@phdthesis{oai:sucra.repo.nii.ac.jp:00010288,
 author = {Mohammad, Abu Yousuf},
 month = {},
 note = {xvii, 164 p., The development of robot is entering a new stage where the focus is placed on interaction with people in their daily environments. The concept of service robot is rapidly emerging. The service robot will act as a peer providing mental, communicational, and physical support. Such interactive tasks are of importance for allowing robots to take part in human society. Many robots have already been applied to various fields like hospital, school, day care center, museum and so on in daily environment. In museum context, guide robot needs to interact with the visitors in a natural way. Although much research has already been conducted in the area of non-verbal communication between a guide robot and human, such as facial expression, eye-gaze, and gesture commands, whether create and control spatial formation with the multiple visitors is also a fundamental function for the museum guide robots that remain unexplored. Drawing upon psychological and sociological studies on the spatial relationship between human, it is considered that museum guide robots should have also the capability to create and control spatial formation in various situations.
The research questions that we seek to address in this area are as follows: What are the constraints to create spatial formation with the visitors? How does guide robot create spatial formation with the visitors before start its explanation of any exhibit? Can the robot attract visitor's attention to creates spatial formation properly? Can the guide robot indentify interested bystanders and invite them into an ongoing explanation session and thus reconfigure spatial formation? Can the robot reconfigure spatial formation during explaining multiple exhibits collectively? How does guide robot initiate conversation with the multiple visitors?
This dissertation seeks to find answers to these questions by incrementally exploring the constraints to create spatial formation and developed an integrated model to configure spatial formation with the visitors in various situations. We began by observing and videotaping scenes of actual museum galleries where human guides explained exhibits to multiple visitors. Based on these analyses of the video, we developed a mobile robot system able to create and control spatial formation while guiding multiple visitors inside the gallery from one exhibit to another. We evaluate the guide robot system in a series of study that focuses on different situations where guide robot creates spatial formation with the visitors. The first study focused on designing a model to create spatial formation by analyzing the constraints of spatial formation before start the explanation by the guide robot. The effectiveness of the guide robot system was confirmed through the experiments.
In a museum context, when a guide explains any exhibit to a small numbers of visitors, many other visitors who are not participating in the current explanation may stand around the explanation area. Among them who demonstrate interest in the explanation are considered to be interested bystanders. A museum guide robot needs to identify interested bystanders and invite them into ongoing explanation session. Thus to deal with the bystanders, we extended our model and evaluate its performance through a series of experiments in the next. These experiments focused on designing three steps process of identifying and inviting interested bystanders into ongoing explanation session. Change of robot's body orientation plays an important role to reconfigure the spatial formation again. This dissertation also seeks to find the answer how robot changes the position and orientation of the visitors by rotating its own body from one exhibit to another while explaining multiple exhibits collectively. Experimental results suggest that repositioning and reorientation of the visitor's body are reasonable indications of the visitor's intention of spatial reconfiguration. Finally, we have presented a model to initiate conversation with the visitors. Museum guide robot should observe visitors to find those who may want to be guided and initiate conversation with them. We developed a model that describes the constraints and expected behaviors in the phase of initiating conversation. We conducted an evaluation experiment that demonstrates that our model significantly improves the robot's performance in initiating conversation.
This research contributes to the design of a mobile museum guide robotic system that is capable to create and control spatial formation with the visitors in different situations., Dedication .......................................................................................................... ii
Acknowledgements ........................................................................................... iii
Abstract ............................................................................................................. v
Contents ............................................................................................................ ix
List of Figures ................................................................................................ xiv
List of Tables ................................................................................................. xvii
1. Introduction ................................................................................................ 1
1.1 Objectives ............................................................................................. 3
1.2 Motivation ............................................................................................ 4
1.3 Research Contribution ......................................................................... 6
1.4 Structure of Thesis ............................................................................... 7
2. Background ............................................................................................... 10
2.1 Robots and Human-Robot Interaction ................................................. 10
2.2 HRI: Situation and Context .................................................................. 11
2.3 Taxonomies of HRI ................................................................................ 12
2.4 Types of Robot ....................................................................................... 13
2.5 Related Robotic Works .......................................................................... 15
2.5.1 Guide Robot Overview .................................................................... 15
2.5.1.1 Autonomous Movement of Robots ............................................ 16
2.5.1.2 Verbal Communication with the Visitors ................................ 17
2.5.1.3 Non-verbal Communication with the Visitors......................... 18
2.5.2 Position-Based Interaction Overview ............................................ 21
2.6 Social Spaces ......................................................................................... 25
2.7 What is Spatial Formation? .................................................................. 27
2.7.1 Domains of Spatial formation ........................................................ 30
2.7.2 Category of Spatial formation ........................................................ 31
2.7.3 Shapes of Spatial Formation .......................................................... 32
2.8 Guide-Visitors Interaction in Museum ................................................ 33
2.9 Chapter Summary ................................................................................. 35
3. A Empirical Framework to Create Spatial Formation by Guide Robot . 37
3.1 Guide Robot System .............................................................................. 38
3.1.1 System Overview ............................................................................ 38
3.1.1.1 Hardware Configuration ......................................................... 39
3.1.1.2 Software Configuration ........................................................... 41
3.1.2 Tracking Framework ...................................................................... 42
3.1.2.1 Particle Filtering ...................................................................... 42
3.1.2.2 AdaBoost-based cascade classifier ........................................... 44
3.1.3 Modeling Human as Tracking Target ............................................ 46
3.1.4 Likelihood Evaluation .................................................................... 47
3.1.4.1 Evaluation Based on Laser Image ........................................... 47
3.1.4.2 Evaluation Based on Omni-directional Camera Image .......... 48
3. 2 Proposed Modeling of Interaction ........................................................ 51
3.2.1 Model of Spatial Formation ............................................................ 51
3.2.2 Model to Achieve Mutual Gaze ...................................................... 52
3.3 Evaluation Experiments ....................................................................... 56
3.3.1 Experimental 1: Create Spatial Formation Considering the Constraints of Proximity, Face Direction and FOV ................................ 56
3.3.1.1 Experimental Environment ..................................................... 57
3.3.1.2 Experimental Procedure........................................................... 57
3.3.1.3 Experimental Conditions ......................................................... 60
3.3.2 Experimental 2: Create Spatial Formation Considering the Constraints of Proximity, Body Orientation, Face Direction, and FOV . 61
3.3.2.1 Experimental Procedure........................................................... 62
3.3.2.2 Guide Robot Behaviors ............................................................. 63
3.3.2.3 Experimental Condition ........................................................... 66
3.3.2.4 Hypothesis and Prediction ...................................................... 67
3.4 Experimental Results ........................................................................... 68
3.4.1 Control of Visitor's Standing Position ............................................ 68
3.4.2 Control of Visitor's Body Orientation.............................................. 72
3.4.3 Control of Visitor's Face Direction .................................................. 75
3.4.4 Subjective Evaluation .................................................................... 78
3.5 Chapter Summary ................................................................................ 80
3.5.1 Limitations ..................................................................................... 81
4. Reconfiguration of Spatial Formation While Interested Bystanders Join into Ongoing Explanation ............................................................................... 82
4.1 Who is Bystander? ................................................................................ 83
4.2 Model of Incorporating Interested Bystanders .................................... 84
4.2.1 The Robot should Identify the Visitors Around itself ................... 84
4.2.2 The Robot should Assess Visitors' Intentions ................................ 85
4.2.3 Approaching Interested Bystanders Appropriately ...................... 86
4.3 Evaluation Experiment ......................................................................... 87
4.4 Experimental Results ........................................................................... 89
4.5 Chapter Summary ................................................................................. 93
4.5.1 Limitations ..................................................................................... 93
5. Reconfiguration of Spatial Formation during Explanation of Multiple Exhibits to Multiple Visitors .......................................................................... 95
5.1 Modeling of Interaction with Visitors .................................................. 96
5.1.1 Model of Spatial Position ................................................................ 97
5.1.1.1 Constraint of Proximity ............................................................ 97
5.1.1.2 Constraint of Visitor's Face Direction ..................................... 97
5.1.1.3 Constraint of Body Orientation ............................................... 97
5.1.1.4 Constraint of Robot's Field of View......................................... 99
5.1.2 Model to Attract Visitor's Attention ............................................... 99
5.2 Tasks Performed by Guide Robot ......................................................... 99
5.3 Experiment with Multiple Exhibits ................................................... 101
5.3.1 Experimental Design ..................................................................... 101
5.3.2 Results .......................................................................................... 102
5.3.2.1 Spatial Formation Transformation ........................................ 103
5.3.2.2 Reconfiguration of Spatial Formation ................................... 104
5.3.2.3 Subjective Evaluation ............................................................. 106
5.4 Chapter Summary ............................................................................... 108
5.4.1 Limitations ..................................................................................... 108
6. Spatial Formation Model to Initiate Conversation ............................... 109
6.1 Modified System Architecture ............................................................ 110
6.1.1 Tracking Position and Orientation of Visitors ............................. 112
6.1.2 Tracking Location and Orientation of Robot ............................... 115
6.1.3 Tracking Face Direction of Visitors ............................................. 117
6.2 Modeling of Initiation of Interaction .................................................. 119
6.2.1 Identifying Visitors' and Robots' Transactional Segments ......... 119
6.2.2 Control of Spatial Position and Initiation of Conversation ......... 120
6.2.2.1 All Visitors are looking Towards the Robot ........................... 121
6.2.2.2 Some of the Visitors are Looking Towards the Robot ........... 122
6.2.2.3 All Visitors are Looking Towards the exhibit........................ 124
6.3 Experiment with Guide Robot ............................................................ 125
6.3.1 Experimental Area ........................................................................ 126
6.3.2 Experimental Condition ............................................................... 126
6.3.3 Procedure ...................................................................................... 127
6.4 Experimental Results ......................................................................... 128
6.5 Chapter Summary ............................................................................... 130
6.5.1 Limitations .................................................................................... 131
7. Conclusion ............................................................................................... 132
7.1 Methodological Contributions ............................................................ 133
7.2 Theoretical Contributions .................................................................. 135
7.3 Technical Contributions ...................................................................... 136
7.4 Future Works ...................................................................................... 137
7.5 Published Papers from the Study ....................................................... 139
7.6 Closing Remarks ................................................................................. 141
A. Data Collection Technique ...................................................................... 142
References ...................................................................................................... 145, 主指導教員 : 久野義徳, text, application/pdf},
 school = {埼玉大学},
 title = {Mobile Museum Guide Robots Able to Create Spatial Formations with Multiple Visitors},
 year = {2013},
 yomi = {モハマド, アブ ユサフ}
}