Yoh Shiraishi

Multi-agent interface architecture for real-world oriented distributed human interface systems

The authors propose the real-world oriented distributed human interface system named AIDA (Architecture for Interfacing Distributed Agents). AIDA supports human activities in the real-world (e.g., in offices and houses) without restricting user movements. AIDA is based on multi-agent model in which interfacing elements (e.g., mobile robots, workstations) cooperates with each other for providing continuous support to a user. An agent is constructed by a set of behavior modules for providing reactive responses to a user. Also, with AIDA, the system can adapt to the uncertainty of users position and the users attention that may change in time. They have developed a laboratory guiding system based on AIDA. And they have confirmed the efficiency of AIDA by experiment.

Task planning based on human-robot interaction for autonomous mobile robots

We propose a new method of task planning for autonomous mobile robots based on the properties of human-robot interaction. First, we present a planning method under restricted time for interaction and planning. We divide the planning process into two phases: phase 1 (during human interaction) and phase 2 (after human interaction). Second, we describe an algorithm to generate a plan that realizes simultaneous execution of multiple tasks. These tasks are constructed by a sequence of subtasks, and a new plan is generated by merging a task to the intermediate plan in the incremental planning process. Finally, we examine the effectiveness of this planning method through simulation.

Real-world oriented distributed human-robot interface system

In this paper, we propose the real-world oriented distributed human interface system named AIDA (Architecture for Interfacing Distributed Agents). AIDA supports human activities in the real-world (e.g., in offices or house) without restricting users movements. AIDA is based on multi-agent model in which each interfacing elements (e.g., mobile robots, workstations) cooperates with each other for providing continuous support to a user. An agent is constructed by a set of behavior modules for providing reactive responses to a user. Also, with AIDA, the system can adapt to the uncertainty of users position and users attention that may change in time. We have developed a laboratory guiding system based on AIDA. We have confirmed the efficiency of AIDA by experiment.

A User-centric Approach for Interactive Visualization and Mapping of Geo-sensor Data

Sensor network applications collect and use sensor data from distributed sensor networks and databases. These real-time and time series sensor data are very useful for many location-based systems that manage and browse various kinds of personal spatial information such as digital photograph, travel diary and so on. Such location-based system for personal use requires a user-centric framework that can support intuitive query request and direct sensor data mapping. This paper proposes a user-centric approach for interactive visualization and mapping of geographically distributed sensor data. The overview of the prototype system that we are developing is briefly described. Our approach generates a query for distributed sensor databases based on users track log. This method produces understandable information from collected sensor data based on GIS (geographic information system) methods.

Step-wise context extraction in AoK mule system

Extracting humans health condition using wireless sensors impose a challenge in the balance between data storage and CPU power. Taking available resources on nodes into consideration, we apply Step-wise Context Extraction (SCE) to AoK mule system [4]. SCE compresses data obtained at the mule into a context as the data is forwarded. In this demonstration, we show how the raw data is converted into the context in the AoK system.

Spatial Document Management System for Ubiquitous Mapping

This paper proposes a spatial document management system (SDMS) that can easily and directly manage spatial documents. A spatial document is an electronic document that includes spatial reference information, such as HTML file, Excel file, text file and so on. Our system provides a simple interface operating such spatial documents in own personal computer and on the web and manages textual information about Point of Interest (POI) in these documents. When a user can load a spatial document in the system by “drag and drop” operation, the system converts address expressions in the document into POI information and displays a distribution of the POI information on a map. Our SDMS will support such mapping actions by many ordinary people and become a new tool for “ubiquitous mapping”.