JSME-JT

Size: px

Start display at page:

Download "JSME-JT"

えいしろうしもかさ
5 years ago
Views:

1 Bulletin of the JSME 日本機械学会論文集 Transactions of the JSME (in Japanese) Vol.80, No.819, 2014 Unconscious gestures that empower turn taking for telepresence robot Komei HASEGAWA *1 and Yasushi NAKAUCHI *2 *1 Graduate School of Systems and Information Engineering, University of Tsukuba Tennodai, Tsukuba, Ibaraki , Japan *2 Faculty of Engineering, Information and Systems, University of Tsukuba Tennodai, Tsukuba, Ibaraki , Japan Received 2 July 2014 *1 *2 Abstract In this research, we propose a telepresence robot that avoids speech collisions occurs in remote conversations. In face-to-face conversations, humans predict the next speaker by seeing others gestures. However, it is difficult to predict it at 2D video chat situations. The failure of prediction causes speech collisions and awkward conversations. To solve the problem, we propose the telepresence robot that conveys 3D spontaneous gestures. The proposed system employs Kinect as a gesture input device and conveys unconscious gestures to telepresence robot. We conducted experiments with subjects and confirmed the efficiency of the proposed system. Key words : Telepresence robots, Gestures, Multi-party conversations, Turn taking, Nonverbal cues 1 1 Web Web 300 ms ( 1981) Web 30 ( 2009) ( 2011) Web 3 (Vargas 1986) No *1 筑波大学大学院システム情報工学研究科 ( 茨城県つくば市天王台 1-1-1) *2 正員, 筑波大学システム情報系 of corresponding author: komei@hri.iit.tsukuba.ac.jp 1

2 (Vargas 1986) (Mehrabian 1972) Marjorie (Vargas 1986) ( 2011) Paulos PRoP (Paulos and Canny 2001) Anybots QB PRoP (Anybots 2014) InTouchTechnologies RP-7 (InTouch Technologies 2014) ( 2010) ( 2008) 4 3 ReplieeQ2( 2007) Geminoid(Matsui et al. 2005) Robovie-M 29cm (Shimoi et al. 2006) (Nabe et al. 2006) Robovie-M 2

3 22 ( 2011) Kinect V-Sido Adalgeirsson MeBot (Adalgeirsson and Breazeal 2010) MeBot 3 MeBot MeBot MeBot MeBot 1 1 MeBot MeBot Cassell (Cassell et al. 1999) 3

4 Fig. 1 Research concept 1 2 Web PC PC SkypeAPI PC Web Web Skype PC PC 3 KHR-3HV

5 Fig. 2 System configuration Fig. 3 Telepresence robot Microsoft Kinect Kinect KinectforWindowsSDK 3 Kinect Kinect Kinect Kinect 3 3 Web SeeingMachines faceapi faceapi Web 3 (x y z ) 3 ( ) faceapi 3 ( ) 1:1 faceapi -30 ~30-20 ~45-90 ~90-70 ~70-15 ~30-65 ~65 MeBot faceapi 5

6 KHR-3HV 300ms ( 1981) 100ms 600ms 500ms ( 2011) 1s 3s A B C 1 3 A B C 3 A B C

of total Standard Deviation turns per session Proposed method 40.

7 Fig. 5 Number of conscious gestures of robot Fig. 4 Experimental environment Table 1 Average numbers of turn taking Average of total Standard Deviation turns per session Proposed method Existing method Face-to-face Fig. 6 Number of unconscious gestures of robot 1: 2: 7

8 Fig. 7 Ratio of turn taking Fig. 8 Number of speech collisions 7 ( 21 ) Mann-Whitney U 5% % 3 Bonferroni t 1% 5% Kruskal-Wallis 5% 3 Bonferroni Mann-Whitney U 5% 8

9 ( 2009) Web 2 3 9

10 ( 2011) ( 2009) 3 10

11 Adalgeirsson, S.O. and Breazeal, C., MeBot: a robotic platform for socially embodied telepresence, Proceedings of Human-Robot Interaction 2010 (HRI2010) (2010), pp Anybots, QB (online), available from < ( ). Cassell, J., McNeill, D. and McCullough, K.E., Speech-gesture mismatches: evidence for one underlying representation of linguistic and nonlinguistic information, Pragmatics and Cognition, Vol.7, No.1 (1999), pp.1-33.,,, 08 (2008), 2A1-B21. InTouch Technologies, Inc., RP-7 (online), available from < ( ).,, (2007).,,,, -?-,, Vol.108, No.487 (2009), pp Matsui, D., Minato, T., MacDorman, K. F. and Ishiguro, H., Generating natural motion in an android by mapping human motion, Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems (2005), pp Mehrabian, A., Nonverbal communication, Aldine-Atherton (1972). Nabe, S., Kanda, T., Hiraki, K., Ishiguro, H., Kogure, K. and Hagita, N., Analysis of human behavior to a communication robot in an open field, Proceedings of Human-Robot Interaction 2006 (HRI2006) (2006), pp Paulos, E. and Canny, J., Social Tele-embodiment: Understanding presence, Autonomous Robots, Vol.11, No.1 (2001), pp Shimoi, M., Kanda, T., Ishiguro, H. and Hagita, N., Interactive humanoid robots for a science museum, Proceedings of Human-Robot Interaction 2006 (HRI2006) (2006), pp ,,,,,, Vol.51, No.1 (2010), pp ,,,, Web, VMA, Vol.29 (2011), pp.9-18.,,,, Web, IEICE Technical Report MVE2009 (2009), pp Vargas, M.F., Louder than words: an introduction to nonverbal communication, Iowa State University Press (1986).,,,,, B, Vol.64, No.11 (1981), pp ,, Kinect, 11 (2011), 2P2-L05. Adalgeirsson, S.O. and Breazeal, C., MeBot: a robotic platform for socially embodied telepresence, Proceedings of Human-Robot Interaction 2010 (HRI2010) (2010), pp

12 Anybots, QB (online), available from < (accessed on 30 June, 2014). Cassell, J., McNeill, D. and McCullough, K.E., Speech-gesture mismatches: evidence for one underlying representation of linguistic and nonlinguistic information, Pragmatics and Cognition, Vol.7, No.1 (1999), pp Inoue, N. and Tsumaki, Y., Development of a wearable miniature humanoid robot, Proceeding of the 2008 JSME Conference on Robotics and Mechatronics Conference (ROBOMECH 2008) (2008), 2A1-B21 (in Japanese). InTouch Technologies, Inc., RP-7 (online), available from < (accessed on 30 June, 2014). Ishiguro, H., Android science robotics research for human understanding, Mainichi communications (2007) (in Japanese). Katayama, T., Mukawa, N., Tokunaga, H. and Yuasa, M., Analysis of speaker's gestures and conversational activity in multiparty video-mediated communication: how does the quality of conversations change in correct and imaginary mutual gaze environments?, IEICE Technical Report, Vol.108, No.487 (2009), pp (in Japanese). Matsui, D., Minato, T., MacDorman, K. F. and Ishiguro, H., Generating natural motion in an android by mapping human motion, Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems (2005), pp Mehrabian, A., Nonverbal communication, Aldine-Atherton (1972). Nabe, S., Kanda, T., Hiraki, K., Ishiguro, H., Kogure, K. and Hagita, N., Analysis of human behavior to a communication robot in an open field, Proceedings of Human-Robot Interaction 2006 (HRI2006) (2006), pp Paulos, E. and Canny, J., Social Tele-embodiment: Understanding presence, Autonomous Robots, Vol.11, No.1 (2001), pp Shimoi, M., Kanda, T., Ishiguro, H. and Hagita, N., Interactive humanoid robots for a science museum, Proceedings of Human-Robot Interaction 2006 (HRI2006) (2006), pp Suzuki, Y., Fukushima, H., Fukasawa, S. and Takeuchi, K., Can robot-movement draw person s attention better than pan-tilt camera movement?, Transactions of Information Processing Society of Japan, Vol.51, No.1 (2010), pp (in Japanese). Tamaki, H., Higashino, S., Kobayashi, M. and Ihara, M., Smooth turn-taking in web conferences, Proceedings of The Institute of Image Electronics Engineers of Japan VMA research society, Vol.29 (2011), pp.9-18 (in Japanese). Tamaki, H., Nakashige, M., Higashino, S. and Kobayashi, M., Facilitation method in web conference focused on communication rhythm, IEICE Technical Report MVE2009 (2009), pp (in Japanese). Vargas, M.F., Louder than words: an introduction to nonverbal communication, Iowa State University Press (1986). Yoroizawa, I., Takikawa, K., Okubo, S. and Watanabe, Y., Subjective effects of talker echo and transmission delay in video conferencing via communication satellite, The IEICE Transactions on Communications (Japanese Edition), Vol.64, No.11 (1981), pp (in Japanese). Yoshizaki, W. and Kagami, S., Full body control of the humanoid robot by kinect, Proceedings of the 2011 JSME Conference on Robotics and Mechatronics (ROBOMECH 2011) (2011), 2P2-L05 (in Japanese). 12

12_26.dvi

12_26.dvi Vol. 48 No. 12 Dec. 2007 WSCS Generation of Spatial Distance ( Maai ) by Emergence of Co-existing Feeling and Expression of Rhythm Shiroh Itai and Yoshiyuki Miwa We have investigated the generation of