Volume 47, Issue 5

Robotic soccer requires the ability of individually acting agents to cooperate. The simulation league of RoboCup therefore offers an ideal testbed for evaluating multi-agent methods. In this paper we discuss how Reinforcement Learning (RL) methods can be succesfully applied within the scenario of learning to cooperatively score a goal. Due to the complexity of the task, enhanced methods of learning have to be applied. We discuss several approaches from literature and also present an own approach. All approaches are evaluated on a discretized version of robotic soccer, which we call gridworld soccer.

This paper shows how an omnidirectional robot can learn to correct inaccuracies when driving, or even learn to use corrective motor commands when a motor fails, whether partially or completely. Driving inaccuracies are unavoidable, since not all wheels have the same grip on the surface, or not all motors can provide exactly the same power. When a robot starts driving, the real system response differs from the ideal behavior assumed by the control software. Also, malfunctioning motors are a fact of life that we have to take into account. Our approach is to let the control software learn how the robot reacts to instructions sent from the control computer. We use a neural network, or a linear model for learning the robot's response to the commands. The model can be used to predict deviations from the desired path, and take corrective action in advance, thus increasing the driving accuracy of the robot. The model can also be used to monitor the robot and assess if it is performing according to its learned response function. If it is not, the new response function of the malfunctioning robot can be learned and updated. We show, that even if a robot loses power from a motor, the system can re-learn to drive the robot in a straight path, even if the robot is a black-box and we are not aware of how the commands are applied internally.

In this article we describe a self-localization method for soccer robots that solves the “Where am I”-problem by visually perceiving and understanding the structure of the field lines on a soccer playing field. The method accrued from our participation in the RoboCup Middle Size league where fully autonomous robots play soccer on a 8 × 12 m field. The method was successfully applied by our FU-Fighter's Middle Size robots during the world championships in 2004, where we placed 4th.

This article describes the architecture and the methods developed by the GermanTeam, the RoboCup world champion 2004 in the Sony Four-Legged Robot League. The architecture supports developing software in a joint effort of many researchers both in sub-teams of the GermanTeam itself, but also in several other teams in the league. In addition to the architecture, the different components required to play soccer in the four-legged league are presented: perception, world modeling, behavior control, and motion control.

VolksBot is a modular mobile robot construction kit, developed during the last 3 years to fit the needs in research and education as well as in application-based rapid prototyping. The component-based approach offers a plug-in architecture with open interfaces in electronic hardware, software and mechanics. The lean and open structure fosters reusability of existing modules, both in hardware and software. Initially this concept was successfully applied to indoor applications. The article addresses this concept and shows how it was extended to fit the higher demands of real-life scenarios like outdoor or rough terrain. As a result, the VolksBot RT (Rough Terrain) construction kit is presented. Examples are given, how domain-specific rapid prototyping of variants of such platforms could be achieved in the fields of Urban Search and Rescue and Autonomous Transportation.

Deploying rescue workers in an urban setting is often a perilous, time-, power-, and force-consuming job, and robot systems to assist in this effort are needed. A fundamental task for rescuer is to localize and salvage injured persons. To this end, robotic systems are used for mapping a site and for remote inspection of suspicious objects. The mobile robot Kurt3D is the first rescue robot that is capable of mapping its environment in 3D and self localize in all six degrees of freedom, i. e., considering its x , y and z positions and the roll, yaw and pitch angles. This capability allowed the small robot to win the Vice World Championship at the RoboCup Rescue competition 2004 at Lisbon.

Humanoid robots are enjoying increasing popularity as a research tool. As step towards the long-term goal of winning against the FIFA world champion, the RoboCup Federation added in 2002 a league for humanoid robots to its annual soccer competitions. In this paper, the Humanoid League competitions that took place so far are reviewed. The different approaches for the design of robot hardware and the software for perception and behavior control of soccer playing humanoid robots are discussed. The paper concludes with an outlook to the future of the RoboCup Humanoid League.

Zusammenfassung Agententechnologie wird als ein vielversprechender Ansatz gesehen, die Probleme der Konstruktion komplexer Software-Systeme wie heterogene Systemumgebungen und dezentrale Strukturen besser beherrschbar zu machen. Dieser Beitrag wirft einen kritischen Blick auf den erreichten Stand der softwaretechnischen Unterstützung, den die Agententechnologie bei der Systementwicklung bietet. Da die Agententechnologie ein stark diversifiziertes Feld ist, wird versucht die unterschiedlichen Einflussfaktoren und ihre Wechselwirkungen aufzuzeigen. Zudem wird durch Beispiele aus der Praxis belegt, für welche Anwendungsfelder die vorgestellten Technologien besonders gut geeignet sind.

Data Mining has enjoyed great popularity in recent years, with advances in both research and commercialization. The first generation of data mining research and development has yielded several commercially available systems, both stand-alone and integrated with database systems, produced scalable versions of algorithms for many classical data mining problems and introduced novel pattern discovery problems. In July 2004 researchers from a variety of backgrounds assembled at the Dagstuhl Conference Center in Germany for a workshop to re-assess the current directions of the field, to identify critical problems that require attention, and to discuss ways to increase the flow of ideas across the different disciplines that Data Mining has brought together. The workshop did not seek to draw up an agenda for the field of data mining. Rather, it offers the participants' perspective on two technical directions – compositionality and privacy – and describes some important application challenges which drove the discussion.