Gerhard K Kraetzschmar | Bonn-Rhein-Sieg University of Applied Sciences (original) (raw)

Papers by Gerhard K Kraetzschmar

Research paper thumbnail of Miro: Middleware for autonomous mobile robots

citeseer. ist. psu. edu/ …

Implementing software for autonomous mobile robots is a non-trivial task, because such robots inc... more Implementing software for autonomous mobile robots is a non-trivial task, because such robots incorporate several sensor systems and actuators that must be controlled simultaneously by a heterogeneous ensemble of networked computers and microcontrollers. Additionally, the use of modern software engineering technologies like object-oriented and distributed programming and client/server architectures is essential in order to maintain program code effectively. In this paper, we present Miro, a new CORBA-based robot programming framework which allows a rapid development of reliable and safe software on heterogeneous computer networks and supports the mixed use of several programming languages. Copyright c 2001 IFAC

Research paper thumbnail of The Ulm Sparrows: Research into Sensorimotor Integration, Agency, Learning, and Multiagent Cooperation

Lecture Notes in Computer Science, 1999

We describe the motivations, research issues, current results, and future directions of The Ulm S... more We describe the motivations, research issues, current results, and future directions of The Ulm Sparrows, a project that aims at the design and implementation of a team of robotic soccer players.

Research paper thumbnail of SFB 527: Integration symbolischer und subsymbolischer Informationsverabeitung in adaptiven sensomotorischen Systemen

Research paper thumbnail of Hierarchical object classification for autonomous mobile robots

ABSTRACT An adaptive neural 3D-object recognition architecture for mobile robot applications is p... more ABSTRACT An adaptive neural 3D-object recognition architecture for mobile robot applications is presented. During training, a hierarchy of LVQ classifiers based on feature vectors with increasingly higher dimensionality is generated. The hierarchy is extended exactly in those regions of the feature space, where objects cannot be distinguished using lower-dimensional feature vectors. During recall, this system can produce object classifications in an anytime fashion with increasingly more detailed and higher confident results. Experimental data obtained from application to two real-world data sets are very encouraging. We found many of the confusion classes to represent meaningful concepts, with obvious implications for symbol grounding and integration of subsymbolic and symbolic representations.

Research paper thumbnail of Biomimetic Neural Learning for Intelligent Robots

This book presents research performed as part of the EU project on biomimetic multimodal learning... more This book presents research performed as part of the EU project on biomimetic multimodal learning in a mirror neuron-based robot (MirrorBot) and contributions presented at the International AI-Workshop in NeuroBotics. The overall aim of the book is to present a broad spectrum of current research into biomimetic neural learning for intelligent autonomous robots. There is a need for a new type of robots which is inspired by nature and so performs in a more flexible learned manner than current robots. This new type of robots is driven by recent new theories and experiments in neuroscience indicating that a biological and neuroscience-oriented approach could lead to new life-like robotic systems. The book focuses on some of the research progress made in the MirrorBot project which uses concepts from mirror neurons as a basis for the integration of vision, language and action. In this book we show the development of new techniques using cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We have developed biomimetic multimodal learning and language instruction in a robot to investigate the task of searching for objects. As well as the research performed in this area for the MirrorBot project, the second part of this book incorporates significant contributes from other research in the field of biomimetic robotics. This second part of the book concentrate on the progress made in neuroscience inspired robotic learning approaches (in short: Neuro-Botics). We hope that this book stimulates and encourages new research in this interesting and dynamic area. We would like to thank all contributors to this book, all the researchers and administrative staff within the MirrorBot project, the reviewers of the chapters and all the participants at the AI-Workshop in NeuroBotics.

Research paper thumbnail of Managing multiple contexts efficiently

Research paper thumbnail of BRICS - Best practice in robotics

In the past, the process of developing a new robot application has had more of the design of a pi... more In the past, the process of developing a new robot application has had more of the design of a piece of artwork or of an act of ingenious engineering than of a structured and formalized process. The prime objective of BRICS is to structure and formalize the robot development process itself and to provide tools, models, and functional libraries, which allow reducing the development time by a magnitude. BRICS is working together with academic as well as industrial providers of robotics “components” (hardware and software), to identify and document best practices in the development of complex robotics systems, to refactor (together) the existing components in order to achieve a much higher level of reusability and robustness, and to support the robot development process with a structured tool chain and code repository. BRICS is a joint research project funded by the European Commission ICT Challenge 2 under grant number 231940. First results include the analysis of existing robot devel...

Research paper thumbnail of Concurrent Object Identification and Localization for a Mobile Robot

Künstliche Intelligenz, 2000

Identification and localization of task-relevant objects is an essential problem for advanced ser... more Identification and localization of task-relevant objects is an essential problem for advanced service robots. We integrate state-of-the-art techniques both for object identification and object localization to solve this problem. Based on a multi- level spatial representation architecture, our approach inte- grates methods for mapping, self-localization and spatial rea- soning for navigation with visual attention, feature detection, and hierarchical neural classifiers.

Research paper thumbnail of Unified Closed Form Inverse Kinematics for the KUKA youBot

Mobile manipulators are of high interest to industry because of the increased flexibility and eff... more Mobile manipulators are of high interest to industry because of the increased flexibility and effectiveness they offer. The combination and coordination of the mobility provided by a mobile platform and of the manipulation capabilities provided by a robot arm leads to complex analytical problems for research. These problems can be studied very well on the KUKA youBot, a mobile manipulator designed for education and research applications. Issues still open in research include solving the inverse kinematics problem for the unified kinematics of the mobile manipulator, including handling the kinematic redundancy introduced by the holonomic platform of the KUKA youBot. As the KUKA youBot arm has only 5 degrees of freedom, a unified platform and manipulator system is needed to compensate for the missing degree of freedom. We present the KUKA youBot as an 8 degree of freedom serial kinematic chain, suggest appropriate redundancy parameters, and solve the inverse kinematics for the 8 degre...

Research paper thumbnail of Overview of RoboCup-99

Lecture Notes in Computer Science, 2000

Research paper thumbnail of The Ulm Sparrows 2003

RoboCup International Symposium, 2000

The Ulm Sparrows is a team of researchers, students, and robots competing in the RoboCup middle-s... more The Ulm Sparrows is a team of researchers, students, and robots competing in the RoboCup middle-size league. This paper de- scribes our research approach, major results achieved so far, and current work.

Research paper thumbnail of Declarative Specification of Robot Perception Architectures

Service robots become increasingly capable and deliver a broader spectrum of services which all r... more Service robots become increasingly capable and deliver a broader spectrum of services which all require a wide range of perceptual capabilities. These capabilities must cope with dynamically changing requirements which make the design and implementation of a robot perception architecture a complex and tedious exercise which is prone to error. We suggest to specify the integral parts of robot perception architectures using explicit models, which allows to easily configure, modify, and validate them. The paper presents the domain-specific language RPSL, some examples of its application, the current state of implementation and some validation experiments.

Research paper thumbnail of Towards a robot perception specification language

In this paper we present our work in progress towards a domain-specific language called Robot Per... more In this paper we present our work in progress towards a domain-specific language called Robot Perception Specification Language (RPSL). RSPL provide means to specify the expected result (task knowledge) of a Robot Perception Architecture in a declarative and framework-independent manner.

Research paper thumbnail of Overview of RoboCup99

RoboCup International Symposium, 1999

Abstract: of competitions and events designed to promote the full integration ofAI and robotics r... more Abstract: of competitions and events designed to promote the full integration ofAI and robotics research. Following the first RoboCup, held in Nagoya in1997, RoboCup-98 was held in Paris from July 2--9, 1998, overlapping withthe real World Cup soccer competition. RoboCup-98 included competitions inthree leagues: the simulation league, the small-size real robot league, and themiddle-size real robot league. Champion teams were

Research paper thumbnail of RoboCup 2004 Competitions and Symposium: A Small Kick for Robots, a Giant Score for Science

Ai Magazine, 2005

RoboCup is an international initiative with the main goals of fostering research and education in... more RoboCup is an international initiative with the main goals of fostering research and education in Artificial Intelligence and Robotics, as well as of promoting science and technology to world citizens. The idea is to provide a standard problem where a wide range of technologies can be integrated and examined, as well as being used for project-oriented education, and to organize

Research paper thumbnail of Visual Robot Detection in RoboCup Using Neural Networks

Robot recognition is a very important point for further improvements in game-play in RoboCup midd... more Robot recognition is a very important point for further improvements in game-play in RoboCup middle size league. In this paper we present a neural recognition method we developed to find robots using different visual information. Two algorithms are introduced to detect possible robot areas in an image and a subsequent recognition method with two combined multi-layer perceptrons is used to classify this areas regarding different features. The presented results indicate a very good overall performance of this approach.

Research paper thumbnail of Vision-Based Robot Localization Using Sporadic Features

Abstract: Knowing its position in an environment is an essential capability forany useful mobile ... more Abstract: Knowing its position in an environment is an essential capability forany useful mobile robot. Monte-Carlo Localization (MCL) has becomea popular framework for solving the self-localization problem in mobilerobots. The known methods exploit sensor data obtained from laser rangenders or sonar rings to estimate robot positions and are quite reliable androbust against noise. An open question is whether comparable localizationperformance can be achieved using only camera images,...

Research paper thumbnail of Vision-based Localization in RoboCup Environments

Knowing its position in an environment is an essential capability for any useful mobile robot. Mo... more Knowing its position in an environment is an essential capability for any useful mobile robot. Monte-Carlo Localization (MCL) has become a popular framework for solving the self-localization problem in mobile robots. The known methods exploit sensor data obtained from laser range finders or sonar rings to estimate robot positions and are quite reliable and robust against noise. An open question

Research paper thumbnail of Vision-based localization for mobile robots

In this paper, we describe methods to localize a mobile robot in an indoor environment from visua... more In this paper, we describe methods to localize a mobile robot in an indoor environment from visual information. An appearance-based approach is adopted in which the environment is represented by a large set of images from which features are extracted. We extended the appearance based approach with an active vision component, which fits well in our probabilistic framework. We also describe another extension, in which depth information is used next to intensity information. The results of our experiments show that a localization accuracy of less then 50 cm can be achieved even when there are un-modeled changes in the environment or in the lighting conditions.

Research paper thumbnail of RoboCup 2000: Robot Soccer World Cup IV

This book is the fourth offical archival publication devoted to RoboCup and documents the achieve... more This book is the fourth offical archival publication devoted to RoboCup and documents the achievements presented at the Fourth Robot World Cup Soccer Games and Conferences, RoboCup 2000, held in Melbourne, Australia, in August/September 2000. The book presents the following parts: introductory overview and survey, championship papers by the winners of the competitions, finalist papers for the RoboCup challenge awards, papers and posters presented at the workshop, team description of a large number of participating ...

Research paper thumbnail of Miro: Middleware for autonomous mobile robots

citeseer. ist. psu. edu/ …

Implementing software for autonomous mobile robots is a non-trivial task, because such robots inc... more Implementing software for autonomous mobile robots is a non-trivial task, because such robots incorporate several sensor systems and actuators that must be controlled simultaneously by a heterogeneous ensemble of networked computers and microcontrollers. Additionally, the use of modern software engineering technologies like object-oriented and distributed programming and client/server architectures is essential in order to maintain program code effectively. In this paper, we present Miro, a new CORBA-based robot programming framework which allows a rapid development of reliable and safe software on heterogeneous computer networks and supports the mixed use of several programming languages. Copyright c 2001 IFAC

Research paper thumbnail of The Ulm Sparrows: Research into Sensorimotor Integration, Agency, Learning, and Multiagent Cooperation

Lecture Notes in Computer Science, 1999

We describe the motivations, research issues, current results, and future directions of The Ulm S... more We describe the motivations, research issues, current results, and future directions of The Ulm Sparrows, a project that aims at the design and implementation of a team of robotic soccer players.

Research paper thumbnail of SFB 527: Integration symbolischer und subsymbolischer Informationsverabeitung in adaptiven sensomotorischen Systemen

Research paper thumbnail of Hierarchical object classification for autonomous mobile robots

ABSTRACT An adaptive neural 3D-object recognition architecture for mobile robot applications is p... more ABSTRACT An adaptive neural 3D-object recognition architecture for mobile robot applications is presented. During training, a hierarchy of LVQ classifiers based on feature vectors with increasingly higher dimensionality is generated. The hierarchy is extended exactly in those regions of the feature space, where objects cannot be distinguished using lower-dimensional feature vectors. During recall, this system can produce object classifications in an anytime fashion with increasingly more detailed and higher confident results. Experimental data obtained from application to two real-world data sets are very encouraging. We found many of the confusion classes to represent meaningful concepts, with obvious implications for symbol grounding and integration of subsymbolic and symbolic representations.

Research paper thumbnail of Biomimetic Neural Learning for Intelligent Robots

This book presents research performed as part of the EU project on biomimetic multimodal learning... more This book presents research performed as part of the EU project on biomimetic multimodal learning in a mirror neuron-based robot (MirrorBot) and contributions presented at the International AI-Workshop in NeuroBotics. The overall aim of the book is to present a broad spectrum of current research into biomimetic neural learning for intelligent autonomous robots. There is a need for a new type of robots which is inspired by nature and so performs in a more flexible learned manner than current robots. This new type of robots is driven by recent new theories and experiments in neuroscience indicating that a biological and neuroscience-oriented approach could lead to new life-like robotic systems. The book focuses on some of the research progress made in the MirrorBot project which uses concepts from mirror neurons as a basis for the integration of vision, language and action. In this book we show the development of new techniques using cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We have developed biomimetic multimodal learning and language instruction in a robot to investigate the task of searching for objects. As well as the research performed in this area for the MirrorBot project, the second part of this book incorporates significant contributes from other research in the field of biomimetic robotics. This second part of the book concentrate on the progress made in neuroscience inspired robotic learning approaches (in short: Neuro-Botics). We hope that this book stimulates and encourages new research in this interesting and dynamic area. We would like to thank all contributors to this book, all the researchers and administrative staff within the MirrorBot project, the reviewers of the chapters and all the participants at the AI-Workshop in NeuroBotics.

Research paper thumbnail of Managing multiple contexts efficiently

Research paper thumbnail of BRICS - Best practice in robotics

In the past, the process of developing a new robot application has had more of the design of a pi... more In the past, the process of developing a new robot application has had more of the design of a piece of artwork or of an act of ingenious engineering than of a structured and formalized process. The prime objective of BRICS is to structure and formalize the robot development process itself and to provide tools, models, and functional libraries, which allow reducing the development time by a magnitude. BRICS is working together with academic as well as industrial providers of robotics “components” (hardware and software), to identify and document best practices in the development of complex robotics systems, to refactor (together) the existing components in order to achieve a much higher level of reusability and robustness, and to support the robot development process with a structured tool chain and code repository. BRICS is a joint research project funded by the European Commission ICT Challenge 2 under grant number 231940. First results include the analysis of existing robot devel...

Research paper thumbnail of Concurrent Object Identification and Localization for a Mobile Robot

Künstliche Intelligenz, 2000

Identification and localization of task-relevant objects is an essential problem for advanced ser... more Identification and localization of task-relevant objects is an essential problem for advanced service robots. We integrate state-of-the-art techniques both for object identification and object localization to solve this problem. Based on a multi- level spatial representation architecture, our approach inte- grates methods for mapping, self-localization and spatial rea- soning for navigation with visual attention, feature detection, and hierarchical neural classifiers.

Research paper thumbnail of Unified Closed Form Inverse Kinematics for the KUKA youBot

Mobile manipulators are of high interest to industry because of the increased flexibility and eff... more Mobile manipulators are of high interest to industry because of the increased flexibility and effectiveness they offer. The combination and coordination of the mobility provided by a mobile platform and of the manipulation capabilities provided by a robot arm leads to complex analytical problems for research. These problems can be studied very well on the KUKA youBot, a mobile manipulator designed for education and research applications. Issues still open in research include solving the inverse kinematics problem for the unified kinematics of the mobile manipulator, including handling the kinematic redundancy introduced by the holonomic platform of the KUKA youBot. As the KUKA youBot arm has only 5 degrees of freedom, a unified platform and manipulator system is needed to compensate for the missing degree of freedom. We present the KUKA youBot as an 8 degree of freedom serial kinematic chain, suggest appropriate redundancy parameters, and solve the inverse kinematics for the 8 degre...

Research paper thumbnail of Overview of RoboCup-99

Lecture Notes in Computer Science, 2000

Research paper thumbnail of The Ulm Sparrows 2003

RoboCup International Symposium, 2000

The Ulm Sparrows is a team of researchers, students, and robots competing in the RoboCup middle-s... more The Ulm Sparrows is a team of researchers, students, and robots competing in the RoboCup middle-size league. This paper de- scribes our research approach, major results achieved so far, and current work.

Research paper thumbnail of Declarative Specification of Robot Perception Architectures

Service robots become increasingly capable and deliver a broader spectrum of services which all r... more Service robots become increasingly capable and deliver a broader spectrum of services which all require a wide range of perceptual capabilities. These capabilities must cope with dynamically changing requirements which make the design and implementation of a robot perception architecture a complex and tedious exercise which is prone to error. We suggest to specify the integral parts of robot perception architectures using explicit models, which allows to easily configure, modify, and validate them. The paper presents the domain-specific language RPSL, some examples of its application, the current state of implementation and some validation experiments.

Research paper thumbnail of Towards a robot perception specification language

In this paper we present our work in progress towards a domain-specific language called Robot Per... more In this paper we present our work in progress towards a domain-specific language called Robot Perception Specification Language (RPSL). RSPL provide means to specify the expected result (task knowledge) of a Robot Perception Architecture in a declarative and framework-independent manner.

Research paper thumbnail of Overview of RoboCup99

RoboCup International Symposium, 1999

Abstract: of competitions and events designed to promote the full integration ofAI and robotics r... more Abstract: of competitions and events designed to promote the full integration ofAI and robotics research. Following the first RoboCup, held in Nagoya in1997, RoboCup-98 was held in Paris from July 2--9, 1998, overlapping withthe real World Cup soccer competition. RoboCup-98 included competitions inthree leagues: the simulation league, the small-size real robot league, and themiddle-size real robot league. Champion teams were

Research paper thumbnail of RoboCup 2004 Competitions and Symposium: A Small Kick for Robots, a Giant Score for Science

Ai Magazine, 2005

RoboCup is an international initiative with the main goals of fostering research and education in... more RoboCup is an international initiative with the main goals of fostering research and education in Artificial Intelligence and Robotics, as well as of promoting science and technology to world citizens. The idea is to provide a standard problem where a wide range of technologies can be integrated and examined, as well as being used for project-oriented education, and to organize

Research paper thumbnail of Visual Robot Detection in RoboCup Using Neural Networks

Robot recognition is a very important point for further improvements in game-play in RoboCup midd... more Robot recognition is a very important point for further improvements in game-play in RoboCup middle size league. In this paper we present a neural recognition method we developed to find robots using different visual information. Two algorithms are introduced to detect possible robot areas in an image and a subsequent recognition method with two combined multi-layer perceptrons is used to classify this areas regarding different features. The presented results indicate a very good overall performance of this approach.

Research paper thumbnail of Vision-Based Robot Localization Using Sporadic Features

Abstract: Knowing its position in an environment is an essential capability forany useful mobile ... more Abstract: Knowing its position in an environment is an essential capability forany useful mobile robot. Monte-Carlo Localization (MCL) has becomea popular framework for solving the self-localization problem in mobilerobots. The known methods exploit sensor data obtained from laser rangenders or sonar rings to estimate robot positions and are quite reliable androbust against noise. An open question is whether comparable localizationperformance can be achieved using only camera images,...

Research paper thumbnail of Vision-based Localization in RoboCup Environments

Knowing its position in an environment is an essential capability for any useful mobile robot. Mo... more Knowing its position in an environment is an essential capability for any useful mobile robot. Monte-Carlo Localization (MCL) has become a popular framework for solving the self-localization problem in mobile robots. The known methods exploit sensor data obtained from laser range finders or sonar rings to estimate robot positions and are quite reliable and robust against noise. An open question

Research paper thumbnail of Vision-based localization for mobile robots

In this paper, we describe methods to localize a mobile robot in an indoor environment from visua... more In this paper, we describe methods to localize a mobile robot in an indoor environment from visual information. An appearance-based approach is adopted in which the environment is represented by a large set of images from which features are extracted. We extended the appearance based approach with an active vision component, which fits well in our probabilistic framework. We also describe another extension, in which depth information is used next to intensity information. The results of our experiments show that a localization accuracy of less then 50 cm can be achieved even when there are un-modeled changes in the environment or in the lighting conditions.

Research paper thumbnail of RoboCup 2000: Robot Soccer World Cup IV

This book is the fourth offical archival publication devoted to RoboCup and documents the achieve... more This book is the fourth offical archival publication devoted to RoboCup and documents the achievements presented at the Fourth Robot World Cup Soccer Games and Conferences, RoboCup 2000, held in Melbourne, Australia, in August/September 2000. The book presents the following parts: introductory overview and survey, championship papers by the winners of the competitions, finalist papers for the RoboCup challenge awards, papers and posters presented at the workshop, team description of a large number of participating ...