Hidehisa Akiyama

Field Experiment on Multiple Mobile Robots Conducted in an Underground Mall

Rapid information gathering during the initial stage of investigation is an important process in case of disasters. However this task could be very risky, or even impossible for human rescue crews, when the environment has contaminated by nuclear, biological, or chemical weapons. We developed the information gathering system using multiple mobile robots teleoperated from the safe place, to be deployed in such situation. In this paper, we described functions of the system and report the field experiment conducted in a real underground mall to validate its usability, limitation, and requirements for future developments.

Multirobot exploration for search and rescue missions: A report on map building in RoboCupRescue 2009

Mobile robots may be able to aid rescue crews in dangerous environments during search and rescue missions after natural or man-made disasters. In 2006, we began a research project to realize mobile robots that can gather information rapidly at the first stage of a disaster. 3D mapping, which can be an important aid for rescue crews in strategizing rescue missions, is one of our important objectives. Some fundamental elements to enable 3D mapping have been developed. We attended RoboCupRescue 2009 to validate our integrated autonomous 3D mapping system. We demonstrated our mapping system using multiple-robots on the RoboCupRescue field. In this paper, we introduce our mapping system and report the results from the RoboCupRescue competition.

HELIOS Base: An Open Source Package for the RoboCup Soccer 2D Simulation

To promote the research of multiagent systems, several base codes have been released for the RoboCup soccer 2D simulation community. As described herein, we present HELIOS base, currently the most popular base codes for 2D soccer simulation. HELIOS base involves a common library, a sample team, a visual debugger, and a formation editor, which help us to develop a simulated soccer team.

Multi-robot exploration for search and rescue missions: A report of map building in RoboCupRescue 2009

Mobile robots may be able to aid rescue crews in dangerous environments during search and rescue missions after natural or man-made disasters. In 2006, we began a research project to realize mobile robots that can gather information rapidly at the first stage of a disaster. 3D mapping, which can be an important aid for rescue crews in strategizing rescue missions, is one of our important objectives. Some fundamental elements to enable 3D mapping have been developed. We attended RoboCupRescue 2009 to validate our integrated autonomous 3D mapping system. We demonstrated our mapping system using multiple-robots on the RoboCupRescue field. In this paper, we introduce our mapping system and report the results from the RoboCupRescue competition.

Online Cooperative Behavior Planning Using a Tree Search Method in the RoboCup Soccer Simulation

In this paper, we propose a tree search approach to generate and evaluate cooprative behavior online in multiagent systems. It was difficult to apply a tree search methodology to tasks that the state-action space is continuous and requires realtimeness. However, it has become possible to apply such an approach since the computational resources became more powerful today. We applied a tree search method to the Robo Cup soccer 2D simulation and analyzed its effect by evaluating the team performance.

On the Progress of Soccer Simulation Leagues

Soccer simulation league is one of the founding leagues of RoboCup. In this paper we discuss the past, present and planned future achievements and changes. Also we summarize the connections and inter-league achievements of this league and provide an overview of the community contributions that made this league successful.

HELIOS2012: RoboCup 2012 Soccer Simulation 2D League Champion

The Soccer Simulation 2D League is one of the oldest competitions among the RoboCup leagues. In the simulation 2D league, the simulator enables two teams of 11 simulated autonomous agents to play a game of soccer with highly realistic rules and game play. This paper introduces the RoboCup 2012 Soccer Simulation 2D League champion team, HELIOS2012, a joint team of Fukuoka University and Osaka Prefecture University.

Learning Evaluation Function for Decision Making of Soccer Agents Using Learning to Rank

In the simulated soccer domain, the evaluation of actions that can be performed by soccer agents is important to design the team behavior. It is not easy to design the evaluation function that reflects the intention of human developers. Usually, manual adjustment of the evaluation function requires much cost. We propose a method to apply Learning to Rank algorithm to the evaluation function of the decision making of soccer agents. The experimental results show Learning to Rank would be promising to using the instruction of human trainer.

Team formation estimation using cluster analysis and triangulation model

In this paper, we propose a method to estimate unknown team formation from observed positional data. We combined Growing Neural Gas Network and triangulation based function representation model in order to analyze positional data and recompose a team formation. In the experiments, we show the estimation results using the log file recorded by the RoboCup soccer 2D simulator.

Integration of sensory data taken by multiple rescue robots using GIS

We propose a framework to collect spatial information acquired by sensor devices mounted on multiple rescue robots to generate an integrated map to help first responders. In order to utilize the multiple robots, matching and adjustment of spatial data is an important function for the geographical information database. We design flexible handling mechanism of coordinate reference systems for the spatial data and formats to represent sensing information. The proposed framework are tested by competitions of RoboCupRescue league, in which our system shows effective integration of information acquired by different kind of sensor devices on robots.