Yasuyuki Sumi

C-MAP: Building a Context-Aware Mobile Assistant for Exhibition Tours

This paper presents the objectives and progress of the Context-aware Mobile Assistant Project (C-MAP). The C-MAP is an attempt to build a personal mobile assistant that provides visitors touring exhibitions with information based on their locations and individual interests. We have prototyped the first version of the mobile assistant and used an open house exhibition held by our research laboratory for a testbed. A personal guide agent with a life-like animated character on a mobile computer guides users using exhibition maps which are personalized depending on their physical and mental contexts. This paper also describes services for facilitating new encounters and information sharing among visitors and exhibitors who have shared interests during/after the exhibition tours.

AgentSalon: facilitating face-to-face knowledge exchange through conversations among personal agents

This paper presents a system called AgentSalon, which facilitates face-to-face knowledge exchange and discussion by people having shared interests, in museums, schools, offices, academic conferences, etc. This system was designed as a sub-system of our ongoing project to construct a personal agent system for tour guidance and knowledge sharing among users. AgentSalon has a big screen for two to five users. The screen shows conversations among animated agents belonging to the users. The personal agent usually runs on our mobile guidance system, called PalmGuide, and guides its user according to his/her individual interests and touring records. When users connect their PalmGuides with AgentSalon by infrared, their personal agents with their personal information migrate to AgentSalon and engage in automated conversation. Contents of the conversation include opinion exchange about tour experiences, mutual recommendations of exhibits on behalf of the users, etc. By observing a chat of the agents, users can effectively obtain appropriate topics: that is, tempts them to follow the chat. This paper shows the first prototype of AgentSalon provided to participants in an academic conference.

An approach to integrating an interactive guide robot with ubiquitous sensors

An interactive exhibition guide robot has been developed, that is integrated with ubiquitous sensors. The robot utilizes its human-like body properties to perform human-like gestures such as eye-contact and pointing. The ubiquitous sensors are embedded in an exhibition room or attached to people in the room, and they provide information not only for the robots interactive guide but also for the development of the robot. The results of a two-days exhibition experiment show that the robot attracted visitors and successfully guided them in the environment. Moreover, the obtained interaction statistics, including video from the ubiquitous sensors, prove to be useful for analyzing the interaction between the robot and visitors, and this implies that the use of such interaction data is a promising approach for developing interactive robots.

ComicDiary: Representing Individual Experiences in a Comics Style

This paper describes a system called ComicDiary that automatically creates a personal diary in a comics style. ComicDiary is built as a sub-system of our ongoing project (C-MAP) to develop a personal guidance system for exhibition touring at museums, trade shows, academic conferences, cities, and so on. The aim of the C-MAP system is to provide users with personalized guidance according to temporal and spatial situations as well as individual interests. ComicDiary is designed as a casual tool for augmenting an individual users memory as well as for encouraging communities of users to exchange personal memories. This paper presents the preliminary results of deploying the ComicDiary system as a digital assistant service for conference participants.

Editorial: awareness and the WWW

Over the last decade, the issue of awareness has received increasing attention from practitioners in academia and industry. This applies to researchers from various horizons, and in particular from the Computer Supported Cooperative Work (CSCW), the Human–Computer Interaction (HCI) and the World Wide Web (WWW) communities. Nevertheless, awareness has remained a somewhat fuzzy concept, for which there exists no single, unequivocal definition. True, awareness is often meant as awareness of other people, and refers to the ability to maintain some knowledge about the situation and activities of others. There is also a tacit agreement that maintaining this knowledge should not require much effort or, in other words, that awareness should happen as ‘‘naturally’’ as possible. Supporting technology should be designed with this aim, which explains why human–computer interaction issues are of prime concern. Research has exhibited a wide spectrum of situations, in the context of which ‘‘awareness’’ can take very different meanings. Rather than to speak about awareness as such, it is therefore more appropriate to speak about particular types of awareness. For instance, group awareness can be defined as the ability that peers may have to stay in touch and to keep track of each others activities. The information that group members maintain about each other may not be very consequent, nor very precise. Having only a general idea of what is happening, or merely that something is happening, is often already very valuable. Let us be clear about it: the realization of group awareness may not require any technology support at all. When people share the same room, they naturally produce and interpret a constant flow of subtle cues with this aim. Glancing at someone may be enough to decide whether it is appropriate or not to start a conversation. On the other hand, when the members of a group are scattered across space and time, technology may offer surrogates to this natural process}media spaces are an example for such technology. Obviously, groups formed in the context of the workplace greatly benefit from increased awareness. Communication and collaboration are easier, cooperation is smoother and, as a result, work processes are more efficient.

WOZ experiments for understanding mutual adaptation

A robot that is easy to teach not only has to be able to adapt to humans but also has to be easily adaptable to. In order to develop a robot with mutual adaptation ability, we believe that it will be beneficial to first observe the mutual adaptation behaviors that occur in human–human communication. In this paper, we propose a human–human WOZ (Wizard-of-Oz) experiment setting that can help us to observe and understand how the mutual adaptation procedure occurs between human beings in nonverbal communication. By analyzing the experimental results, we obtained three important findings: alignment-based action, symbol-emergent learning, and environmental learning.

Digital Assistant for Supporting Conference Participants: An Attempt to Combine Mobile, Ubiquitous and Web Computing

This paper describes a project of providing digital assistants to support participants in an academic conference. We provided participants at the conference with a personal assistant system with mobile and ubiquitous computing technologies and facilitated communications among the participants. We also made online services available via the Web to encourage the participants to continue their relationships even after the conference. In this paper, we show the system we provided for the project and report the results.

Computer-aided thinking by mapping text-objects into metric spaces

Abstract This paper presents a system for computer-aided thinking. We propose the idea of reflecting the mental world indirectly into a metric space to support such human thinking activities as externalizing and forming new ideas. We use a method that maps text-objects into metric spaces for visualizing a users thought space structure. Text-objects imply fragments of a users idea, which have several keywords given by him/her. Spaces composed of text-objects are configured in the way “the higher the mutual relevance between a pair of text-objects is, the closer the text-objects are mapped”. The relevance values among text-objects are calculated due to cooccurrence of their keywords. Results of experiments with our implemented system, named CAT1 (computer-aided thinking, version 1), show that users of the system can get effective stimuli for further thinking in creative concept formation. The paper also discusses the potential application of CAT1 to collaborative work by groups of people.

Conference assistant system for supporting knowledge sharing in academic communities

This paper describes our ongoing attempts to build a communityware system by presenting a project of providing digital assistants to support participants in an academic conference. We provided participants at the conference with a personal assistant system with mobile and ubiquitous computing technologies and facilitated communication among the participants. We also made online services available via the Web to encourage the participants to continue their relationships even after the conference. In this paper, we show the system we provided for the project and report the results. q 2002 Elsevier Science B.V. All rights reserved.

Analysis environment of conversational structure with nonverbal multimodal data

This paper shows the IMADE (Interaction Measurement, Analysis, and Design Environment) project to build a recording and anlyzing environment of human conversational interactions. The IMADE room is designed to record audio/visual, human-motion, eye gazing data for building interaction corpus mainly focusing on understanding of human nonverbal behaviors. In this paper, we show the notion of interaction corpus and iCorpusStudio, software environment for browsing and analyzing the interaction corpus. We also present a preliminary experiment on multiparty conversations.