = "2006",

month = dec,

day = "1",

language = "English",

isbn = "1586035959",

series = "Intelligent Autonomous Systems 9, IAS 2006",

pages = "913--920",

booktitle = "Intelligent Autonomous Systems 9, IAS 2006",

note = "9th International Conference on Intelligent Autonomous Systems, IAS 2006 ; Conference date: 07-03-2006 Through 09-03-2006",

}

TY - GEN

T1 - Learning of object identification by robots commanded by natural language

AU - Jayawardena, Chandimal

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Natural language communication is very important in Human-Robot cooperative systems. As a part of natural language communication, learning to identify natural language references such as "small red cube" is very useful. This paper proposes a method of learning object identification in which the meanings of references such as above can be inferred. The proposed method is demonstrated with an experiment conducted with a PA-10 redundant manipulator and a set of objects. The robot manipulator is issued commands like "pick the big red cube" to identify and pick objects placed on a table. The robot learns to interpret the meaning of this type of natural commands by learning individual lexical symbols in the vocabulary and their corresponding object features.

AB - Natural language communication is very important in Human-Robot cooperative systems. As a part of natural language communication, learning to identify natural language references such as "small red cube" is very useful. This paper proposes a method of learning object identification in which the meanings of references such as above can be inferred. The proposed method is demonstrated with an experiment conducted with a PA-10 redundant manipulator and a set of objects. The robot manipulator is issued commands like "pick the big red cube" to identify and pick objects placed on a table. The robot learns to interpret the meaning of this type of natural commands by learning individual lexical symbols in the vocabulary and their corresponding object features.

KW - Lexical symbols

KW - Natural language commands

KW - Object features

KW - Object identification

UR - http://www.scopus.com/inward/record.url?scp=58149095565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149095565&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:58149095565

SN - 1586035959

SN - 9781586035952

T3 - Intelligent Autonomous Systems 9, IAS 2006

SP - 913

EP - 920

BT - Intelligent Autonomous Systems 9, IAS 2006

T2 - 9th International Conference on Intelligent Autonomous Systems, IAS 2006

Y2 - 7 March 2006 through 9 March 2006

ER -

Learning of object identification by robots commanded by natural language

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this