抄録
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.
元の言語 | English |
---|---|
ホスト出版物のタイトル | Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO |
ページ | 63-69 |
ページ数 | 7 |
DOI | |
出版物ステータス | Published - 2013 |
イベント | 2013 IEEE Workshop on Advanced Robotics and Its Social Impacts, ARSO 2013 - Tokyo 継続期間: 2013 11 7 → 2013 11 9 |
Other
Other | 2013 IEEE Workshop on Advanced Robotics and Its Social Impacts, ARSO 2013 |
---|---|
市 | Tokyo |
期間 | 13/11/7 → 13/11/9 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
これを引用
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.研究成果: Conference contribution
}
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
AN - SCOPUS:84894115369
SN - 9781479923694
SP - 63
EP - 69
BT - Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
ER -