Approximate decision making by natural language commands for robots

Keigo Watanabe, Chandimal Jayawardena, Kiyotaka Izumi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages4480-4485
Number of pages6
DOIs
Publication statusPublished - 2006
Externally publishedYes
EventIECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics - Paris, France
Duration: Nov 6 2006Nov 10 2006

Other

OtherIECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics
CountryFrance
CityParis
Period11/6/0611/10/06

Fingerprint

Decision making
Robots
Robotics
Manipulators
Neural networks
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Watanabe, K., Jayawardena, C., & Izumi, K. (2006). Approximate decision making by natural language commands for robots. In IECON Proceedings (Industrial Electronics Conference) (pp. 4480-4485). [4153761] https://doi.org/10.1109/IECON.2006.347974

Approximate decision making by natural language commands for robots. / Watanabe, Keigo; Jayawardena, Chandimal; Izumi, Kiyotaka.

IECON Proceedings (Industrial Electronics Conference). 2006. p. 4480-4485 4153761.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Watanabe, K, Jayawardena, C & Izumi, K 2006, Approximate decision making by natural language commands for robots. in IECON Proceedings (Industrial Electronics Conference)., 4153761, pp. 4480-4485, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, Paris, France, 11/6/06. https://doi.org/10.1109/IECON.2006.347974
Watanabe K, Jayawardena C, Izumi K. Approximate decision making by natural language commands for robots. In IECON Proceedings (Industrial Electronics Conference). 2006. p. 4480-4485. 4153761 https://doi.org/10.1109/IECON.2006.347974
Watanabe, Keigo ; Jayawardena, Chandimal ; Izumi, Kiyotaka. / Approximate decision making by natural language commands for robots. IECON Proceedings (Industrial Electronics Conference). 2006. pp. 4480-4485
@inproceedings{c51187f72670428384a5715ef880010d,
title = "Approximate decision making by natural language commands for robots",
abstract = "Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used.",
author = "Keigo Watanabe and Chandimal Jayawardena and Kiyotaka Izumi",
year = "2006",
doi = "10.1109/IECON.2006.347974",
language = "English",
isbn = "1424401364",
pages = "4480--4485",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",

}

TY - GEN

T1 - Approximate decision making by natural language commands for robots

AU - Watanabe, Keigo

AU - Jayawardena, Chandimal

AU - Izumi, Kiyotaka

PY - 2006

Y1 - 2006

N2 - Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used.

AB - Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used.

UR - http://www.scopus.com/inward/record.url?scp=50249138349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249138349&partnerID=8YFLogxK

U2 - 10.1109/IECON.2006.347974

DO - 10.1109/IECON.2006.347974

M3 - Conference contribution

SN - 1424401364

SN - 9781424401369

SP - 4480

EP - 4485

BT - IECON Proceedings (Industrial Electronics Conference)

ER -