M. Attamimi, M. Miyata, Tetsuji Yamada, T. Omori, Ryoma Hida
In this paper, we present a method of estimating a child's attention, one of the more important human mental states, in a free-play scenario of child-robot interaction. First, we developed a system that could sense a child's verbal and non- verbal multimodal signals such as gaze, facial expression, proximity, and so on. Then, the observed information was used to train a Support Vector Machine (SVM) to estimate a human's attention level. We investigated the accuracy of the proposed method by comparing with a human judge's estimation, and obtained some promising results which we discuss here.
{"title":"Attention Estimation for Child-Robot Interaction","authors":"M. Attamimi, M. Miyata, Tetsuji Yamada, T. Omori, Ryoma Hida","doi":"10.1145/2974804.2980510","DOIUrl":"https://doi.org/10.1145/2974804.2980510","url":null,"abstract":"In this paper, we present a method of estimating a child's attention, one of the more important human mental states, in a free-play scenario of child-robot interaction. First, we developed a system that could sense a child's verbal and non- verbal multimodal signals such as gaze, facial expression, proximity, and so on. Then, the observed information was used to train a Support Vector Machine (SVM) to estimate a human's attention level. We investigated the accuracy of the proposed method by comparing with a human judge's estimation, and obtained some promising results which we discuss here.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122072261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
There are several merits to embody the remote partner's body to the video conference: showing it physically, making a physical contact, and enhancing social telepresence. In this paper, we tackled to embody a part of a remote partner's body in a video conference. As a method to show how effectively the embodied body part works, we focused on face-to-face communication of the hand gestures such as thumb wrestling, finger number game and pointing. We developed a robotic arm, which seems the remote partner's arm popped out from the video. Our robot arm synchronizes with the remote partner's arm movements. We conducted experiments to verify the method of embodying a part of a remote partner's body. We found that, our method reduced the feeling of being far from the remote partner, and enhanced social telepresence, comparing video and physical embodiment.
{"title":"Embodiment of Video-mediated Communication Enhances Social Telepresence","authors":"Yuya Onishi, Kazuaki Tanaka, Hideyuki Nakanishi","doi":"10.1145/2974804.2974826","DOIUrl":"https://doi.org/10.1145/2974804.2974826","url":null,"abstract":"There are several merits to embody the remote partner's body to the video conference: showing it physically, making a physical contact, and enhancing social telepresence. In this paper, we tackled to embody a part of a remote partner's body in a video conference. As a method to show how effectively the embodied body part works, we focused on face-to-face communication of the hand gestures such as thumb wrestling, finger number game and pointing. We developed a robotic arm, which seems the remote partner's arm popped out from the video. Our robot arm synchronizes with the remote partner's arm movements. We conducted experiments to verify the method of embodying a part of a remote partner's body. We found that, our method reduced the feeling of being far from the remote partner, and enhanced social telepresence, comparing video and physical embodiment.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126161356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This pilot study reports an experiment where we introduced huggable communication media into daytime sleep in co-sleeping situation. The purpose of the experiment was to investigate whether it would improve soothing child users' sleep and how hugging experience with anthropomorphic communication media affects child's anthropomorphic impression on the media in co-sleeping. In the experiment, nursery teachers read two-year-old or five-year-old children to sleep through huggable communication media called Hugvie and asked the children to draw Hugvie before and after the reading to evaluate changes in their impressions of Hugvie. The results show the difference of sleeping behavior with and the impressions on Hugvie between the two classes. Moreover, they also showed the possibility that co-sleeping with a humanlike communication medium induces children to sleep deeply.
{"title":"Can Children Anthropomorphize Human-shaped Communication Media?: A Pilot Study on Co-sleeping with a Huggable Communication Medium","authors":"Junya Nakanishi, H. Sumioka, H. Ishiguro","doi":"10.1145/2974804.2980519","DOIUrl":"https://doi.org/10.1145/2974804.2980519","url":null,"abstract":"This pilot study reports an experiment where we introduced huggable communication media into daytime sleep in co-sleeping situation. The purpose of the experiment was to investigate whether it would improve soothing child users' sleep and how hugging experience with anthropomorphic communication media affects child's anthropomorphic impression on the media in co-sleeping. In the experiment, nursery teachers read two-year-old or five-year-old children to sleep through huggable communication media called Hugvie and asked the children to draw Hugvie before and after the reading to evaluate changes in their impressions of Hugvie. The results show the difference of sleeping behavior with and the impressions on Hugvie between the two classes. Moreover, they also showed the possibility that co-sleeping with a humanlike communication medium induces children to sleep deeply.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129982735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Session details: Main Track Session VIII: Interaction Tactics","authors":"M. Imai, Yusuhike Kitamura","doi":"10.1145/3257130","DOIUrl":"https://doi.org/10.1145/3257130","url":null,"abstract":"","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129668964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sho Sakurai, Yuki Ban, Toki Katsumura, Takuji Narumi, T. Tanikawa, M. Hirose
Agents like human, such as humanoid robots or avatars can be felt as if they have and communicate and communicate due to manipulation of the bodily information. Meanwhile, as in the case of Internet bot, it is still difficult to communiate the emotion described as text, let alone empathizing due to degradation of information online. The current study proposes a method for experiencing emotion on the Internet by reproducing a mechanism of evoking emotion. This method evokes a number of emotions described on the Web, by changing of self-physiological perception with sensory stimuli. To investigate the feasibility of our method, we made a system named "Communious Mouse." This system rewrites the perception of self-skin temperature and pulse in a palm by presenting vibration and thermal stimulation through a mouse device for evoking emotion. The current paper discusses the feasibility of our method based on the obtained feedbacks through an exhibition of the system.
{"title":"Sharing Emotion Described as Text on the Internet by Changing Self-physiological Perception","authors":"Sho Sakurai, Yuki Ban, Toki Katsumura, Takuji Narumi, T. Tanikawa, M. Hirose","doi":"10.1145/2974804.2974825","DOIUrl":"https://doi.org/10.1145/2974804.2974825","url":null,"abstract":"Agents like human, such as humanoid robots or avatars can be felt as if they have and communicate and communicate due to manipulation of the bodily information. Meanwhile, as in the case of Internet bot, it is still difficult to communiate the emotion described as text, let alone empathizing due to degradation of information online. The current study proposes a method for experiencing emotion on the Internet by reproducing a mechanism of evoking emotion. This method evokes a number of emotions described on the Web, by changing of self-physiological perception with sensory stimuli. To investigate the feasibility of our method, we made a system named \"Communious Mouse.\" This system rewrites the perception of self-skin temperature and pulse in a palm by presenting vibration and thermal stimulation through a mouse device for evoking emotion. The current paper discusses the feasibility of our method based on the obtained feedbacks through an exhibition of the system.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128248711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Longjiang Zhou, A. H. Adiwahono, Yuanwei Chua, W. L. Chan
This paper presents a haptic workspace control approach to the arms of a humanoid robot by using the Omega 7 haptic device as the control input device. The haptic device with small workspace is used to control the robot with 2 arm end-effectors of large workspace. This paper also puts forward an approach for users to feel the haptic feedback force when the robot end-effectors touch the virtual boundary areas for the safety consideration. The haptic device can move further but the robot arm end-effector will stop and the haptic force generated is proportional to the travel distance of the haptic device end-effectors until reaching the maximum value of force permitted by the designer. Simulation experiments are designed and implemented to test the motion performance of the arm end-effectors under control of haptic device and the generated haptic force when the virtual boundary walls are reached by the arm end-effectors.
{"title":"Haptic Workspace Control of the Humanoid Robot Arms","authors":"Longjiang Zhou, A. H. Adiwahono, Yuanwei Chua, W. L. Chan","doi":"10.1145/2974804.2980505","DOIUrl":"https://doi.org/10.1145/2974804.2980505","url":null,"abstract":"This paper presents a haptic workspace control approach to the arms of a humanoid robot by using the Omega 7 haptic device as the control input device. The haptic device with small workspace is used to control the robot with 2 arm end-effectors of large workspace. This paper also puts forward an approach for users to feel the haptic feedback force when the robot end-effectors touch the virtual boundary areas for the safety consideration. The haptic device can move further but the robot arm end-effector will stop and the haptic force generated is proportional to the travel distance of the haptic device end-effectors until reaching the maximum value of force permitted by the designer. Simulation experiments are designed and implemented to test the motion performance of the arm end-effectors under control of haptic device and the generated haptic force when the virtual boundary walls are reached by the arm end-effectors.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126568464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Viktor Richter, Birte Carlmeyer, Florian Lier, Sebastian Meyer zu Borgsen, David Schlangen, F. Kummert, S. Wachsmuth, B. Wrede
In this paper, we present our humanoid robot "Meka", participating in a multi party human robot dialogue scenario. Active arbitration of the robot's attention based on multi-modal stimuli is utilised to observe persons which are outside of the robots field of view. We investigate the impact of this attention management and addressee recognition on the robot's capability to distinguish utterances directed at it from communication between humans. Based on the results of a user study, we show that mutual gaze at the end of an utterance, as a means of yielding a turn, is a substantial cue for addressee recognition. Verification of a speaker through the detection of lip movements can be used to further increase precision. Furthermore, we show that even a rather simplistic fusion of gaze and lip movement cues allows a considerable enhancement in addressee estimation, and can be altered to adapt to the requirements of a particular scenario.
{"title":"Are you talking to me?: Improving the Robustness of Dialogue Systems in a Multi Party HRI Scenario by Incorporating Gaze Direction and Lip Movement of Attendees","authors":"Viktor Richter, Birte Carlmeyer, Florian Lier, Sebastian Meyer zu Borgsen, David Schlangen, F. Kummert, S. Wachsmuth, B. Wrede","doi":"10.1145/2974804.2974823","DOIUrl":"https://doi.org/10.1145/2974804.2974823","url":null,"abstract":"In this paper, we present our humanoid robot \"Meka\", participating in a multi party human robot dialogue scenario. Active arbitration of the robot's attention based on multi-modal stimuli is utilised to observe persons which are outside of the robots field of view. We investigate the impact of this attention management and addressee recognition on the robot's capability to distinguish utterances directed at it from communication between humans. Based on the results of a user study, we show that mutual gaze at the end of an utterance, as a means of yielding a turn, is a substantial cue for addressee recognition. Verification of a speaker through the detection of lip movements can be used to further increase precision. Furthermore, we show that even a rather simplistic fusion of gaze and lip movement cues allows a considerable enhancement in addressee estimation, and can be altered to adapt to the requirements of a particular scenario.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127491311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we present results of an exploratory experiment investigating the effects of a contingently self-interrupting vs non-self-interrupting virtual agent who transmits information to a human interaction partner. In the experimental condition self-interruptions of the agent were triggered by an external event whereas in the control group the agent did not react to this event. We measured the effect of the agent's self-interruptions on human attention, memory performance and subjective ratings. In this paper we discuss the results with respect to the design of incremental human-agent dialogue modeling.
{"title":"\"Look at Me!\": Self-Interruptions as Attention Booster?","authors":"Birte Carlmeyer, David Schlangen, B. Wrede","doi":"10.1145/2974804.2980488","DOIUrl":"https://doi.org/10.1145/2974804.2980488","url":null,"abstract":"In this paper we present results of an exploratory experiment investigating the effects of a contingently self-interrupting vs non-self-interrupting virtual agent who transmits information to a human interaction partner. In the experimental condition self-interruptions of the agent were triggered by an external event whereas in the control group the agent did not react to this event. We measured the effect of the agent's self-interruptions on human attention, memory performance and subjective ratings. In this paper we discuss the results with respect to the design of incremental human-agent dialogue modeling.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"634 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134003883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Okanda, Yue Zhou, T. Kanda, H. Ishiguro, S. Itakura
This study examined response tendencies in 4-year-old Japanese children (N = 45) to yes-no questions asked by a communicative, or a non-communicative robot. The children watched a video of a robot that was either responsive (communicative condition), or unresponsive (non-communicative condition) to human actions. Then, all the children watched a video of the same robot asking yes-no questions pertaining to familiar and unfamiliar objects. The children in both conditions exhibited a nay-saying bias to questions about unfamiliar objects, with children in the non-communicative condition tending to show a stronger nay-saying bias than children in the communicative condition. Children's response tendencies towards questions asked by humans and other agents are discussed.
{"title":"Response Tendencies of Four-Year-Old Children to Communicative and Non-Communicative Robots","authors":"M. Okanda, Yue Zhou, T. Kanda, H. Ishiguro, S. Itakura","doi":"10.1145/2974804.2980490","DOIUrl":"https://doi.org/10.1145/2974804.2980490","url":null,"abstract":"This study examined response tendencies in 4-year-old Japanese children (N = 45) to yes-no questions asked by a communicative, or a non-communicative robot. The children watched a video of a robot that was either responsive (communicative condition), or unresponsive (non-communicative condition) to human actions. Then, all the children watched a video of the same robot asking yes-no questions pertaining to familiar and unfamiliar objects. The children in both conditions exhibited a nay-saying bias to questions about unfamiliar objects, with children in the non-communicative condition tending to show a stronger nay-saying bias than children in the communicative condition. Children's response tendencies towards questions asked by humans and other agents are discussed.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"243 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131653548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Overweight and obesity due to lack of physical activities incur a serious social problem and a number of systems to promote physical activities using information and communication technologies have been developed. Virtual Kobe Marathon is an Android app to make a user experience a marathon race virtually. It shows the Kobe Marathon course on its display and moves an agent along the course according to the user's moving distance. It also has a competition scheme to make a user compete virtually with others running at different places and times. This scheme facilitates competitions with a small number of opponents, and we, in this paper, introduce a massive competition scheme utilizing the record of 17,769 runners who participated in the 3rd Kobe Marathon. The evaluation experiment shows the massive competition scheme promotes physical activities more than the one-to-one competition scheme.
{"title":"Promoting Physical Activities by Massive Competition in Virtual Marathon","authors":"Yuya Nakanishi, Y. Kitamura","doi":"10.1145/2974804.2980483","DOIUrl":"https://doi.org/10.1145/2974804.2980483","url":null,"abstract":"Overweight and obesity due to lack of physical activities incur a serious social problem and a number of systems to promote physical activities using information and communication technologies have been developed. Virtual Kobe Marathon is an Android app to make a user experience a marathon race virtually. It shows the Kobe Marathon course on its display and moves an agent along the course according to the user's moving distance. It also has a competition scheme to make a user compete virtually with others running at different places and times. This scheme facilitates competitions with a small number of opponents, and we, in this paper, introduce a massive competition scheme utilizing the record of 17,769 runners who participated in the 3rd Kobe Marathon. The evaluation experiment shows the massive competition scheme promotes physical activities more than the one-to-one competition scheme.","PeriodicalId":185756,"journal":{"name":"Proceedings of the Fourth International Conference on Human Agent Interaction","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133096747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：