Oliver Zweigle

RoboEarth: connecting robots worldwide

In this paper, we present the core concept and the benefits of an approach called RoboEarth which will be highly beneficial for future robotic applications in science and industry. RoboEarth is a world-wide platform which robots can use to exchange position and map information as well as task-related, hardware-independent action recipes. This will enable manufacturers worldwide to break down their costs and efforts for reproducing software algorithms for robot behavior over and over again. The RoboEarth framework can store all relevant data from algorithms to complex behavior descriptions what allows robots to act autonomously in an unknown, unspecified environment. Especially in the field of interaction with humans RoboEarth can bring forward the behavior of robots and simplify the software design for developers in that field.

Creating and using RoboEarth object models

This paper presented an approach to create 3D object models for robotic and vision applications in a fast and inexpensive way compared to established approaches. By using the RoboEarth system for storing the created object models users have world-wide access to the data and can immediately reuse a model as soon as it was created and uploaded. The approach shows general applicability for different kinds of cameras. In this work this was shown by two example implementations for the recognition process of objects. The quality of the recognition can be verified in the video. Combined with the knowledge saved in the RoboEarth database the objects can also be properly classified.

Evaluating Coupled Selection Equations for Dynamic Task Assignment Using a Behavior Framework

In this paper we focus on methods for a reliable and robust mechanism to distribute roles among a team of cooperating robots. In previous work, we showed the principal applicability of a novel approach based on self organization using coupled selection equations. To show the applicability in the robocup scenario we used a simple scenario to assign the roles attacker and defender. In this paper we present the application of the novel approach to more realistic and complex scenarios like kick-off or pass play. One of the critical parts in this method is the parameterization of utility and activation functions used to determine the additional parameters.

Supervised learning algorithm for automatic adaption of situation templates using uncertain data

In this paper a learning algorithm for the automatic adaption of a situation template is presented. The approach strongly relies on human-machine interaction as user feedback is a substantial part to automatically adapt a global knowledgebase in this case. The work bases on the assumption of uncertain data and includes elements from the domain of Bayesian Networks and Machine Learning. It is embedded into the cluster of excellence Nexus at the University of Stuttgart which has the aim to build a distributed context aware user-friendly system for sharing context data.

Extended TA Algorithm for Adapting a Situation Ontology

In this work we introduce an improved version of a learning algorithm for the automatic adaption of a situation ontology (TAA) [1] which extends the basic principle of the learning algorithm. The approach bases on the assumption of uncertain data and includes elements from the domain of Bayesian Networks and Machine Learning. It is embedded into the cluster of excellence Nexus at the University of Stuttgart which has the aim to build a distributed context aware system for sharing context data.

Event based distributed real-time communication architecture for multi-agent systems

In this paper an event-based distributed real-time communication architecture for multi-agent systems is presented. The architecture was designed regarding the needs of hardware-based multi-agent systems, especially robotic systems. This includes in particular fast and reliable transportation of messages in unstable wireless networks. Furthermore the architecture is usable for different agent-based software systems and allows communication between different systems even if they have a complete different representation of internal data. The architecture was evaluated in the RoboCup scenario with a multi-agent system of 5 robots interacting in a highly dynamic environment. Using this system, the RoboCup team of the University of Stuttgart won the RoboCup German Open Championship and World Championship in 2009.

Advanced Data Logging in RoboCup

In this work an advanced data logging approach for the RoboCup domain using an autonomous camera man is presented. It includes approaches from the field of real-time robot message logging, situation based camera control and 3D video visualisation. Based on the implementation of this work the RoboCup team of the IPVS of the University of Stuttgart won the first price in the scientific challenge of the RoboCup World Championship 2009 in Graz.

A Novel Framework for Anomaly Detection of Robot Behaviors

Autonomous mobile robots are designed to behave appropriately in changing real-world environments without human intervention. In order to satisfy the requirements of autonomy, robots have to cope with unknown settings and several issues of uncertainties in dynamic, unstructured and complex environments. A first step is to provide a robot with cognitive capabilities and the ability of self-examination to detect behavioral abnormalities. Unfortunately, most existing anomaly detection systems are neither suitable for the domain of robotic behavior nor flexible enough or even well generalizable. In the following article, we introduce a novel anomaly detection framework based on spatial-temporal models for robotic behaviors which is generally applicable for e.g., plan execution monitoring. The introduced framework combines the methodology of Kohonen’s Self-organizing Maps (SOMs) and Probabilistic Graphical Models (PGM) exploiting all advantages of both concepts. The underlying methods of the framework are discussed briefly, whereas the data-driven training of the spatial-temporal model and the reasoning process are described in detail. Finally, the framework is evaluated with different scenarios to emphasize its potential and its high level of generalization and flexibility in robotic application.

Physical Simulation of the Dynamical Behavior of Three-Wheeled Omni-directional Robots

Hardware simulation is a very efficient way for parameter tuning. We developed a Simulink-based simulator for the navigation components of our robotic soccer team. This physical simulation has interfaces to be interconnected with the higher levels of the real control software and is therefore able to perform an overall simulation of single robots.

A Generic Framework for Behavior Recognition of Complex Activities in Robotics

Considering the current state in service-robotics, an expert is still necessary to add new tasks and execution behaviors by textual and error-prone programming. Under the consideration that humans typically execute same activities almost identical (or at least similar) and further combine simple behaviors to more complex activities, we follow the constitutive assumption that all complex behaviors are composed of a limited set of atomic behaviors. This work introduces a generic framework for spatial-temporal analysis and classification of arbitrary atomic behaviors. Therefore, we propose the combination of Self-Organizing Maps (SOM) and Probabilistic Graphical Models (PGM) in order to exploit the advantages of both concepts. In this work, we describe the essential methods of the framework briefly, whereas the data-driven training of the spatial-temporal model and the reasoning process are described in detail. In order to demonstrate the potential and to emphasize the high level of generalization and flexibility in real-world environments, the framework is evaluated in an exemplary scenario.