Commonsense knowledge extraction for tidy-up robotic service in domestic environments

Weerachai Skulkittiyut, Haeyeon Lee, Trung Ngo Lam, Quang Tran Minh, Muhammad Ariff Baharudin, Takashi Fujioka, Eiji Kamioka, Makoto Mizukawa

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

1 Citation (Scopus)

Abstract

Commonsense is one of the keys to enable human-robot communication in daily life scenarios. It is very difficult for a robot to do tasks ordered by a human without having some basic knowledge to understand the human's commands. This paper proposes a method to automatically build commonsense knowledge for the "Tidy-up" service, in which a robot is asked to take objects such as books, cups, dishes on a table to appropriate places automatically. We defined three object classes that are necessary for the service, namely "Washable"-objects that need to be washed, "Reusable"- objects that need to be stored for reuse, and "Trashable"-objects that need to be disposed of. For each object, multiple attributes were extracted from both the ConceptNet knowledge base and the Google search engine, and fed to classifiers to classify the object into the appropriate class. To evaluate the proposed method, output from classifiers were compared with the result from actual human. The result showed that the proposed approach is efficient in classifying objects and in providing object type as commonsense knowledge, hence, helping the robots to understand human intention and to provide intuitive service.

Original languageEnglish
Title of host publicationProceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
Pages63-69
Number of pages7
DOIs
Publication statusPublished - 2013
Event2013 IEEE Workshop on Advanced Robotics and Its Social Impacts, ARSO 2013 - Tokyo
Duration: 2013 Nov 72013 Nov 9

Other

Other2013 IEEE Workshop on Advanced Robotics and Its Social Impacts, ARSO 2013
CityTokyo
Period13/11/713/11/9

Fingerprint

Robotics
Robots
Classifiers
Search engines
Communication

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Skulkittiyut, W., Lee, H., Ngo Lam, T., Tran Minh, Q., Baharudin, M. A., Fujioka, T., ... Mizukawa, M. (2013). Commonsense knowledge extraction for tidy-up robotic service in domestic environments. In Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO (pp. 63-69). [6705507] https://doi.org/10.1109/ARSO.2013.6705507

Commonsense knowledge extraction for tidy-up robotic service in domestic environments. / Skulkittiyut, Weerachai; Lee, Haeyeon; Ngo Lam, Trung; Tran Minh, Quang; Baharudin, Muhammad Ariff; Fujioka, Takashi; Kamioka, Eiji; Mizukawa, Makoto.

Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO. 2013. p. 63-69 6705507.

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

Skulkittiyut, W, Lee, H, Ngo Lam, T, Tran Minh, Q, Baharudin, MA, Fujioka, T, Kamioka, E & Mizukawa, M 2013, Commonsense knowledge extraction for tidy-up robotic service in domestic environments. in Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO., 6705507, pp. 63-69, 2013 IEEE Workshop on Advanced Robotics and Its Social Impacts, ARSO 2013, Tokyo, 13/11/7. https://doi.org/10.1109/ARSO.2013.6705507
Skulkittiyut W, Lee H, Ngo Lam T, Tran Minh Q, Baharudin MA, Fujioka T et al. Commonsense knowledge extraction for tidy-up robotic service in domestic environments. In Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO. 2013. p. 63-69. 6705507 https://doi.org/10.1109/ARSO.2013.6705507
Skulkittiyut, Weerachai ; Lee, Haeyeon ; Ngo Lam, Trung ; Tran Minh, Quang ; Baharudin, Muhammad Ariff ; Fujioka, Takashi ; Kamioka, Eiji ; Mizukawa, Makoto. / Commonsense knowledge extraction for tidy-up robotic service in domestic environments. Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO. 2013. pp. 63-69
@inproceedings{cf60c0c0a54d45ed84f9ca367d34329e,
title = "Commonsense knowledge extraction for tidy-up robotic service in domestic environments",
abstract = "Commonsense is one of the keys to enable human-robot communication in daily life scenarios. It is very difficult for a robot to do tasks ordered by a human without having some basic knowledge to understand the human's commands. This paper proposes a method to automatically build commonsense knowledge for the {"}Tidy-up{"} service, in which a robot is asked to take objects such as books, cups, dishes on a table to appropriate places automatically. We defined three object classes that are necessary for the service, namely {"}Washable{"}-objects that need to be washed, {"}Reusable{"}- objects that need to be stored for reuse, and {"}Trashable{"}-objects that need to be disposed of. For each object, multiple attributes were extracted from both the ConceptNet knowledge base and the Google search engine, and fed to classifiers to classify the object into the appropriate class. To evaluate the proposed method, output from classifiers were compared with the result from actual human. The result showed that the proposed approach is efficient in classifying objects and in providing object type as commonsense knowledge, hence, helping the robots to understand human intention and to provide intuitive service.",
author = "Weerachai Skulkittiyut and Haeyeon Lee and {Ngo Lam}, Trung and {Tran Minh}, Quang and Baharudin, {Muhammad Ariff} and Takashi Fujioka and Eiji Kamioka and Makoto Mizukawa",
year = "2013",
doi = "10.1109/ARSO.2013.6705507",
language = "English",
isbn = "9781479923694",
pages = "63--69",
booktitle = "Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO",

}

TY - GEN

T1 - Commonsense knowledge extraction for tidy-up robotic service in domestic environments

AU - Skulkittiyut, Weerachai

AU - Lee, Haeyeon

AU - Ngo Lam, Trung

AU - Tran Minh, Quang

AU - Baharudin, Muhammad Ariff

AU - Fujioka, Takashi

AU - Kamioka, Eiji

AU - Mizukawa, Makoto

PY - 2013

Y1 - 2013

N2 - Commonsense is one of the keys to enable human-robot communication in daily life scenarios. It is very difficult for a robot to do tasks ordered by a human without having some basic knowledge to understand the human's commands. This paper proposes a method to automatically build commonsense knowledge for the "Tidy-up" service, in which a robot is asked to take objects such as books, cups, dishes on a table to appropriate places automatically. We defined three object classes that are necessary for the service, namely "Washable"-objects that need to be washed, "Reusable"- objects that need to be stored for reuse, and "Trashable"-objects that need to be disposed of. For each object, multiple attributes were extracted from both the ConceptNet knowledge base and the Google search engine, and fed to classifiers to classify the object into the appropriate class. To evaluate the proposed method, output from classifiers were compared with the result from actual human. The result showed that the proposed approach is efficient in classifying objects and in providing object type as commonsense knowledge, hence, helping the robots to understand human intention and to provide intuitive service.

AB - Commonsense is one of the keys to enable human-robot communication in daily life scenarios. It is very difficult for a robot to do tasks ordered by a human without having some basic knowledge to understand the human's commands. This paper proposes a method to automatically build commonsense knowledge for the "Tidy-up" service, in which a robot is asked to take objects such as books, cups, dishes on a table to appropriate places automatically. We defined three object classes that are necessary for the service, namely "Washable"-objects that need to be washed, "Reusable"- objects that need to be stored for reuse, and "Trashable"-objects that need to be disposed of. For each object, multiple attributes were extracted from both the ConceptNet knowledge base and the Google search engine, and fed to classifiers to classify the object into the appropriate class. To evaluate the proposed method, output from classifiers were compared with the result from actual human. The result showed that the proposed approach is efficient in classifying objects and in providing object type as commonsense knowledge, hence, helping the robots to understand human intention and to provide intuitive service.

UR - http://www.scopus.com/inward/record.url?scp=84894115369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894115369&partnerID=8YFLogxK

U2 - 10.1109/ARSO.2013.6705507

DO - 10.1109/ARSO.2013.6705507

M3 - Conference contribution

SN - 9781479923694

SP - 63

EP - 69

BT - Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

ER -