Development of Remote Class Support System and Field Trial using
Download
Report
Transcript Development of Remote Class Support System and Field Trial using
Development of Remote Class
Support System and Field Trial
using an Android Robot
學號:M9920214
學生:高啟瑋
指導教授:許毅然
1
Outline
Abstract
Introduction
Android Robot SAYA
Remote Class Suport System
Field Trial Elementary School and
Evaluation
Conclusion
2
Abstract
Android robots that have a human-like
appearance have been developed recently.
The purpose of android robots is to
realize natural communication between
human and robot by implementing
human-like behaviors.
3
Introduction(1)
Since robots might come to be our
partners in the near future, the robot that
could be a test bed and platform to
investigate what kind of mechanisms.
intelligence and functions they should
possess for effective communication with
human beings.
4
Introduction(2)
Currently many kinds of communication
robots that act and interact with human
in our daily lives have been developed
actively.
For example, pet type robot AIBO which
acts in life space were commercialized
and had tongues wagging several years
ago.
5
Fig.1 Android Robot SAYA
6
Introduction(3)
In humanoid-type robot researches, bodily
motions like gestures, nodding , eyedirection, facial expressions .
On are used actively as non-verbal
behavior for realizing natural
communication with human beings.
7
Introduction(4)
We propose remote class support system
because of the practical point of an
android robot.
In this paper, we verify that
communication ability and influence of
android robot on children by conducting
experiment in an elementary school.
8
II. ANDROID ROBOT SAYA(1)
Anthropomorphic face robots that can
express human-like facial expressions
have been developed.
In face-to face communication, facial
expressions are said to play an important
role as non-verbal communication.
9
ANDROID ROBOT SAYA(2)
In order to generate human-like facial
expressions , we referred to FACS (Facial
Action Coding System),19 control points
on the face are selected according to
FACS.
Combining movements of these control
points, various facial expressions are
realized with the face robot similar to
human beings.
10
Fig. 2 Examples of SAYA's facial expressions
11
ANDROID ROBOT SAYA(3)
Since the android robot SAYA equips the
face robot on a mannequin body as a
head part, it looks like a real human as
shown in Fig. 1 .
We applied the android robot SAYA to
the reception in our university entrance
by implementing voice conversation
system.
12
III. REMOTE CLASS SUPPORT
SYSTEM(1)
We developed remote class support
system with the android robot mentioned
above as a roll of a teacher. The detailed
system structure is shown in Fig. 5.
Images from CCD camera that is
mounted in the left side eye ball are
transmitted to "Operation PC".
13
Fig. 5 System configuration
14
REMOTE CLASS SUPPORT SYSTEM(2)
The operator can see class room in the
robot's view point by replaying these
images. The operator also can move the
view point of the android robot by
controlling its eyes and head direction.
Thus, the operator is able to get overview
of the class room and also bring android's
eye direction to specific child.
15
REMOTE CLASS SUPPORT SYSTEM(3)
Moreover a video camera and a
microphone are arranged at rearward to
obtain overview and sounds of the class
room.
The operator controls the robot's
behaviors with the use of these videos
and sounds.
16
REMOTE CLASS SUPPORT SYSTEM(4)
Commands from "Operation PC" are
delivered to "Control PC" through the
network. "Control PC" execute robot's
behaviors based on received commands.
17
IV. FIELD TRIAL AT ELEMENTARY
SCHOOL AND EVALUATION(1)
We put the android robot or the speaker
in front of the class room as a roll of a
teacher.
These systems have functions to explain
tasks of seatwork and to indicate to child
with recorded voice, and they are able to
call child's name.
18
FIELD TRIAL AT ELEMENTARY
SCHOOL AND EVALUATION(2)
Furthermore the system with the android
robot can make an eye contact with
certain child and express facial
expressions (i.e. surprise, fear, disgust,
anger, happiness, sadness) corresponding
to its utterance.
19
Experimental environment in each
condition.
20
Overview of experiment in the
elementary school
21
Evaluation method
(1) Did you concentrate in the seatwork ?
(2) Did you feel nervous ?
(3) Did you feel something is wrong in the
experiment ?
(4) Was the explanation of the seat work
easy to understand?
(5) Were you involved in the class joyfully ?
(6) Do you want to participate again ?
22
In addition, we also asked children to
comment on the class casually. In order to
compare differences quantitatively
between these systems.
We measured sound pressure level in the
class room as shown in Fig. 6 for 15
seconds before and after each system
asked children to keep quiet.
23
Fig. 6 Measurment of sound pressure
24
Result of questionnaire
Fig. 7 shows the result of questionnaire. It
shows the means, the standard deviations
and results oft-test. As a result, there are
significant difference between two
conditions in question (I), (4), (5) and (6).
25
Fig. 7 Result of questionnaire
26
Thus, the using android robot as the
interface of the remote class support
system improves "concentration",
"easiness of understanding“ ,
"pleasantness" and "participation desire".
The following comments were obtained
as children's impression in each system.
27
Result of measuring sound pressure
level
We measured sound pressure level in the
room for 15 seconds before and after
each system warned children to keep
quiet when whisper were increased.
Table 2 shows reduction rates between
before and after of warnings .
28
Table 2.Comparison of reduction rates
of sound pressure level in both
conditions
29
It is verified that the reduction rates in
the case of using the android robot are
larger than that of the speaker.
When the android robot warns the child,
On the other hand, the speaker just uses
a voice without eye contact.
30
Therefore, it can be said that not only
calling child's name but also making eye
contact with child have children accept
warning easily .
This capability is advantage of the robot ic
system compared with using only speaker
or existing tele-con ference system.
31
V. CONCLUSION(1)
We confirmed that the advantage of the
android robot in management ability of
children . We also confirmed that positive
effects and possibility of developed
system in educational fields.
32
CONCLUSION(2)
Our future work is to investigate
effectiveness of developed system by
conducting field trial for the people at
various ages and comparing other existing
medium such as tele-conference system.
Furthermore, we believe that this system
also can be applied to other remote
communication systems like a remote
diagnosis.
33
REFERENCES(1)
[1] M. Fujita, "AIBO: towards the era of digital creatures",
International Journal of Robotics Research,Vol. 20, No. 10, pp. 781794,2001.
[2] K. wada, T. Shibata, T. Saito and K. Tanie, "Analysis of factors that
bring mental effects to elderly people in robot assisted activety",
Proceedings of IEEE/RSJ International Conference on Intelligent Robots
and Systems,Vol. 2, pp. 1152-1157,2002.
[3] T. Kanda, H. Ishiguro, M. Imai and T. Ono, "Development and
Evaluation of Interactive Humanoid Robots", Proceedings of the IEEE
(Special issue on Human Interactive Robot for Psychological Enrichment),
Vol. 92, No. 11, pp. 1839-1850,2004.
34
REFERENCES(2)
[4] D. Sakamoto, T. Kanda, T. Ono, M. Kamashima, M. Imai and H.
Ishiguro, "Cooperative embodied communication emerged by
interactive humanoid robots", Proceedings of the 13th IEEE
International Workshop on Robot and Human Interactive
Communication (RO-MAN'04), pp. 443-448, 2004.
[5] T. Watanabe, M. Okubo and H. Ogawa, "An Embodied
Interaction Robots System Based on Speech", Proceedings of the 8th
IEEE International Workshop on Robot and Human Communication
(ROMAN‘ 99), pp. 225-230, 1999
[6] C. Breazeal and B. Scassellati, "How to build robots that make
friends and influence people", Proceedings of Inteligent Robots Systems
(IROS '99), pp. 858-863,1999.
35
REFERENCES(3)
[7] H. Kobayashi and F. Hara, "Study on face robot for active human
interface-mechanisms of face robot and expression of 6 basic facial
expressions", Proceedings of 2nd IEEE International Workshop on Robot
and Human Communication (RO-MAN'93), pp. 276-281,1993.
[8] H. Ishiguro, "Android Science -Toward a new crossinterdisciplinary framework-", Proceedings of International Symposium
of Robotics Research, 2005.
[9] J. Oh, D. Hanson, W. Kim, I. Han, 1. Kim and I. Park, "Design of
Android Type Humanoid Robot Albert HUBO", Proceedings of the
2006 IEEE/RSJ International Conference on Intelligent Robots and
Systems (IROS '06), pp. 1428-1433,2006.
[10] D. Matsui, T. Minato, K. F. MacDorman and H. Ishiguro,
"Generating natural motion in an android by mapping human
motion", Procedings of 2005 IEEE/RSJ International Conference on
Intelligent Robots and Systems (IROS'05), pp.3301-3308, 2005.
36
REFERENCES(4)
[11] D. Sakamoto, T. Kanda, T. Ono, H. Ishiguro, N. Hagita, "Android
as a telecommunication medium with a human-like presence",
Proceedings of the ACM/IEEE international conference on Humanrobot interaction, pp. 193-200,2007.
[12] T. Hashimoto, S. Hiramatsu, T. Tsuji and H. Kobayashi,
"Development of the Face Robot SAYA for Rich Facial Expressions",
Proceedings of SICE-ICASE International Joint Conference 2006, pp.
5423-5428, 2006.
[13] T. Hashimoto and H. Kobayashi, "Development of the
receptionist system with an anthropomorphism face", Proceedings of
the 5th Asian Symposium on Applied Electromagnetics And Mechanics,
pp. 190-196, 2005.
[14] A. Mehrabian, "Communication without Words", Psychology
Today, Vol. 2, No.4, pp.53-55, 1968.
37
REFERENCES(4)
[15] P. Ekman, and W.V. Friesen, "The Facial Action Coding System",
Consulting Psychologists Press, 1978.
[16] C.P. Chou and B. Hannaford, "Measurement and Modeling of
McKibben Pneumatic Artificial Muscles", IEEE Transactions on
Robotics and Automation, vol. 12, pp. 90-102,1996.
[17] H. F. Schulte, Jr., "The characteristics of the McKibben artificial
muscle", In:The Application of external power in prosthetics and
orthotics. National Academy of Sciences-National Research Council,
Washington D. C., 1961.
38
Thanks for your attention
39