Robotic action/observation planning for playing yamakuzushi based on human motion
In this paper, we propose a novel robotic action/observation planning method for playing“ Yamakuzushi ”game which is a Japanese board game selecting one Shogi piece from the randomly stacked pile and sliding it off the board. In our proposed method, we first select one of the pieces from the pile by...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2020-12-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/86/892/86_20-00146/_pdf/-char/en |
| _version_ | 1828125917624401920 |
|---|---|
| author | Tomohiro MOTODA Weiwei WAN Kensuke HARADA |
| author_facet | Tomohiro MOTODA Weiwei WAN Kensuke HARADA |
| author_sort | Tomohiro MOTODA |
| collection | DOAJ |
| description | In this paper, we propose a novel robotic action/observation planning method for playing“ Yamakuzushi ”game which is a Japanese board game selecting one Shogi piece from the randomly stacked pile and sliding it off the board. In our proposed method, we first select one of the pieces from the pile by referring a human operation characteristics. We use the CNN trained by using the depth image of the pile and the result of human operation. To successfully slide the selected piece off the board without making collision with the neighboring pieces, we formulate the action/observation planning based on the partially observable Markov decision process (POMDP). We select the view pose to obtain enough visibility of the pile around the selected piece. After obtaining the visibility, we determine the direction of piece’s motion to avoid the contact with the neighboring objects. The effectiveness of the proposed method is confirmed by experiments. |
| first_indexed | 2024-04-11T15:27:48Z |
| format | Article |
| id | doaj.art-51a127c27cea4163957b22b7f6596a87 |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-04-11T15:27:48Z |
| publishDate | 2020-12-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-51a127c27cea4163957b22b7f6596a872022-12-22T04:16:12ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612020-12-018689220-0014620-0014610.1299/transjsme.20-00146transjsmeRobotic action/observation planning for playing yamakuzushi based on human motionTomohiro MOTODA0Weiwei WAN1Kensuke HARADA2Graduate School of Engineering Science, Osaka UniversityGraduate School of Engineering Science, Osaka UniversityGraduate School of Engineering Science, Osaka UniversityIn this paper, we propose a novel robotic action/observation planning method for playing“ Yamakuzushi ”game which is a Japanese board game selecting one Shogi piece from the randomly stacked pile and sliding it off the board. In our proposed method, we first select one of the pieces from the pile by referring a human operation characteristics. We use the CNN trained by using the depth image of the pile and the result of human operation. To successfully slide the selected piece off the board without making collision with the neighboring pieces, we formulate the action/observation planning based on the partially observable Markov decision process (POMDP). We select the view pose to obtain enough visibility of the pile around the selected piece. After obtaining the visibility, we determine the direction of piece’s motion to avoid the contact with the neighboring objects. The effectiveness of the proposed method is confirmed by experiments.https://www.jstage.jst.go.jp/article/transjsme/86/892/86_20-00146/_pdf/-char/enrobotic manipulationprobabilistic motion planningpomdpcnnyamakuzushi game |
| spellingShingle | Tomohiro MOTODA Weiwei WAN Kensuke HARADA Robotic action/observation planning for playing yamakuzushi based on human motion Nihon Kikai Gakkai ronbunshu robotic manipulation probabilistic motion planning pomdp cnn yamakuzushi game |
| title | Robotic action/observation planning for playing yamakuzushi based on human motion |
| title_full | Robotic action/observation planning for playing yamakuzushi based on human motion |
| title_fullStr | Robotic action/observation planning for playing yamakuzushi based on human motion |
| title_full_unstemmed | Robotic action/observation planning for playing yamakuzushi based on human motion |
| title_short | Robotic action/observation planning for playing yamakuzushi based on human motion |
| title_sort | robotic action observation planning for playing yamakuzushi based on human motion |
| topic | robotic manipulation probabilistic motion planning pomdp cnn yamakuzushi game |
| url | https://www.jstage.jst.go.jp/article/transjsme/86/892/86_20-00146/_pdf/-char/en |
| work_keys_str_mv | AT tomohiromotoda roboticactionobservationplanningforplayingyamakuzushibasedonhumanmotion AT weiweiwan roboticactionobservationplanningforplayingyamakuzushibasedonhumanmotion AT kensukeharada roboticactionobservationplanningforplayingyamakuzushibasedonhumanmotion |