Johannes Pellenz | Universität Koblenz (original) (raw)

Papers by Johannes Pellenz

The main task of rescue robots is to locate victims after a desaster such as an earthquake. For t... more The main task of rescue robots is to locate victims after a desaster such as an earthquake. For this task sensor data is used to localize the robots in their environment, build maps, and mark the victims in the maps. Usually, thermal and color cameras, monitored by a human operator, are used for the detection. Hyperspectral imaging techniques are today used for industrial tasks such as quality control, fast material sorting or food analysis. This paper proposes a new approach for the victim detection in rescue environments, based on hyperspectral imaging in the near infrared spectral domain. This technique involves a simultaneous recording of spatial and spectral information. Different materials can be distinguished when the spectra are analyzed. The result of the experiments show that the spectra of skin are very characteristic and that even under the impact of ash layers the spectral similarity remains very high. Thus our approach can be used for rescue robots to find human bodies autonomously, where other techniques such as color or thermal image analysis would fail.

ABSTRACT The 2012 IEEE Robotics and Automation Society Safety, Security, and Rescue Robotics Summ... more ABSTRACT The 2012 IEEE Robotics and Automation Society Safety, Security, and Rescue Robotics Summer School was held from the 9th to the 15th of September in Alanya, Turkey, and brought together a select group of students, researchers, responders, manufacturers, and standards organization representatives for a week of learning, dissemination of challenges and best-in-class solutions, and networking. This event builds on a series of summer schools that started in Rome in 2004 and were significant in their combination of lectures, hands-on practicals, and networking opportunities, all carried out in one all-inclusive venue. In this paper, we report on the outcomes and novel aspects of the latest incarnation of this event.

Lecture Notes in Computer Science, 2015

The RoboCup Rescue Robot League (RRL) aims to foster the development of rescue robots that can be... more The RoboCup Rescue Robot League (RRL) aims to foster the development of rescue robots that can be used after disasters such as earthquakes. These robots help to discover victims in the collapsed structure without endanger the rescue personnel. The RRL has been held since 2000. The experience gained during these competitions has increased the level of maturity of the field, which allowed to deploy robots after real disasters, e.g. at the Fukushima Daiichi nuclear disaster. This article provides an overview on the competition and its history. It also highlights the current state of the art, the current challenges and the way ahead.

Mapping is an important task for mobile robots in general and for Safety, Security, and Rescue Ro... more Mapping is an important task for mobile robots in general and for Safety, Security, and Rescue Robotics (SSRR) in particular. It is hence one core aspect which is evaluated in the RoboCup Rescue league. But assessing the quality of maps in a simple and efficient way is not trivial, especially if no detailed, complete ground truth data of the environment is available. A new approach on map evaluation is presented here. It makes use of artificial objects placed in the environment named "fiducials". Using the known ground-truth positions and the positions of the fiducials identified in the map, a number of quality attributes can be assigned to that map. Depending on the application domain those attributes can weighed to compute a final score. Results are presented that are based on using this method during the RoboCup Rescue competition 2010 in Singapore where maps were generated by different teams in an maze populated with fiducials. Those maps are evaluated here and compared to a human judgment, showing the effectiveness of the fiducial approach.

Mapping is an important task for mobile robots. Assessing the quality of those maps is an open to... more Mapping is an important task for mobile robots. Assessing the quality of those maps is an open topic. A new approach on map evaluation is presented here. It makes use of artificial objects placed in the environment named "Fiducials". Using the known ground-truth positions and the positions of the fiducials identified in the map, a number of quality attributes can be assigned to that map. Those attributes are weighed to compute a final score depending on the application domain. During the 2010 NIST Response Robot Evaluation Exercise at Disaster City an area was populated with fiducials and different mapping runs were performed. The maps generated there are assessed in this paper demonstrating the Fiducial approach. Finally this map scoring algorithm is compared to other approaches found in literature.

This paper gives a description of the robot hardware and software used by team homer@UniKoblenz, ... more This paper gives a description of the robot hardware and software used by team homer@UniKoblenz, which participates in RoboCup@home 2009. A Special Focus is put on novel scientific achievements and newly developed features with respect to last year's competition.

The main task of rescue robots is to locate victims after a desaster such as an earthquake. For t... more The main task of rescue robots is to locate victims after a desaster such as an earthquake. For this task sensor data is used to localize the robots in their environment, build maps, and mark the victims in the maps. Usually, thermal and color cameras, monitored by a human operator, are used for the detection. Hyperspectral imaging techniques are today used for industrial tasks such as quality control, fast material sorting or food analysis. This paper proposes a new approach for the victim detection in rescue environments, based on hyperspectral imaging in the near infrared spectral domain. This technique involves a simultaneous recording of spatial and spectral information. Different materials can be distinguished when the spectra are analyzed. The result of the experiments show that the spectra of skin are very characteristic and that even under the impact of ash layers the spectral similarity remains very high. Thus our approach can be used for rescue robots to find human bodies autonomously, where other techniques such as color or thermal image analysis would fail.

Three-dimensional laser range finders provide autonomous systems with vast amounts of information... more Three-dimensional laser range finders provide autonomous systems with vast amounts of information. However, autonomous robots navigating in unstructured environments are usually not interested in every geometric detail of their surroundings. Instead, they require realtime information about the location of obstacles and the condition of drivable areas. In this paper, we first present grid-based algorithms for classifying regions as either drivable or not. In a subsequent step, drivable regions are further examined using a novel algorithm which determines the local terrain roughness. This information can be used by a path planning algorithm to decide whether to prefer a rough, muddy area, or a plain street, which would not be possible using binary drivability information only.

Autonomous robots in rescue environments have to fulfill several task at the same time: They have... more Autonomous robots in rescue environments have to fulfill several task at the same time: They have to localize themselves, build maps, detect victims and decide where to go next for further exploration. In this contribution we present an approach that provides a robust solution for the exploration task: Based on the knowledge of the environment that the robot has already acquired, the algorithm calculates a path to the next interesting "frontier". Our comprehensive approach takes into account the distance to the next frontier and the difficulty of the path for the robot. Those difficulties can result from narrow passages but also from wide, open spaces where the sensors cannot detect any landmark. For the native exploration task, the algorithm is fed with occupancy grids. For the search task, it can also process maps that encode additional information, e. g. places that have not been searched by other sensors yet. The Exploration Transform was successfully implemented on our mobile system Robbie and was used during the RoboCup German Open 2007 and the RoboCup World Championship 2007. Using this approach, our Team "resko" achieved the "Best in Class Autonomy Award" in the Rescue Robot League in both competitions.

Springer eBooks, 2011

Autonomous robots in real world applications have to deal with a complex 3D environment, but are ... more Autonomous robots in real world applications have to deal with a complex 3D environment, but are often equipped with standard 2D laser range finders (LRF) only. By using the 2D LRF for both, the 2D localization and mapping (which can be done efficiently and precisely) and for the 3D obstacle detection (which makes the robot move safely), a completely autonomous robot can be built with affordable 2D LRFs. We use the 2D LRF to perform particle filter based SLAM to generate a 2D occupancy grid, and the same LRF (moved by two servo motors) to acquire 3D scans to detect obstacles not visible in the 2D scans. The 3D data is analyzed with a recursive principal component analysis (PCA) based method, and the detected obstacles are recorded in a separate obstacle map. This obstacle map and the occupancy map are merged for the path planning. Our solution was tested on our mobile system Robbie during the RoboCup Rescue competitions in 2008 and 2009, winning the mapping challenge at the world championship 2008 and the German Open in 2009. This shows that the benefit of a sensor can dramatically be increased by actively controlling it, and that mixed 2D/3D perception can efficiently be achieved with a standard 2D sensor by controlling it actively.

Advanced Robotics and its Social Impacts, Oct 1, 2011

The RoboCupRescue Robot League is an international competition where teams from all over the worl... more The RoboCupRescue Robot League is an international competition where teams from all over the world compete against an arena that allows them to demonstrate their advanced robotic capabilities for emergency response applications. The league is also a community that works together to advance the state-of-the-art towards improving performance and the standards that help quantify this performance. In this paper, we present the current state of the competition, its links to the wider standardization process and how it is guiding robots towards fieldable capabilities.

ABSTRACT The tasks of autonomous rescue robots operating in unknown environments are manifold. Se... more ABSTRACT The tasks of autonomous rescue robots operating in unknown environments are manifold. Self localization, map generation and the detection of possible victims are indespensable. Apart from these, other factors can become crucial for the survival of the involved persons and for the safe operation of the robot itself. A first step in autonomously detecting such dangers is the real-time recognition of standardized danger signs in camera images. The knowledge of such information can be incorporated into the exploration algorithm as well as enhance the generated maps for later usage by human rescue teams. Our approach is a combination of histogram backprojection and speeded up robust feature (SURF) matching. The first one is used to detect regions of interest within the image. In the second step, interest points are extracted and their features are calculated. These features are then matched against the samples in a database, taking into account the constraints resulting from the affine transformation of the matching objects. We have tested the approach on a set of 240 scene images containing 5 different kinds of hazard signs. In 90 images, none of the signs was present, but objects of similar size and color. The approach detected 92% of the signs if the signs filled at least five percent of the pixels in the 1024 times 768 pixels image. None of the fake objects were detected as a hazmat sign in these experiments. The approach was implemented and successfully tested in practice on our mobile system "Robbie X", which was used by the team "resko" at the RoboCup World Championship 2008 in Suzhou, China.

Springer eBooks, 2010

Often Particle Filters are used to solve the SLAM (Simultaneous Localization and Mapping) problem... more Often Particle Filters are used to solve the SLAM (Simultaneous Localization and Mapping) problem in robotics: The particles represent the possible poses of the robot, and their weight is determined by checking if the sensor readings are consistent with the so far acquired map. Mostly a single map is maintained during the exploration, and only with Rao-Blackwellized Particle Filters each particle carries its own map. In this contribution, we propose a Hyper Particle Filter (HPF)-a Particle Filter of Particle Filters-for solving the SLAM problem in unstructured environments. Each particle of the HPF contains a standard Particle Filter (with a map and a set particles, that model the belief of the robot pose in this particular map). To measure the weight of a particle in the HPF, we developed two map quality measures that can be calculated automatically and do not rely on a ground truth map: The first map quality measure determines the contrast of the occupancy map. If the map has a high contrast, it is likely that the pose of the robot was always determined correctly before the map was updated, which finally leads to an overall consistent map. The second map quality measure determines the distribution of the orientation of wall pixels calculated by the Sobel operator. Using the model of a rectangular overall structure, slight but systematic errors in the map can be detected. Using the two measures, broken maps can automatically be detected. The corresponding particle is then more likely to be replaced by a particle with a better map within the HPF. We implemented the approach on our robot "Robbie 12", which will be used in the RoboCup Rescue league in 2009. We tested the HPF using the log files from last years RoboCup Rescue autonomy final, and with new data of a larger building. The quality of the generated maps outperformed our last years (league's best) maps. With the data acquired in the larger structure, Robbie was able to close loops in the map. Due to a highly efficient implementation, the algorithm still runs online during the autonomous exploration.

101 Reports on the Workshops Held at the Sixth International

Abstract: Designing a generic robot system architecture is a challenging task. Many design goals,... more Abstract: Designing a generic robot system architecture is a challenging task. Many design goals, such as scalability, applicability to various scenarios, easy integration of soft- and hardware, and reusability of components need to be considered. The code has to be kept easy to read and maintainable by developers and researchers. In this paper we describe the message-based software architecture Robbie that was specifically designed to address these goals. It has been successfully applied to fulfill various and complex tasks for different robots and scenarios in the context of autonomous mobile systems. We also examine how Robbie is related to the widely spread robot operating system ROS. 1

Maintenance cannot be looked at detached from other software development processes as it plays a ... more Maintenance cannot be looked at detached from other software development processes as it plays a crucial role in the software life cycle. In this thesis I have outlined how the perception of maintenance has changed over the years and what is now considered to be important. I have determined maintenance activities in theory and practice in the context of software process models for the use of academics and practitioners. I assumed the role of an interpretive traveller, first looking at different theoretical perspectives, then investigating current practices and finally bringing it together to establish a maintenance workflow within the context of the Rational Unified Process.

International Journal of Intelligent Defence Support Systems, 2021

This paper describes the research and experiment efforts of the NATO STO group IST-149-RTG capabi... more This paper describes the research and experiment efforts of the NATO STO group IST-149-RTG capability concept demonstrator for interoperability within unmanned ground systems and C2 and the NAAG team of experts on UGV. The main purpose of the group was to investigate possible standards for controlling UGVs and tests them in a real world scenario. The efforts have been two folded, where the first effort was two NATO groups having an experiment demonstrating interoperability between the UGVs and OCUs available within the group. The Belgium contribution is done in the EU project ICARUS. Both efforts used the Joint Architecture for Unmanned Systems (JAUS) with the interoperability profile (IOP) to successfully enable interoperability between the systems. The trials showed that it is possible to extend the systems quite easily and achieve compliance with parts of the standard in a relatively short time.

Themaintaskofrescue robots istolocate victims after adesaster suchasanearthquake. Forthis tasksen... more Themaintaskofrescue robots istolocate victims after adesaster suchasanearthquake. Forthis tasksensor datais usedtolocalize therobots intheir environment, build maps, and markthevictims inthemaps.Usually, thermal andcolor cameras, monitored byahumanoperator, areusedforthedetection. Hyperspectral imaging techniques aretoday usedforindustrial tasks suchasquality control, fast material sorting orfoodanalysis. Thispaperproposes anewapproach forthevictim detection in rescue environments, basedonhyperspectral imaging inthenear infrared spectral domain. Thistechnique involves a simultaneous recording ofspatial andspectral information. Different materials can bedistinguished whenthespectra areanalyzed. Theresult oftheexperiments showthat thespectra ofskin are verycharacteristic andthat evenunder theimpact ofashlayers the spectral similarity remains veryhigh. Thusourapproach canbeused forrescue robots tofind humanbodies autonomously whereother techniques suchascolor orthermal imageanalysis wo...

This paper describes our approach for the RoboCup 2006 Rescue League. The mobile system we use is... more This paper describes our approach for the RoboCup 2006 Rescue League. The mobile system we use is based on an ActivMedia Pineer 3 AT. It is equipped with a four wheel drive and sonar sensors in the front and in the back. On this platform, an alumnium rack is installed where the other devices are attached to: A self made stereo camera system (consisting of two high resolution Sony FireWire cameras), an electronic compass and a HOKUYU laser range finder (LRF). In addition, a third FireWire camera is attached to the back of the robot to give a rear view. The robot is manually controlled from a client computer, which is operated by one team member. The map building is done by the computer automatically by merging the collected LRF data with the depth information aquired by the stereo system. The operator can adjust the map proposed by the computer by correcting wrong matches. The victim detection has to be done by human observations using the visual cameras. The system was develpoped by...

Kundenbindung durch kosteneffiziente Service Excellence, 2016

The main task of rescue robots is to locate victims after a desaster such as an earthquake. For t... more The main task of rescue robots is to locate victims after a desaster such as an earthquake. For this task sensor data is used to localize the robots in their environment, build maps, and mark the victims in the maps. Usually, thermal and color cameras, monitored by a human operator, are used for the detection. Hyperspectral imaging techniques are today used for industrial tasks such as quality control, fast material sorting or food analysis. This paper proposes a new approach for the victim detection in rescue environments, based on hyperspectral imaging in the near infrared spectral domain. This technique involves a simultaneous recording of spatial and spectral information. Different materials can be distinguished when the spectra are analyzed. The result of the experiments show that the spectra of skin are very characteristic and that even under the impact of ash layers the spectral similarity remains very high. Thus our approach can be used for rescue robots to find human bodies autonomously, where other techniques such as color or thermal image analysis would fail.

ABSTRACT The 2012 IEEE Robotics and Automation Society Safety, Security, and Rescue Robotics Summ... more ABSTRACT The 2012 IEEE Robotics and Automation Society Safety, Security, and Rescue Robotics Summer School was held from the 9th to the 15th of September in Alanya, Turkey, and brought together a select group of students, researchers, responders, manufacturers, and standards organization representatives for a week of learning, dissemination of challenges and best-in-class solutions, and networking. This event builds on a series of summer schools that started in Rome in 2004 and were significant in their combination of lectures, hands-on practicals, and networking opportunities, all carried out in one all-inclusive venue. In this paper, we report on the outcomes and novel aspects of the latest incarnation of this event.

Lecture Notes in Computer Science, 2015

The RoboCup Rescue Robot League (RRL) aims to foster the development of rescue robots that can be... more The RoboCup Rescue Robot League (RRL) aims to foster the development of rescue robots that can be used after disasters such as earthquakes. These robots help to discover victims in the collapsed structure without endanger the rescue personnel. The RRL has been held since 2000. The experience gained during these competitions has increased the level of maturity of the field, which allowed to deploy robots after real disasters, e.g. at the Fukushima Daiichi nuclear disaster. This article provides an overview on the competition and its history. It also highlights the current state of the art, the current challenges and the way ahead.

Mapping is an important task for mobile robots in general and for Safety, Security, and Rescue Ro... more Mapping is an important task for mobile robots in general and for Safety, Security, and Rescue Robotics (SSRR) in particular. It is hence one core aspect which is evaluated in the RoboCup Rescue league. But assessing the quality of maps in a simple and efficient way is not trivial, especially if no detailed, complete ground truth data of the environment is available. A new approach on map evaluation is presented here. It makes use of artificial objects placed in the environment named "fiducials". Using the known ground-truth positions and the positions of the fiducials identified in the map, a number of quality attributes can be assigned to that map. Depending on the application domain those attributes can weighed to compute a final score. Results are presented that are based on using this method during the RoboCup Rescue competition 2010 in Singapore where maps were generated by different teams in an maze populated with fiducials. Those maps are evaluated here and compared to a human judgment, showing the effectiveness of the fiducial approach.

Mapping is an important task for mobile robots. Assessing the quality of those maps is an open to... more Mapping is an important task for mobile robots. Assessing the quality of those maps is an open topic. A new approach on map evaluation is presented here. It makes use of artificial objects placed in the environment named "Fiducials". Using the known ground-truth positions and the positions of the fiducials identified in the map, a number of quality attributes can be assigned to that map. Those attributes are weighed to compute a final score depending on the application domain. During the 2010 NIST Response Robot Evaluation Exercise at Disaster City an area was populated with fiducials and different mapping runs were performed. The maps generated there are assessed in this paper demonstrating the Fiducial approach. Finally this map scoring algorithm is compared to other approaches found in literature.

This paper gives a description of the robot hardware and software used by team homer@UniKoblenz, ... more This paper gives a description of the robot hardware and software used by team homer@UniKoblenz, which participates in RoboCup@home 2009. A Special Focus is put on novel scientific achievements and newly developed features with respect to last year's competition.

The main task of rescue robots is to locate victims after a desaster such as an earthquake. For t... more The main task of rescue robots is to locate victims after a desaster such as an earthquake. For this task sensor data is used to localize the robots in their environment, build maps, and mark the victims in the maps. Usually, thermal and color cameras, monitored by a human operator, are used for the detection. Hyperspectral imaging techniques are today used for industrial tasks such as quality control, fast material sorting or food analysis. This paper proposes a new approach for the victim detection in rescue environments, based on hyperspectral imaging in the near infrared spectral domain. This technique involves a simultaneous recording of spatial and spectral information. Different materials can be distinguished when the spectra are analyzed. The result of the experiments show that the spectra of skin are very characteristic and that even under the impact of ash layers the spectral similarity remains very high. Thus our approach can be used for rescue robots to find human bodies autonomously, where other techniques such as color or thermal image analysis would fail.

Three-dimensional laser range finders provide autonomous systems with vast amounts of information... more Three-dimensional laser range finders provide autonomous systems with vast amounts of information. However, autonomous robots navigating in unstructured environments are usually not interested in every geometric detail of their surroundings. Instead, they require realtime information about the location of obstacles and the condition of drivable areas. In this paper, we first present grid-based algorithms for classifying regions as either drivable or not. In a subsequent step, drivable regions are further examined using a novel algorithm which determines the local terrain roughness. This information can be used by a path planning algorithm to decide whether to prefer a rough, muddy area, or a plain street, which would not be possible using binary drivability information only.

Autonomous robots in rescue environments have to fulfill several task at the same time: They have... more Autonomous robots in rescue environments have to fulfill several task at the same time: They have to localize themselves, build maps, detect victims and decide where to go next for further exploration. In this contribution we present an approach that provides a robust solution for the exploration task: Based on the knowledge of the environment that the robot has already acquired, the algorithm calculates a path to the next interesting "frontier". Our comprehensive approach takes into account the distance to the next frontier and the difficulty of the path for the robot. Those difficulties can result from narrow passages but also from wide, open spaces where the sensors cannot detect any landmark. For the native exploration task, the algorithm is fed with occupancy grids. For the search task, it can also process maps that encode additional information, e. g. places that have not been searched by other sensors yet. The Exploration Transform was successfully implemented on our mobile system Robbie and was used during the RoboCup German Open 2007 and the RoboCup World Championship 2007. Using this approach, our Team "resko" achieved the "Best in Class Autonomy Award" in the Rescue Robot League in both competitions.

Springer eBooks, 2011

Autonomous robots in real world applications have to deal with a complex 3D environment, but are ... more Autonomous robots in real world applications have to deal with a complex 3D environment, but are often equipped with standard 2D laser range finders (LRF) only. By using the 2D LRF for both, the 2D localization and mapping (which can be done efficiently and precisely) and for the 3D obstacle detection (which makes the robot move safely), a completely autonomous robot can be built with affordable 2D LRFs. We use the 2D LRF to perform particle filter based SLAM to generate a 2D occupancy grid, and the same LRF (moved by two servo motors) to acquire 3D scans to detect obstacles not visible in the 2D scans. The 3D data is analyzed with a recursive principal component analysis (PCA) based method, and the detected obstacles are recorded in a separate obstacle map. This obstacle map and the occupancy map are merged for the path planning. Our solution was tested on our mobile system Robbie during the RoboCup Rescue competitions in 2008 and 2009, winning the mapping challenge at the world championship 2008 and the German Open in 2009. This shows that the benefit of a sensor can dramatically be increased by actively controlling it, and that mixed 2D/3D perception can efficiently be achieved with a standard 2D sensor by controlling it actively.

Advanced Robotics and its Social Impacts, Oct 1, 2011

The RoboCupRescue Robot League is an international competition where teams from all over the worl... more The RoboCupRescue Robot League is an international competition where teams from all over the world compete against an arena that allows them to demonstrate their advanced robotic capabilities for emergency response applications. The league is also a community that works together to advance the state-of-the-art towards improving performance and the standards that help quantify this performance. In this paper, we present the current state of the competition, its links to the wider standardization process and how it is guiding robots towards fieldable capabilities.

ABSTRACT The tasks of autonomous rescue robots operating in unknown environments are manifold. Se... more ABSTRACT The tasks of autonomous rescue robots operating in unknown environments are manifold. Self localization, map generation and the detection of possible victims are indespensable. Apart from these, other factors can become crucial for the survival of the involved persons and for the safe operation of the robot itself. A first step in autonomously detecting such dangers is the real-time recognition of standardized danger signs in camera images. The knowledge of such information can be incorporated into the exploration algorithm as well as enhance the generated maps for later usage by human rescue teams. Our approach is a combination of histogram backprojection and speeded up robust feature (SURF) matching. The first one is used to detect regions of interest within the image. In the second step, interest points are extracted and their features are calculated. These features are then matched against the samples in a database, taking into account the constraints resulting from the affine transformation of the matching objects. We have tested the approach on a set of 240 scene images containing 5 different kinds of hazard signs. In 90 images, none of the signs was present, but objects of similar size and color. The approach detected 92% of the signs if the signs filled at least five percent of the pixels in the 1024 times 768 pixels image. None of the fake objects were detected as a hazmat sign in these experiments. The approach was implemented and successfully tested in practice on our mobile system "Robbie X", which was used by the team "resko" at the RoboCup World Championship 2008 in Suzhou, China.

Springer eBooks, 2010

Often Particle Filters are used to solve the SLAM (Simultaneous Localization and Mapping) problem... more Often Particle Filters are used to solve the SLAM (Simultaneous Localization and Mapping) problem in robotics: The particles represent the possible poses of the robot, and their weight is determined by checking if the sensor readings are consistent with the so far acquired map. Mostly a single map is maintained during the exploration, and only with Rao-Blackwellized Particle Filters each particle carries its own map. In this contribution, we propose a Hyper Particle Filter (HPF)-a Particle Filter of Particle Filters-for solving the SLAM problem in unstructured environments. Each particle of the HPF contains a standard Particle Filter (with a map and a set particles, that model the belief of the robot pose in this particular map). To measure the weight of a particle in the HPF, we developed two map quality measures that can be calculated automatically and do not rely on a ground truth map: The first map quality measure determines the contrast of the occupancy map. If the map has a high contrast, it is likely that the pose of the robot was always determined correctly before the map was updated, which finally leads to an overall consistent map. The second map quality measure determines the distribution of the orientation of wall pixels calculated by the Sobel operator. Using the model of a rectangular overall structure, slight but systematic errors in the map can be detected. Using the two measures, broken maps can automatically be detected. The corresponding particle is then more likely to be replaced by a particle with a better map within the HPF. We implemented the approach on our robot "Robbie 12", which will be used in the RoboCup Rescue league in 2009. We tested the HPF using the log files from last years RoboCup Rescue autonomy final, and with new data of a larger building. The quality of the generated maps outperformed our last years (league's best) maps. With the data acquired in the larger structure, Robbie was able to close loops in the map. Due to a highly efficient implementation, the algorithm still runs online during the autonomous exploration.

101 Reports on the Workshops Held at the Sixth International

Abstract: Designing a generic robot system architecture is a challenging task. Many design goals,... more Abstract: Designing a generic robot system architecture is a challenging task. Many design goals, such as scalability, applicability to various scenarios, easy integration of soft- and hardware, and reusability of components need to be considered. The code has to be kept easy to read and maintainable by developers and researchers. In this paper we describe the message-based software architecture Robbie that was specifically designed to address these goals. It has been successfully applied to fulfill various and complex tasks for different robots and scenarios in the context of autonomous mobile systems. We also examine how Robbie is related to the widely spread robot operating system ROS. 1

Maintenance cannot be looked at detached from other software development processes as it plays a ... more Maintenance cannot be looked at detached from other software development processes as it plays a crucial role in the software life cycle. In this thesis I have outlined how the perception of maintenance has changed over the years and what is now considered to be important. I have determined maintenance activities in theory and practice in the context of software process models for the use of academics and practitioners. I assumed the role of an interpretive traveller, first looking at different theoretical perspectives, then investigating current practices and finally bringing it together to establish a maintenance workflow within the context of the Rational Unified Process.

International Journal of Intelligent Defence Support Systems, 2021

This paper describes the research and experiment efforts of the NATO STO group IST-149-RTG capabi... more This paper describes the research and experiment efforts of the NATO STO group IST-149-RTG capability concept demonstrator for interoperability within unmanned ground systems and C2 and the NAAG team of experts on UGV. The main purpose of the group was to investigate possible standards for controlling UGVs and tests them in a real world scenario. The efforts have been two folded, where the first effort was two NATO groups having an experiment demonstrating interoperability between the UGVs and OCUs available within the group. The Belgium contribution is done in the EU project ICARUS. Both efforts used the Joint Architecture for Unmanned Systems (JAUS) with the interoperability profile (IOP) to successfully enable interoperability between the systems. The trials showed that it is possible to extend the systems quite easily and achieve compliance with parts of the standard in a relatively short time.

Themaintaskofrescue robots istolocate victims after adesaster suchasanearthquake. Forthis tasksen... more Themaintaskofrescue robots istolocate victims after adesaster suchasanearthquake. Forthis tasksensor datais usedtolocalize therobots intheir environment, build maps, and markthevictims inthemaps.Usually, thermal andcolor cameras, monitored byahumanoperator, areusedforthedetection. Hyperspectral imaging techniques aretoday usedforindustrial tasks suchasquality control, fast material sorting orfoodanalysis. Thispaperproposes anewapproach forthevictim detection in rescue environments, basedonhyperspectral imaging inthenear infrared spectral domain. Thistechnique involves a simultaneous recording ofspatial andspectral information. Different materials can bedistinguished whenthespectra areanalyzed. Theresult oftheexperiments showthat thespectra ofskin are verycharacteristic andthat evenunder theimpact ofashlayers the spectral similarity remains veryhigh. Thusourapproach canbeused forrescue robots tofind humanbodies autonomously whereother techniques suchascolor orthermal imageanalysis wo...

This paper describes our approach for the RoboCup 2006 Rescue League. The mobile system we use is... more This paper describes our approach for the RoboCup 2006 Rescue League. The mobile system we use is based on an ActivMedia Pineer 3 AT. It is equipped with a four wheel drive and sonar sensors in the front and in the back. On this platform, an alumnium rack is installed where the other devices are attached to: A self made stereo camera system (consisting of two high resolution Sony FireWire cameras), an electronic compass and a HOKUYU laser range finder (LRF). In addition, a third FireWire camera is attached to the back of the robot to give a rear view. The robot is manually controlled from a client computer, which is operated by one team member. The map building is done by the computer automatically by merging the collected LRF data with the depth information aquired by the stereo system. The operator can adjust the map proposed by the computer by correcting wrong matches. The victim detection has to be done by human observations using the visual cameras. The system was develpoped by...

Kundenbindung durch kosteneffiziente Service Excellence, 2016