Publications

2022

  • Thesis RoboCup Software Framework
    Softwareframework Für Den Humanoiden Roboter Gretchen Dominik Treßin Bachelorarbeit. Humboldt-Universität zu Berlin, 2022. (in German)
    @mastersthesis{2022_bachelorarbeit_tressin, author = {Treßin, Dominik}, keyword = {Thesis,RoboCup,Software Framework}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Softwareframework für den humanoiden Roboter Gretchen}, type = {Bachelorarbeit}, year = {2022} }
  • Thesis RoboCup Audio Localization
    Akustische Ortung Im Roboterfußball Jakob Dübel Masterarbeit. Humboldt-Universität zu Berlin, 2022. (in German)
    @mastersthesis{2022_masterarbeit_duebel, author = {Dübel, Jakob}, keyword = {Thesis,RoboCup,Audio,Localization}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Akustische Ortung im Roboterfußball}, type = {Masterarbeit}, year = {2022} }

2020

  • Thesis RoboCup
    Analyse Von Robocup Spielen - Erkennen Und Lokalisieren Von Nao Robotern Stella Alice Schlotter Studienarbeit. Humboldt-Universität zu Berlin, 2020. (in German)
    @mastersthesis{2020_studienarbeit_schlotter, author = {Schlotter, Stella Alice}, keyword = {Thesis,RoboCup}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Analyse von RoboCup Spielen - Erkennen und Lokalisieren von Nao Robotern}, type = {Studienarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2020-studienarbeit-schlotter.pdf}, year = {2020} }
  • Thesis RoboCup Motion Walk
    Zweibeiniges Laufen Für Humanoide Roboter Im Robocup Steffen Kaden Studienarbeit. Humboldt-Universität zu Berlin, 2020. (in German)
    @mastersthesis{2020_studienarbeit_kaden, author = {Kaden, Steffen}, keyword = {Thesis,RoboCup,Motion,Walk}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Zweibeiniges Laufen für Humanoide Roboter im RoboCup}, type = {Studienarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2020-studienarbeit-kaden.pdf}, year = {2020} }
  • Thesis RoboCup Localization Vision DNN
    Realtime Object Detection On The Nao Robot Anh Thu Nguyen Studienarbeit. Humboldt-Universität zu Berlin, 2020.
    @mastersthesis{2020_studienarbeit_nguyen, author = {Nguyen, Anh Thu}, keyword = {Thesis,RoboCup,Localization,Vision,DNN}, school = {Humboldt-Universität zu Berlin}, title = {Realtime Object Detection on the NAO Robot}, type = {Studienarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2020-studienarbeit-nguyen.pdf}, year = {2020} }
  • Thesis Hardware Infrastructure Humanoid Robot Gretchen
    Gretchen - A Humanoid Robot For Research And Education Anastasia Prisacaru Bachelorarbeit. Humboldt-Universität zu Berlin, 2020.
    @mastersthesis{2020_prisacaru_bachelorarbeit, author = {Prisacaru, Anastasia}, keyword = {Thesis,Hardware,Infrastructure,Humanoid Robot,Gretchen}, school = {Humboldt-Universität zu Berlin}, title = {Gretchen - a humanoid robot for research and education}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2020-bachelorarbeit-prisacaru.pdf}, year = {2020} }
  • Thesis RoboCup Behavior Team Coordination Communication
    Teamstrategie Und -Koordination Im Kontext Des Roboterfußballs Philipp Strobel Diplomarbeit. Humboldt-Universität zu Berlin, 2020. (in German)
    @mastersthesis{2020_strobel_diplomarbeit, author = {Strobel, Philipp}, keyword = {Thesis,RoboCup,Behavior,Team Coordination,Communication}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Teamstrategie und -koordination im Kontext des Roboterfußballs}, type = {Diplomarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2020-diplomarbeit-strobel.pdf}, year = {2020} }
  • Anticipation As A Mechanism For Complex Behavior In Artificial Agents Heinrich Mellmann, Stella Alice Schlotter, Lea Musiolek, Verena V. Hafner Artificial Life Conference Proceedings, number 32, pp. 157–159, 2020.
    @article{ALIFE-MellmannEtAl-20, author = {Mellmann, Heinrich and Schlotter, Stella Alice and Musiolek, Lea and Hafner, Verena V.}, doi = {10.1162/isal_a_00314}, eprint = {https://www.mitpressjournals.org/doi/pdf/10.1162/isal_a_00314}, journal = {Artificial Life Conference Proceedings}, number = {32}, pages = {157-159}, title = {Anticipation as a Mechanism for Complex Behavior in Artificial Agents}, url = {https://www.mitpressjournals.org/doi/abs/10.1162/isal_a_00314}, year = {2020} }
    Anticipation is a skill that enables complex decision making in humans and other biological agents. We review different implementations of anticipatory behavior in robots and give an overview on anticipation in biological systems. Based on an example of anticipatory behavior in humanoid robots, we discuss decision making and anticipation in artificial agents. We show that anticipation can enable fast decisions in highly dynamic and complex situations. Our findings are supported by experimental results performed in simulation and on real robots in large scale experiments.

2019

  • Robocup.tools - Data Driven Research And Development In Robocup Heinrich Mellmann, Stella Alice Schlotter, Philipp Strobel Project Proposal. 2019.
    @misc{2019-rcf20-project-game-evaluation, author = {Heinrich Mellmann and Stella Alice Schlotter and Philipp Strobel}, title = {robocup.tools - Data Driven Research and Development in RoboCup}, type = {Project Proposal}, url = {http://robocup.tools}, year = {2019} }
  • Berlin United - Nao Team Humboldt Team Report 2019 Heinrich Mellmann, Stella Alice Schlotter, Steffen Kaden, Philipp Strobel, Thomas Krause, Etienne Couque-Castelnovo, Claas-Norman Ritter, Robert Martin Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2019.
    @techreport{naoth-report19, author = {Heinrich Mellmann and Stella Alice Schlotter and Steffen Kaden and Philipp Strobel and Thomas Krause and Etienne Couque-Castelnovo and Claas-Norman Ritter and Robert Martin}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2020-01-22}, title = {Berlin United - Nao Team Humboldt Team Report 2019}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report19.pdf}, year = {2019} }
  • Thesis RoboCup Vision Object Detection DNN
    Neural Architecture Search Zur Bildklassifikation Darko Nedic Bachelorarbeit. Humboldt-Universität zu Berlin, 2019. (in German)
    @mastersthesis{2019_bachlorarbeit_darko, author = {Darko Nedic}, date = {42.42.2019}, keyword = {Thesis,RoboCup,Vision,Object Detection,DNN}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Neural Architecture Search zur Bildklassifikation}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2019-bachlorarbeit-darko.pdf}, year = {2019} }
  • Thesis RoboCup Vision Object Detection Field Features
    Visuelle Positionsbestimmung Für Mobile Roboter Im Robocup Kontext Robert Martin Bachelorarbeit. Humboldt-Universität zu Berlin, 2019. (in German)
    @mastersthesis{2019_martin_bachelorarbeit, author = {Martin, Robert}, keyword = {Thesis,RoboCup,Vision,Object Detection,Field Features}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Visuelle Positionsbestimmung für mobile Roboter im RoboCup Kontext}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2019-bachelorarbeit-martin.pdf}, year = {2019} }
  • RoboCup Data Driven Development Robot Detection Visual Robot Tracking Camera Localization
    Toward Data Driven Development In Robocup Heinrich Mellmann, Stella Alice Schlotter, Philipp Strobel RoboCup 2019: Robot Soccer World Cup XXIII, Lecture Notes in Computer Science, volume 11531, pp. 176–188, 2019. Springer International Publishing.
    @inproceedings{RC-MellmannSchlotterStrobel-19, author = {Heinrich Mellmann and Stella Alice Schlotter and Philipp Strobel}, booktitle = {RoboCup 2019: Robot Soccer World Cup XXIII}, doi = {10.1007/978-3-030-35699-6_14}, keyword = {RoboCup, Data Driven Development, Robot Detection, Visual Robot Tracking, Camera Localization}, pages = {176--188}, publisher = {Springer International Publishing}, series = {Lecture Notes in Computer Science}, title = {Toward Data Driven Development in RoboCup}, volume = {11531}, year = {2019} }
    Conducting games in RoboCup incurs high cost in terms of effort, time, and money. The scientific outcome, however, is quite limited and often not very conclusive. Especially, analyzing and drawing conclusions about the performance of complex processes like decision making of an individual robot or the behavior on the team level poses a considerable challenge. Collecting more data during the competition games will help to analyze the performance of algorithms, identify errors and areas for improvement, and make more signiffcant statements regarding the performance of the robots. In this work we investigate the possibilities for collection of the large scale RoboCup data and its analysis. We present a system for automatic recording of synchronized videos of RoboCup games and an application for exploration and annotation of large sets of RoboCup-related data. We also present data sets collected during the competitions in 2018 and an algorithm for visual detection and tracking of robots in the RoboCup videos. A first empirical evaluation shows promising results and demonstrates how such data can be integrated and used to validate robot's behavior.

2018

  • Berlin United - Nao Team Humboldt Team Report 2018 Heinrich Mellmann, Stella Alice Schlotter, Steffen Kaden, Philipp Strobel, Thomas Krause, Etienne Couque-Castelnovo, Claas-Norman Ritter, Tobias Hübner, Schahin Tofangchi Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2018.
    @techreport{naoth-report18, author = {Heinrich Mellmann and Stella Alice Schlotter and Steffen Kaden and Philipp Strobel and Thomas Krause and Etienne Couque-Castelnovo and Claas-Norman Ritter and Tobias Hübner and Schahin Tofangchi}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2018-11-11}, title = {Berlin United - Nao Team Humboldt Team Report 2018}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report18.pdf}, year = {2018} }
  • Thesis RoboCup Behavior Team Coordination Communication
    Methoden Und Werkzeuge Zur Analyse Von Teamverhalten Und -Strategie Im Roboterfußball Philipp Strobel Studienarbeit. Humboldt-Universität zu Berlin, 2018. (in German)
    @mastersthesis{strobel-studienarbeit, author = {Strobel, Philipp}, keyword = {Thesis,RoboCup,Behavior,Team Coordination,Communication}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Methoden und Werkzeuge zur Analyse von Teamverhalten und -strategie im Roboterfußball}, type = {Studienarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2019-studienarbeit-strobel.pdf}, year = {2018} }
  • Thesis RoboCup Vision Object Detection Robot Detection
    Visuelle Echtzeit Detektion Humanoider Roboter Im Robocup Kontext Denis Ring Bachelorarbeit. Humboldt-Universität zu Berlin, 2018. (in German)
    @mastersthesis{2018_bachelor_ring, author = {Denis Ring}, date = {42.42.2018}, keyword = {Thesis,RoboCup,Vision,Object Detection,Robot Detection}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Visuelle Echtzeit Detektion humanoider Roboter im RoboCup Kontext}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2018-bachelorarbeit-ring.pdf}, year = {2018} }
  • Thesis RoboCup Video Analysis
    Visuelle Verfolgung Humanoider Roboter Im Robocup-Kontext Lucas Schwaß Diplomarbeit. Humboldt-Universität zu Berlin, 2018. (in German)
    @mastersthesis{schwass2018, author = {Lucas Schwaß}, date = {31.01.2018}, keyword = {Thesis,RoboCup,Video Analysis}, month = {January}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Visuelle Verfolgung humanoider Roboter im RoboCup-Kontext}, type = {Diplomarbeit}, year = {2018} }

2017

  • Berlin United - Nao Team Humboldt Team Report 2017 Heinrich Mellmann, Stella Alice Schlotter, Steffen Kaden, Philipp Strobel, Thomas Krause, Claas-Norman Ritter, Tobias Hübner, Schahin Tofangchi Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2017.
    @techreport{naoth-report17, author = {Heinrich Mellmann and Stella Alice Schlotter and Steffen Kaden and Philipp Strobel and Thomas Krause and Claas-Norman Ritter and Tobias Hübner and Schahin Tofangchi}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2018-11-11}, title = {Berlin United - Nao Team Humboldt Team Report 2017}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report17.pdf}, year = {2017} }
  • Thesis RoboCup Vision Object Detection Robot Detection
    Deep Learning Based Robot Detection In The Context Of Robocup Robin Papke Bachelorarbeit. Humboldt-Universität zu Berlin, 2017.
    @mastersthesis{papke2017, author = {Robin Papke}, date = {12.11.2017}, keyword = {Thesis,RoboCup,Vision,Object Detection, Robot Detection}, month = {November}, school = {Humboldt-Universität zu Berlin}, title = {Deep Learning Based Robot Detection in the Context of RoboCup}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2017-bachelorarbeit-papke.pdf}, year = {2017} }
  • Thesis RoboCup Vision Object Detection Robot Detection
    Visuelle Detektion Humanoider Roboter Basierend Auf Histogrammen Orientierter Gradienten Dominik Krienelke Diplomarbeit. Humboldt-Universität zu Berlin, 2017. (in German)
    @mastersthesis{krienelke2017, author = {Krienelke, Dominik}, date = {14.09.2018}, keyword = {Thesis,RoboCup,Vision,Object Detection, Robot Detection}, month = {Februar}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Visuelle Detektion humanoider Roboter basierend auf Histogrammen orientierter Gradienten}, type = {Diplomarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2017-krienelke-diploma-thesis.pdf}, year = {2017} }
  • Thesis RoboCup Behavior Path-Planing
    Pfadplanung Und Schrittkoordination Für Humanoide Roboter Yigit Can Akcay Bachelorarbeit. Humboldt-Universität zu Berlin, 2017. (in German)
    @mastersthesis{2017_akcay_bachelorarbeit, author = {Can Akcay, Yigit}, keyword = {Thesis,RoboCup,Behavior,Path-Planing}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Pfadplanung und Schrittkoordination für Humanoide Roboter}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2017-bachelorarbeit-akcay.pdf}, year = {2017} }
  • Thesis RoboCup Behavior Modeling Decision-Making
    Selection Of Actions Based On Forward Simulations Stella Alice Schlotter Bachelorarbeit. Humboldt-Universität zu Berlin, 2017.
    @mastersthesis{schlotter2017, author = {Schlotter, Stella Alice}, keyword = {Thesis,RoboCup,Behavior,Modeling,Decision-Making}, school = {Humboldt-Universität zu Berlin}, title = {Selection of Actions based on Forward Simulations}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2017-bachelor-thesis-schlotter.pdf}, year = {2017} }
  • Advances On Simulation Based Selection Of Actions For A Humanoid Soccer-Robot Heinrich Mellmann, Stella Alice Schlotter Proceedings of the 12th Workshop on Humanoid Soccer Robots, 17th IEEE-RAS International Conference on Humanoid Robots (Humanoids), address Birmingham, UK., 2017.
    @inproceedings{HSR-MellmannSchlotter-17, address = {Birmingham, UK.}, author = {Heinrich Mellmann and Stella Alice Schlotter}, booktitle = {Proceedings of the 12th Workshop on Humanoid Soccer Robots, 17th IEEE-RAS International Conference on Humanoid Robots (Humanoids)}, title = {Advances on Simulation Based Selection of Actions for a Humanoid Soccer-Robot}, url = {http://lofarolabs.com/events/robocup/ws17/program.php}, year = {2017} }
    This paper introduces a method for making fast decisions in a highly dynamic situation, based on forward simulation. This approach is inspired by the decision problem within the RoboCup domain. In this environment, selecting the right action is often a challenging task. The outcome of a particular action may depend on a wide variety of environmental factors, such as the robot's position on the field or the location of obstacles. In addition, the perception is often heterogeneous, uncertain, and incomplete.In this context, we investigate forward simulation as a versatile and extensible yet simple mechanism for inference of decisions. To evaluate an action, the outcome is simulated based on the estimated state of the situation. The simulation of a single action is split into a number of simple deterministic simulations - samples - based on the uncertainties of the estimated state and of the action model. Each of the samples is then evaluated separately, and the evaluations are combined and compared with those of other actions to inform the overall decision. This allows us to effectively combine heterogeneous perceptual data, calculate a stable decision, and reason about its uncertainty. This approach is implemented for the kick selection task in the RoboCup SPL environment and is actively used in competitions. In simulated experiments we validate the new scheme and evaluate different strategies.

2016

  • Berlin United - Nao Team Humboldt Team Report 2016 Heinrich Mellmann, Stella Alice Schlotter, Steffen Kaden, Philipp Strobel, Thomas Krause, Claas-Norman Ritter, Tobias Hübner, Schahin Tofangchi Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2016.
    @techreport{naoth-report16, author = {Heinrich Mellmann and Stella Alice Schlotter and Steffen Kaden and Philipp Strobel and Thomas Krause and Claas-Norman Ritter and Tobias Hübner and Schahin Tofangchi}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2016-12-09}, title = {Berlin United - Nao Team Humboldt Team Report 2016}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report16.pdf}, year = {2016} }
  • Thesis Humanoid Robot Audio Perception
    Interne Modelle Zur Vorhersage Der Eigengeräusche Bei Humanoiden Robotern Claas Ritter Diplomarbeit. Humboldt-Universität zu Berlin, 2016. (in German)
    @mastersthesis{2016_ritter_diplomarbeit, author = {Ritter, Claas}, date = {04.05.2016}, keyword = {Thesis,Humanoid Robot,Audio Perception}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Interne Modelle zur Vorhersage der Eigengeräusche bei humanoiden Robotern}, type = {Diplomarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2016-diplomarbeit-ritter.pdf}, year = {2016} }
  • RoboCup humanoid robots internal simulation decision making
    Simulation Based Selection Of Actions For A Humanoid Soccer-Robot Heinrich Mellmann, Stella Alice Schlotter, Christian Blum RoboCup 2016: Robot Soccer World Cup XX, 2016.
    @inproceedings{RC-MellmannSchlotterBlum-16, author = {Heinrich Mellmann and Stella Alice Schlotter and Christian Blum}, booktitle = {RoboCup 2016: Robot Soccer World Cup XX}, keyword = {RoboCup, humanoid robots, internal simulation, decision making}, title = {Simulation Based Selection of Actions for a Humanoid Soccer-Robot}, url = {http://www.ais.uni-bonn.de/robocup.de/2016/papers/RoboCup_Symposium_2016_Mellmann.pdf}, year = {2016} }
    This paper introduces a method for making fast decisions in a highly dynamic situation, based on forward simulation. This approach is inspired by the decision problem within the RoboCup domain. In this environment, selecting the right action is often a challenging task. The outcome of a particular action may depend on a wide variety of environmental factors, such as the robot's position on the field or the location of obstacles. In addition, the perception is often heterogeneous, uncertain, and incomplete. In this context, we investigate forward simulation as a versatile and extensible yet simple mechanism for inference of decisions. The outcome of each possible action is simulated based on the estimated state of the situation. The simulation of a single action is split into a number of simple deterministic simulations -- samples -- based on the uncertainties of the estimated state and of the action model. Each of the samples is then evaluated separately, and the evaluations are combined and compared with those of other actions to inform the overall decision. This allows us to effectively combine heterogeneous perceptual data, calculate a stable decision, and reason about its uncertainty. This approach is implemented for the kick selection task in the RoboCup SPL environment and is actively used in competitions. We present analysis of real game data showing significant improvement over our previous methods.

2015

  • Berlin United - Nao Team Humboldt Team Report 2015 Heinrich Mellmann, Thomas Krause, Claas-Norman Ritter, Steffen Kaden, Tobias Hübner, Stella Alice Schlotter, Schahin Tofangchi Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2015.
    @techreport{naoth-report15, author = {Heinrich Mellmann and Thomas Krause and Claas-Norman Ritter and Steffen Kaden and Tobias Hübner and Stella Alice Schlotter and Schahin Tofangchi}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2015-12-07}, title = {Berlin United - Nao Team Humboldt Team Report 2015}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report15.pdf}, year = {2015} }

2014

  • Berlin United - Nao Team Humboldt Team Report 2014 Heinrich Mellmann, Thomas Krause, Claas-Norman Ritter, Steffen Kaden, Tobias Hübner, Stella Alice Schlotter, Schahin Tofangchi, Maximilian Bielefeld, Alexander Berndt Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany, 2014.
    @techreport{naoth-report14, author = {Heinrich Mellmann and Thomas Krause and Claas-Norman Ritter and Steffen Kaden and Tobias Hübner and Stella Alice Schlotter and Schahin Tofangchi and Maximilian Bielefeld and Alexander Berndt}, institution = {Adaptive Systeme, Institut für Informatik, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany}, timestamp = {2015-01-11}, title = {Berlin United - Nao Team Humboldt Team Report 2014}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/publications/technical/naoth-report14.pdf}, year = {2014} }
  • Thesis RoboCup Motion Walk
    From Simulation To Reality: Migration Of Humanoid Robot Control Yuan Xu Dissertation. Humboldt-Universität zu Berlin, 2014.
    @phdthesis{2014_xu_dissertation, author = {Xu, Yuan}, date = {17.03.2014}, doi = {http://dx.doi.org/10.18452/16961}, keyword = {Thesis,RoboCup,Motion,Walk}, school = {Humboldt-Universität zu Berlin}, title = {From Simulation to Reality: Migration of Humanoid Robot Control}, type = {Dissertation}, year = {2014} }
  • Thesis RoboCup Perception Modeling
    Multi-Hypothesen-Partikelfilter Zur Objektmodellierung Am Beispiel Eines Tormodells Im Robocup-Kontext Marcus Scheunemann Diplomarbeit. Humboldt-Universität zu Berlin, 2014. (in German)
    @mastersthesis{2014_scheunemann_diplomarbeit, author = {Scheunemann, Marcus}, date = {04.09.2014}, keyword = {Thesis,RoboCup,Perception,Modeling}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Multi-Hypothesen-Partikelfilter zur Objektmodellierung am Beispiel eines Tormodells im RoboCup-Kontext}, type = {Diplomarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2014-scheunemann-diploma-thesis.pdf}, year = {2014} }
  • RoboCup Vision Modeling
    Multi-Hypothesis Goal Modeling For A Humanoid Soccer Robot Marcus Scheunemann, Heinrich Mellmann Proceedings of the 9th Workshop on Humanoid Soccer Robots, 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids), address Madrid, Spain, 2014.
    @inproceedings{HSR-ScheunemannMellmann-14, address = {Madrid, Spain}, author = {Scheunemann, Marcus and Mellmann, Heinrich}, booktitle = {Proceedings of the 9th Workshop on Humanoid Soccer Robots, 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids)}, keyword = {RoboCup,Vision,Modeling}, month = {November}, timestamp = {2014.11.29}, title = {Multi-Hypothesis Goal Modeling for a Humanoid Soccer Robot}, url = {http://www.ais.uni-bonn.de/humanoidsoccer/ws14/papers/HSR14_Scheunemann.pdf}, video = {https://www.youtube.com/watch?v=VCI9fuMvp38}, year = {2014} }
    Information about objects and their positions in an environment are necessary requirements for most tasks of a mobile autonomous robot, in particular regarding the control of behavior and navigation. This presents a special challenge for robots with a limited view angle. Autonomously soccer playing robots in the dynamic environment of the RoboCup Standard Platform League are exposed to these difficulties. Most approaches aggregate all available information in one holistic model in order to localize robots. In case of inconsistent perceptions the model either turns noisy or creates and tracks an addiotional hypothesis. To improve the localization -- and thus the behavior control -- local models have received only little attention so far. In this work the implementation of a local goal model is presented and analyzed. A multi-hypothesis particle filter is used to cope with ambiguity of goal post percepts as well as to process incomplete and uncertain sensor information. Additionally, a percept buffer supports the initialization and also facilitates the handling of sparse false measurements. On the basis of this local goal model inconsistencies can be explicitly modeled, which may be used to stabilize the location of a robot.

2013

  • Thesis RoboCup Behavior Path-Planing Navigation
    Strategische Positionierung Von Robotern Im Robocup Steffen Kaden Bachelorarbeit. Humboldt-Universität zu Berlin, 2013. (in German)
    @mastersthesis{2013_kaden_bachelorarbeit, author = {Kaden, Steffen}, keyword = {Thesis,RoboCup,Behavior,Path-Planing,Navigation}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Strategische Positionierung von Robotern im RoboCup}, type = {Bachelorarbeit}, url = {https://www2.informatik.hu-berlin.de/~naoth/docs/theses/2013-bachelorarbeit-kaden.pdf}, year = {2013} }
  • Adaptive Grasping For A Small Humanoid Robot Utilizing Force- And Electric Current Sensors Heinrich Mellmann, Marcus Scheunemann, Oliver Stadie Proceedings of the 22nd International Workshop on Concurrency, Specification and Programming (CS&P), CEUR Workshop Proceedings, volume 1032, pp. 283–293, address Warsaw, Poland, 2013. CEUR-WS.org.
    @inproceedings{CSP-MellmannScheunemannEtAl-13, address = {Warsaw, Poland}, author = {Heinrich Mellmann and Marcus Scheunemann and Oliver Stadie}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {Proceedings of the 22nd International Workshop on Concurrency, Specification and Programming (CS&P)}, crossref = {DBLP:conf/csp/2013}, editor = {Marcin S. Szczuka and Ludwik Czaja and Magdalena Kacprzak}, pages = {283-293}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Adaptive Grasping for a Small Humanoid Robot Utilizing Force- and Electric Current Sensors}, url = {http://ceur-ws.org/Vol-1032/paper-24.pdf}, volume = {1032}, year = {2013} }
    The ability to grasp objects of different size and shape is one of the most important skills of a humanoid robot. Human grasping integrates a lot of different senses. In particular, the tactile sensing is very important for a stable grasping motion. When we lift a box without knowing what is inside, we do it carefully using our tactile and proprioceptive senses to estimate the weight and thus, the force necessary to hold and to lift this box. In this paper we present an adaptive controlling mechanism which enables a robot to grasp objects of different weights. Thereby, we only use the proprioceptive sensors like positions and electric current at the joints and force sensors at the end-effectors providing the robot with tactile feedback. We implemented and tested our approach on a humanoid robot.
  • Voronoi Based Strategic Positioning For Robot Soccer Steffen Kaden, Heinrich Mellmann, Marcus Scheunemann, Hans-Dieter Burkhard Proceedings of the 22nd International Workshop on Concurrency, Specification and Programming (CS&P), CEUR Workshop Proceedings, volume 1032, pp. 271–282, address Warsaw, Poland, 2013. CEUR-WS.org.
    @inproceedings{CSP-KadenMellmannEtAl-13, address = {Warsaw, Poland}, author = {Steffen Kaden and Heinrich Mellmann and Marcus Scheunemann and Hans-Dieter Burkhard}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {Proceedings of the 22nd International Workshop on Concurrency, Specification and Programming (CS&P)}, editor = {Marcin S. Szczuka and Ludwik Czaja and Magdalena Kacprzak}, pages = {271-282}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, timestamp = {2013.11.03}, title = {Voronoi Based Strategic Positioning for Robot Soccer}, url = {http://ceur-ws.org/Vol-1032/paper-23.pdf}, volume = {1032}, year = {2013} }
    Strategic positioning is a decisive part of the team play within a soccer game. In most solutions the positioning techniques are treated as a constituent of a complete team play strategy. In a comprehensive overview we discuss the team play and positioning methods used within RoboCup and extract the essential requirements for player positioning. In this work, we propose an approach for strategic positioning allowing for flexible formulation of arbitrary strategies. Based on the conditions of a specific strategy, the field is subdivided in regions by a Voronoi tessellation and each region is assigned a weight. Those weights influence the calculation of the optimal robot position as well as the path. A team play strategy can be expressed by the choice of the tessellation as well as the choice of the weights. This provides a powerful abstraction layer simplifying the design of the actual play strategy. We also present an implementation of an example strategy based on this approach and analyse the performance of our approach in simulation.

2011

  • Thesis
    Erfahrungsbasierte Lernmethoden Zur Visuellen Trajektorienvorhersage Humanoider Roboter Thomas Krause Diplomarbeit. Humboldt-Universität zu Berlin, 2011. (in German)
    @mastersthesis{krause_erfahrungsbasierte_2011, author = {Krause, Thomas}, keyword = {Thesis}, note = {(in German)}, school = {Humboldt-Universität zu Berlin}, title = {Erfahrungsbasierte Lernmethoden zur visuellen Trajektorienvorhersage humanoider Roboter}, type = {Diplomarbeit}, year = {2011} }
  • Local Goal Model For A Humanoid Soccer Robot Heinrich Mellmann, Marcus Scheunemann Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P), pp. 353–360, address Pułtusk, Poland, 2011. Białystok University of Technology.
    @inproceedings{CSP-MellmannScheunemann-11, address = {Pułtusk, Poland}, author = {Heinrich Mellmann and Marcus Scheunemann}, booktitle = {Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P)}, editor = {Marcin Szczuka and Ludwik Czaja and Andrzej Skowron and Magdalena Kacprzak}, month = {September}, pages = {353-360}, publisher = {Białystok University of Technology}, timestamp = {2011.11.12}, title = {Local Goal Model for a Humanoid Soccer Robot}, year = {2011} }
  • Dynamic Motion Control: Adaptive Bimanual Grasping For A Humanoid Robot Heinrich Mellmann, Giuseppe Cotugno Fundamenta Informaticae, volume 112, number 1, pp. 89–101, 2011.
    @article{FI-MellmannCotugno-11, author = {Heinrich Mellmann and Giuseppe Cotugno}, journal = {Fundamenta Informaticae}, number = {1}, pages = {89-101}, timestamp = {2011.06.13}, title = {Dynamic Motion Control: Adaptive Bimanual Grasping for a Humanoid Robot}, volume = {112}, year = {2011} }
    The ability to grasp objects of different size and shape is one of the most important skills of a humanoid robot. There are a lot of different approaches tackling this problem; however, there is no general solution. The complexity and the skill of a possible grasping motion depend hardly on a particular robot. In this paper we analyze the kinematic and sensory grasping abilities of the humanoid robot Nao. Its kinematic constraints and hand's mechanical structure represent an interesting case of study due to lack of actuators for fingers and the limited computation power. After describing the platform and studying its capabilities, we propose some simple controllers and we present a benchmark based on some experimental data.

2010

  • Nao-Team Humboldt 2010 Hans-Dieter Burkhard, Florian Holzhauer, Thomas Krause, Heinrich Mellmann, Claas Norman Ritter, Oliver Welter, Yuan Xu Humboldt-Universität zu Berlin, 2010.
    @techreport{tdp10, author = {Hans-Dieter Burkhard and Florian Holzhauer and Thomas Krause and Heinrich Mellmann and Claas Norman Ritter and Oliver Welter and Yuan Xu}, institution = {Humboldt-Universität zu Berlin}, timestamp = {2010.02.03}, title = {NAO-Team Humboldt 2010}, url = {http://www.naoteamhumboldt.de/wp-content/uploads/2010/02/NaoTH10Description.pdf}, year = {2010} }
  • Thesis RoboCup Perception Modeling Localization
    Ein Anderes Modell Der Welt: Alternative Methoden Zur Lokalisierung Mobiler Roboter Heinrich Mellmann Diploma Thesis. Humboldt Universität zu Berlin, 2010. (in German)
    @mastersthesis{DiplomaThesis-Mellmann-10, author = {Heinrich Mellmann}, doi = {http://dx.doi.org/10.18452/14229}, keyword = {Thesis,RoboCup,Perception,Modeling,Localization}, month = {April}, note = {(in German)}, school = {Humboldt Universität zu Berlin}, timestamp = {2010.07.27}, title = {Ein anderes Modell der Welt: Alternative Methoden zur Lokalisierung Mobiler Roboter}, type = {Diploma Thesis}, url = {https://www2.informatik.hu-berlin.de/~mellmann/content/publications/data/2011-05-13-diplomarbeit-mellmann-very-final.pdf}, year = {2010} }
    Many tasks of a mobile robot, e.g., navigation, require the knowledge of the positions of the objects in the surrounding environment. This task is especially challenging for the robots which perception is based on a directed visual system, e.g., a camera with a limited view angle. The incomplete and noisy sensor information leads to the uncertainty in the robots belief of the world. An appropriate model of the world may enable the robot to make plans and to realize complex behavior. The state of the art modeling methods use often only a small part of the available information. In particular the redundant information remain unused. In this work we investigate methods to exploit effectively the redundant information in order to get a better model of the world. In the first part we discuss a number of possibilities to use of specific properties of the objects to estimate the parameters of the camera matrix. In the second part we present a constraint based approach for the world modeling.
  • An Approach To Close The Gap Between Simulation And Real Robots Yuan Xu, Heinrich Mellmann, Hans-Dieter Burkhard 2nd International Conference on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR), Lecture Notes in Computer Science, pp. 533–544, 2010. Springer Berlin / Heidelberg.
    @inproceedings{SIMPAR-XuMellmannEtAl-10, affiliation = {Institut für Informatik, LFG Künstliche Intelligenz, Humboldt-Universität zu Berlin, Rudower Chaussee 25, 12489 Berlin, Germany}, author = {Xu, Yuan and Mellmann, Heinrich and Burkhard, Hans-Dieter}, booktitle = {2nd International Conference on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR)}, doi = {10.1007/978-3-642-17319-6_48}, editor = {Ando, Noriaki and Balakirsky, Stephen and Hemker, Thomas and Reggiani, Monica and von Stryk, Oskar}, pages = {533--544}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2011.01.04}, title = {An Approach to Close the Gap between Simulation and Real Robots}, url = {http://dx.doi.org/10.1007/978-3-642-17319-6_48}, year = {2010} }
    Numerous simulators have been developed over the years to assist robotics research in the development, testing, and evaluation. Nevertheless, there is still a big gap between the simulation and the reality. This makes it difficult to transfer methods and code. The 3D simulator | SimSpark is developed and used by a big community of AI researchers in RoboCup. But up to now there are only few applications to real robots. In this paper, we discuss the general possibilities how the SimSpark simulator can be used to support research in cognitive robotics and present applications on the humanoid robot Nao. As a result of our investigation we have developed a unified team playing both in Simulation League and Standard Platform League in RoboCup.
  • Adaptive Motion Control: Dynamic Kick For A Humanoid Robot Yuan Xu, Heinrich Mellmann Proceedings of the 33rd Annual German Conference on Artificial Intelligence (KI 2010), Lecture Notes in Computer Science, volume 6359, pp. 392–399, 2010. Springer Berlin / Heidelberg.
    @inproceedings{KI-XuMellmann-10, affiliation = {Institut für Informatik, LFG Künstliche Intelligenz, Humboldt-Universität zu Berlin, Germany}, author = {Xu, Yuan and Mellmann, Heinrich}, booktitle = {Proceedings of the 33rd Annual German Conference on Artificial Intelligence (KI 2010)}, doi = {10.1007/978-3-642-16111-7_45}, editor = {Dillmann, Rüdiger and Beyerer, Jürgen and Hanebeck, Uwe and Schultz, Tanja}, pages = {392--399}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {2011.01.04}, title = {Adaptive Motion Control: Dynamic Kick for a Humanoid Robot}, url = {http://dx.doi.org/10.1007/978-3-642-16111-7_45}, volume = {6359}, year = {2010} }
    Automatic, full body motion generation for humanoid robots presents a formidable computational challenge. The kicking motion is one of the most important motions in a soccer game. However, at the current state the most common approaches of implementing this motion are based on key frame technique. Such solutions are inflexible and cost a lot of time to adjust robot’s position. In this paper we present an approach for adaptive control of the motions. We implemented our approach in order to solve the task of kicking the ball on a humanoid robot Nao. The approach was tested both in simulation and on a real robot.
  • Adaptive Motion Control With Visual Feedback For A Humanoid Robot Heinrich Mellmann, Yuan Xu IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), 2010.
    @inproceedings{IROS-MellmannXu-10, author = {Heinrich Mellmann and Yuan Xu}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010)}, doi = {10.1109/IROS.2010.5650226}, timestamp = {2010.07.27}, title = {Adaptive Motion Control with Visual Feedback for a Humanoid Robot}, year = {2010} }
    The performance of a soccer robot is highly dependent on its motion ability. The kicking motion is one of the most important motions in a soccer game. However, automatic, full body motion generation for humanoid robots presents a formidable computational challenge. At the current state the most common approaches of implementing this motion are based on key frame technique. Such solutions are inflexible, i.e., in order to adjust the aimed direction of the kick the robot has to walk around the ball. The adjustment costs a lot of time especially if some precise adjustments have to be done, e.g., for a penalty kick. In this paper we present an approach for adaptive control of the motions. We implemented our approach in order to solve the task of kicking the ball on a humanoid robot Nao. The approach was tested both in simulation and on a real robot.
  • Naoth Software Architecture For An Autonomous Agent Heinrich Mellmann, Yuan Xu, Thomas Krause, Florian Holzhauer Proceedings of the International Workshop on Standards and Common Platforms for Robotics (SCPR 2010), pp. 316–327, address Darmstadt, 2010.
    @inproceedings{SCPR-MellmannXuEtAl-10, address = {Darmstadt}, author = {Heinrich Mellmann and Yuan Xu and Thomas Krause and Florian Holzhauer}, booktitle = {Proceedings of the International Workshop on Standards and Common Platforms for Robotics (SCPR 2010)}, month = {November}, pages = {316--327}, timestamp = {2010.11.21}, title = {NaoTH Software Architecture for an Autonomous Agent}, url = {http://www.naoteamhumboldt.de/wp-content/papercite-data/pdf/scpr-mellmannxuetal-10.pdf}, year = {2010} }
    An appropriate architecture (i.e., framework) is the base of each successful heterogeneous software project. It enables a group of developers to work at the same project and to organize their solutions. From this point of view, the artificial intelligence and/or robotics related research projects are usually more complicated, since the actual result of the project is often not clear. In particular, a strong organization of the software is necessary if the project is involved in education. Obviously, there is no perfect framework which could satisfy all the needs of the developers. In this paper we present a modular software architecture designed to implement an autonomous agent. In particular, it is used to develop software which is used simultaneously at several platforms (e.g., humanoid robot, simulated agent). One of the main aspects considered in our design is a strong code modularization which allows for re-usability, transparency and easily testing. Other important aspects are real-time applicability and simple usage. This paper presents the main concepts and the particular implementation of the important parts. We also provide a qualitative comparison with other existing robotics frameworks.
  • Dynamic Motion Control: Adaptive Bimanual Grasping For A Humanoid Robot Giuseppe Cotugno, Heinrich Mellmann Workshop on Concurrency, Specification, and Programming (CS&P), volume Volume 2, address Börnicke (near Berlin), Germany, 2010.
    @inproceedings{CSP-CotugnoMellmann-10, address = {Börnicke (near Berlin), Germany}, author = {Giuseppe Cotugno and Heinrich Mellmann}, booktitle = {Workshop on Concurrency, Specification, and Programming (CS&P)}, month = {September}, timestamp = {2010.09.29}, title = {Dynamic Motion Control: Adaptive Bimanual Grasping for a Humanoid Robot}, volume = {Volume 2}, year = {2010} }
    In this paper we analyze the kinematic and sensory grasping abilities of the humanoid robot Nao. Its kinematic constraints and hand's mechanical structure represent an interesting case of study due to lack of actuators for fingers and the limited computation power. After describing the platform and studying its capabilities, we propose some simple controllers and we present a benchmark based on some experimental data.
  • Narrowing Reality Gap And Validation: Improving The Simulator For Humanoid Soccer Robot Yuan Xu, Hans-Dieter Burkhard Concurrency, Specification and Programming (CS&P), address Helenenau, Germany, 2010.
    @inproceedings{xucsp2010, address = {Helenenau, Germany}, author = {Yuan Xu and Hans-Dieter Burkhard}, booktitle = {Concurrency, Specification and Programming (CS&P)}, month = {September}, timestamp = {2014.01.27}, title = {Narrowing Reality Gap and Validation: Improving the Simulator for Humanoid Soccer Robot}, year = {2010} }

2009

  • Nao-Team Humboldt 2009 Hans-Dieter Burkhard, Florian Holzhauer, Thomas Krause, Heinrich Mellmann, Claas Norman Ritter, Oliver Welter, Yuan Xu Humboldt-Universität zu Berlin, 2009.
    @techreport{tdp09, author = {Hans-Dieter Burkhard and Florian Holzhauer and Thomas Krause and Heinrich Mellmann and Claas Norman Ritter and Oliver Welter and Yuan Xu}, institution = {Humboldt-Universität zu Berlin}, timestamp = {2010.02.03}, title = {NAO-Team Humboldt 2009}, url = {http://www.naoteamhumboldt.de/wp-content/uploads/2010/02/NaoTH09Report_final.pdf}, year = {2009} }
  • Theis RoboCup Robotics Artificial Intelligence Localization Approaches Constraints
    Constraint Based World Modeling For Multi Agent Systems In Dynamic Environments Daniel Göhring Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 2009. Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II .
    @phdthesis{Goehring10Dissertation, author = {Daniel Göhring}, doi = {http://dx.doi.org/10.18452/16040}, keyword = {Theis, RoboCup, Robotics, Artificial Intelligence, Localization Approaches, Constraints}, publisher = {Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II }, school = {Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II}, title = {Constraint based world modeling for multi agent systems in dynamic environments}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?id=30348}, year = {2009} }
    Mobile autonomous robotics is a very young and complex field of research. Only in recent decades have robots become able to explore, to move, navigate and to interact with their environment. Since the world is uncertain and since robots can only gain partial information about it, probabilistic navigation algorithms have become very popular whenever a robot has to localize itself or surrounding objects. Furthermore, cooperative exploration and localization approaches have become very relevant lately, as robots begin to act not just alone but in groups. Within this thesis a new approach using the concept of spatial percept-relations for cooperative environment modeling is presented and evaluated. As a second contribution, constraint based localization techniques will be introduced for having a robot or a group of robots efficiently localized and to model their environment.
  • Visuelle Gestenerkennung Zur Interaktion Zwischen Mensch Und Roboter (In German) F.A. Bertsch Proceedings of 15. Workshop Farbbildverarbeitung 2009, address Berlin, 2009.
    @inproceedings{Bertsch2009, address = {Berlin}, author = {Bertsch, F.A.}, booktitle = {Proceedings of 15. Workshop Farbbildverarbeitung 2009}, month = {08.-09.10.2009}, organization = {GfaI}, title = {Visuelle Gestenerkennung zur Interaktion zwischen Mensch und Roboter (in German)}, year = {2009} }
  • Gesture Recognition As A Prerequisite Of Imitation Learning In Human-Humanoid Experiments F.A. Bertsch, V.V. Hafner Proceedings of EpiRob09, Ninth International Conference on Epigenetic Robotics, pp. pp. 197–198, 2009.
    @inproceedings{BertschHafner09b, author = {Bertsch, F.A. and Hafner, V.V.}, booktitle = {Proceedings of EpiRob09, Ninth International Conference on Epigenetic Robotics}, editor = {Lola Canamero, Pierre-Yves Oudeyer, Christian Balkenius}, organization = {Lund University Cognitive Studies, 146}, pages = {pp. 197-198}, title = {Gesture recognition as a prerequisite of imitation learning in human-humanoid experiments}, year = {2009} }
  • Real-Time Dynamic Visual Gesture Recognition In Human-Robot Interaction F.A. Bertsch, V.V. Hafner Proceedings of Humanoids 2009, 9th IEEE-RAS International Conference on Humanoid Robots, 2009.
    @inproceedings{BertschHafner09a, author = {Bertsch, F.A. and Hafner, V.V.}, booktitle = {Proceedings of Humanoids 2009, 9th IEEE-RAS International Conference on Humanoid Robots}, title = {Real-time dynamic visual gesture recognition in human-robot interaction}, url = {https://ieeexplore.ieee.org/document/5379541}, year = {2009} }
  • Constraint Based Belief Modeling Daniel Göhring, Heinrich Mellmann, Hans-Dieter Burkhard RoboCup 2008: Robot Soccer World Cup XII, pp. 73–84, address Berlin, Heidelberg, 2009. Springer Berlin Heidelberg.
    @inproceedings{rc-goehringmellmann-08-preprint, address = {Berlin, Heidelberg}, author = {Göhring, Daniel and Mellmann, Heinrich and Burkhard, Hans-Dieter}, booktitle = {RoboCup 2008: Robot Soccer World Cup XII}, editor = {Iocchi, Luca and Matsubara, Hitoshi and Weitzenfeld, Alfredo and Zhou, Changjiu}, isbn = {978-3-642-02921-9}, pages = {73--84}, publisher = {Springer Berlin Heidelberg}, title = {Constraint Based Belief Modeling}, year = {2009} }
    In this paper we present a novel approach using constraint based techniques for world modeling, i.e. self localization and object modeling. Within the last years, we have seen a reduction of landmarks as beacons, colored goals, within the RoboCup domain. Using other features as line information becomes more important. Using such sensor data is tricky, especially when the resulting position belief is stretched over a larger area. Constraints can overcome this limitations, as they have several advantages: They can represent large distributions and are easy to store and to communicate to other robots. Propagation of a several constraints can be computationally cheap. Even high dimensional belief functions can be used. We will describe a sample implementation and show experimental results.
  • Autonomous Agents Humanoid Robots Localization
    Constraint Based World Modeling In Mobile Robotics Daniel Göhring, Heinrich Mellmann, Hans-Dieter Burkhard Proc. IEEE International Conference on Robotics and Automation (ICRA 2009), pp. 2538–2543, 2009.
    @inproceedings{ICRA-GoehringMellmann-09, author = {Daniel Göhring and Heinrich Mellmann and Hans-Dieter Burkhard}, booktitle = {Proc. IEEE International Conference on Robotics and Automation (ICRA 2009)}, doi = {10.1109/ROBOT.2009.5152208}, file = {:ICRA-GoehringMellmann-09.pdf:PDF}, keyword = {Autonomous Agents, Humanoid Robots, Localization}, pages = {2538--2543}, title = {Constraint Based World Modeling in Mobile Robotics}, year = {2009} }
    In this paper we present a novel approach using constraint based techniques for world modeling, i.e. self localization and object modeling. Within the last years, we have seen a reduction of landmarks such as beacons or colored goals within the RoboCup domain. Using other features as line information becomes more important. Using such sensor data is tricky, especially when the resulting position belief is stretched over a larger area. Constraints can overcome this limitations, as they have several advantages: they can represent large distributions and are easy to store and to communicate to other robots. Propagation of several constraints can be computationally cheap. Even high dimensional belief functions can be used. We will describe a sample implementation and show experimental results.
  • RoboCup localization landmark selection active vision humanoid robots Aibo
    Active Landmark Selection For Vision-Based Self-Localization Heinrich Mellmann Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P), volume Volume 2, pp. 398–405, address Kraków-Przegorzaly, Poland, 2009.
    @inproceedings{CSP-Mellmann-09, address = {Kraków-Przegorzaly, Poland}, author = {Heinrich Mellmann}, booktitle = {Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P)}, keyword = {RoboCup, localization, landmark selection, active vision, humanoid robots, Aibo}, month = {September}, pages = {398--405}, timestamp = {2009.10.04}, title = {Active Landmark Selection for Vision-Based Self-Localization}, url = {http://csp2009.mimuw.edu.pl/proc.php}, volume = {Volume 2}, year = {2009} }
    The most of the vision based self-localization methods are using landmarks to estimate the position of the robot. The results of those methods depend highly on the precision of the perceptual information provided by the vision system. Depending on situation, some landmarks provide more certain measurements than others. We present a general criterion to predict the sensitivity of measurements concerning errors. In addition an algorithm is presented for automatic selection of optimal landmarks. This enables the robot to choose actively those landmarks that provide the highest certainty, which leads to better localization results. We demonstrate the performance and accuracy of the algorithm through a series of experiments.
  • Reinforcement Learning In Continuous State And Action Spaces Victor Uc-Cetina Humboldt-Universität zu Berlin, 2009.
    @phdthesis{uccetina09thesis, author = {Victor Uc-Cetina}, school = {Humboldt-Universität zu Berlin}, title = {Reinforcement Learning in Continuous State and Action Spaces}, year = {2009} }

2008

  • Improving Vision-Based Distance Measurements Using Reference Objects Matthias Jüngel, Heinrich Mellmann, Michael Spranger RoboCup 2007: Robot Soccer World Cup XI, pp. 89–100, address Berlin, Heidelberg, 2008. Springer Berlin Heidelberg.
    @inproceedings{rc-juengelmellmannspranger-07-preprint, address = {Berlin, Heidelberg}, author = {Jüngel, Matthias and Mellmann, Heinrich and Spranger, Michael}, booktitle = {RoboCup 2007: Robot Soccer World Cup XI}, editor = {Visser, Ubbo and Ribeiro, Fernando and Ohashi, Takeshi and Dellaert, Frank}, isbn = {978-3-540-68847-1}, pages = {89--100}, publisher = {Springer Berlin Heidelberg}, title = {Improving Vision-Based Distance Measurements Using Reference Objects}, year = {2008} }
    Robots perceiving their environment using cameras usually need a good representation of how the camera is aligned to the body and how the camera is rotated relative to the ground. This is especially important for bearing-based distance measurements. In this paper we show how to use reference objects to improve vision-based distance measurements to objects of unknown size. Several methods for different kinds of reference objects are introduced. These are objects of known size (like a ball), objects extending over the horizon (like goals and beacons), and objects with known shape on the ground (like field lines). We give a detailed description how to determine the rotation of the robot's camera relative to the ground, provide an error-estimation for all methods and describe the experiments we performed on an Aibo robot.
  • Constraint Based Object State Modeling Daniel Göhring, Heinrich Mellmann, Hans-Dieter Burkhard European Robotics Symposium 2008 (EUROS), Springer Tracts in Advanced Robotics, volume Volume 44/2008, pp. 63–72, address Prague, Chech Republic, 2008. Springer Berlin / Heidelberg.
    @inproceedings{EUROS-GoehringMellmann-08, address = {Prague, Chech Republic}, author = {Daniel Göhring and Heinrich Mellmann and Hans-Dieter Burkhard}, booktitle = {European Robotics Symposium 2008 (EUROS)}, doi = {10.1007/978-3-540-78317-6_7}, editor = {Bruyninckx Herman and Preucil Libor and Kulich Miroslav}, pages = {63--72}, publisher = {Springer Berlin / Heidelberg}, series = {Springer Tracts in Advanced Robotics}, title = {Constraint Based Object State Modeling}, url = {http://www.springerlink.com/content/th6218453434x817}, volume = {Volume 44/2008}, year = {2008} }
    Modeling the environment is crucial for a mobile robot. Common approaches use Bayesian filters like particle filters, Kalman filters and their extended forms. We present an alternative and supplementing approach using constraint techniques based on spatial constraints between object positions. This yields several advantages: a) the agent can choose from a variety of belief functions, b) the computational complexity is decreased by efficient algorithms. The focus of the paper are constraint propagation techniques under the special requirements of navigation tasks.
  • Constraint Based Belief Modeling Daniel Göhring, Heinrich Mellmann, Hans-Dieter Burkhard RoboCup 2008: Robot Soccer World Cup XII, Lecture Notes in Artificial Intelligence, pp. 73–84, address Berlin, Heidelberg, 2008. Springer Berlin Heidelberg.
    @inproceedings{RC-GoehringMellmann-08, address = {Berlin, Heidelberg}, author = {Daniel Göhring and Heinrich Mellmann and Hans-Dieter Burkhard}, booktitle = {RoboCup 2008: Robot Soccer World Cup XII}, doi = {10.1007/978-3-642-02921-9}, editor = {Luca Iocchi and Hitoshi Matsubara and Alfredo Weitzenfeld and Changjiu Zhou}, pages = {73--84}, publisher = {Springer Berlin Heidelberg}, series = {Lecture Notes in Artificial Intelligence}, title = {Constraint Based Belief Modeling}, year = {2008} }
    In this paper we present a novel approach using constraint based techniques for world modeling, i.e. self localization and object modeling. Within the last years, we have seen a reduction of landmarks as beacons, colored goals, within the RoboCup domain. Using other fea- tures as line information becomes more important. Using such sensor data is tricky, especially when the resulting position belief is stretched over a larger area. Constraints can overcome this limitations, as they have several advantages: They can represent large distributions and are easy to store and to communicate to other robots. Propagation of a several constraints can be computationally cheap. Even high dimensional belief functions can be used. We will describe a sample implementation and show experimental results.
  • Constraint Based World Modeling Daniel Göhring, Heinrich Mellmann, Kataryna Gerasymova, Hans-Dieter Burkhard Fundamenta Informaticae, volume 85, number 1-4, pp. 123–137, 2008.
    @article{FI-GoehringMellmannGerasimova-08, author = {Daniel Göhring and Heinrich Mellmann and Kataryna Gerasymova and Hans-Dieter Burkhard}, journal = {Fundamenta Informaticae}, number = {1-4}, pages = {123-137}, title = {Constraint Based World Modeling}, url = {https://content.iospress.com/articles/fundamenta-informaticae/fi85-1-4-10}, volume = {85}, year = {2008} }
    Common approaches for robot navigation use Bayesian filters like particle filters, Kalman filters and their extended forms. We present an alternative and supplementing approach using constraint techniques based on spatial constraints between object positions. This yields several advantages. The robot can choose from a variety of belief functions, and the computational complexity is decreased by efficient algorithms. The paper investigates constraint propagation techniques under the special requirements of navigation tasks. Sensor data are noisy, but a lot of redundancies can be exploited to improve the quality of the result. We introduce two quality measures: The ambiguity measure for constraint sets defines the precision, while inconsistencies are measured by the inconsistency measure. The measures can be used for evaluating the available data and for computing best fitting hypothesis. A constraint propagation algorithm is presented.
  • Constraint Based Localization On A Humanoid Robot Daniel Göhring, Heinrich Mellmann, Hans-Dieter Burkhard Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P), 2008.
    @inproceedings{CSP-GoehringMellmannEtAl-08, author = {Daniel Göhring and Heinrich Mellmann and Hans-Dieter Burkhard}, booktitle = {Proceedings of the Workshop on Concurrency, Specification, and Programming (CS&P)}, timestamp = {2009.10.05}, title = {Constraint Based Localization on a Humanoid Robot}, year = {2008} }
    In this paper we will present an application for constraint based methods to self localize within the RoboCup domain. During a robotic soccer game, robots of a team need to know where they and their team mates are on the Field, therefore they need to localize themselves. For self localization, constraint based methods can be an effective alternative to classic Bayesian approaches as Kalman filters or Monte-Carlo methods. In this paper we will present, how constraint based techniques can be applied to a humanoid robot. Therefore we will implement constraint based methods in a humanoid robot "NAO" and see how the constraint based approach works within the Standard Platform League.
  • Memory-Based State-Estimation Matthias Jüngel, Heinrich Mellmann Fundamenta Informaticae, volume Volume 85, number Number 1-4, pp. 297–311, 2008.
    @article{FI-JuengelMellmann-08, author = {Matthias Jüngel and Heinrich Mellmann}, journal = {Fundamenta Informaticae}, number = {Number 1-4}, pages = {297--311}, timestamp = {2008.08.05}, title = {Memory-Based State-Estimation}, url = {http://iospress.metapress.com/content/2051310891588554/}, volume = {Volume 85}, year = {2008} }
    In this paper we introduce a state-estimation method that uses a short-term memory to calculate the current state. A common way to solve state estimation problems is to use implementations of the Bayesian algorithm like Kalman filters or particle filters. When implementing a Bayesian filter several problems can arise. One difficulty is to obtain error models for the sensors and for the state transitions. The other difficulty is to find an adequate compromise between the accuracy of the belief probability distribution and the computational costs that are needed to update it. In this paper we show how a short-term memory of perceptions and actions can be used to calculate the state. In contrast to the Bayesian filter, this method does not need an internal representation of the state which is updated by the sensor and motion information. It is shown that this is especially useful when information of sparse sensors (sensors with non-unique measurements with respect of the state) has to be integrated.
  • Localization Computer Vision Recognition
    Using Reference Objects To Improve Vision-Based Bearing Measurements Heinrich Mellmann, Matthias Jüngel, Michael Spranger Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems IROS 2008, pp. 3939–3945, address Acropolis Convention Center, Nice, France, 2008. IEEE.
    @inproceedings{IROS-MellmannJuengelSpranger-08, address = {Acropolis Convention Center, Nice, France}, author = {Heinrich Mellmann and Matthias Jüngel and Michael Spranger}, booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems IROS 2008}, doi = {10.1109/IROS.2008.4651128}, keyword = {Localization, Computer Vision, Recognition}, month = {22--26 Sept.}, pages = {3939--3945}, publisher = {IEEE}, timestamp = {2008.08.05}, title = {Using Reference Objects to Improve Vision-Based Bearing Measurements}, year = {2008} }
    Robots perceiving its environment using cameras usually need a good representation of how the camera is aligned to the body and how the camera is rotated relative to the ground. This is especially important for bearing-based distance measurement. In this paper we show how to use reference objects to improve vision-based distance measurements to objects of unknown size. Several methods for different kinds of reference objects are introduced. These are objects of known size (like a ball), objects extending over the horizon (like goals and beacons), and objects with known shape on the ground (like field lines). We give a detailed description how to determine the rotation of the robot's camera relative to the ground, provide an error-estimation for all methods and describe the experiments we performed on an Aibo robot.

2007

  • RoboCup humanoid robots Aibo camera matrix reference objects
    Improving Vision-Based Distance Measurements Using Reference Objects Matthias Jüngel, Heinrich Mellmann, Michael Spranger RoboCup 2007: Robot Soccer World Cup XI, Lecture Notes in Computer Science, volume Volume 5001/2008, pp. 89–100, 2007. Springer Berlin / Heidelberg.
    @inproceedings{RC-JuengelMellmannSpranger-07, author = {Matthias Jüngel and Heinrich Mellmann and Michael Spranger}, booktitle = {RoboCup 2007: Robot Soccer World Cup XI}, doi = {10.1007/978-3-540-68847-1}, editor = {Ubbo Visser and Fernando Ribeiro and Takeshi Ohashi and Frank Dellaert}, keyword = {RoboCup, humanoid robots, Aibo, camera matrix, reference objects}, pages = {89--100}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, timestamp = {Freitag, 18. Juli 2008}, title = {Improving Vision-Based Distance Measurements using Reference Objects}, url = {http://www.springerlink.com/content/y4730241r836k4l5}, volume = {Volume 5001/2008}, year = {2007} }
    Robots perceiving their environment using cameras usually need a good representation of how the camera is aligned to the body and how the camera is rotated relative to the ground. This is especially important for bearing-based distance measurements. In this paper we show how to use reference objects to improve vision-based distance measurements to objects of unknown size. Several methods for different kinds of reference objects are introduced. These are objects of known size (like a ball), objects extending over the horizon (like goals and beacons), and objects with known shape on the ground (like field lines). We give a detailed description how to determine the rotation of the robot's camera relative to the ground, provide an error-estimation for all methods and describe the experiments we performed on an Aibo robot.
  • Exploiting Past Experience. Case-Based Decision Support For Soccer Agents Ralf Berger, Gregor Lämmel Proceedings of the 30th Annual German Conference on Artificial Intelligence (KI'07), 2007. Springer.
    @inproceedings{berger-laemmel-wall-pass, author = {Ralf Berger and Gregor Lämmel}, booktitle = {Proceedings of the 30th Annual German Conference on Artificial Intelligence (KI'07)}, publisher = {Springer}, title = {Exploiting Past Experience. Case-Based Decision Support for Soccer Agents}, year = {2007} }

2006

  • Die Doppelpass-Architektur. Verhaltenssteuerung Autonomer Agenten In Dynamischen Umgebungen Ralf Berger Diploma Thesis. Humboldt-Universität zu Berlin, Institut für Informatik, 2006. (in German)
    @mastersthesis{diplom-berger, author = {Ralf Berger}, note = {(in German)}, school = {Humboldt-Universität zu Berlin, Institut für Informatik}, title = {Die Doppelpass-Architektur. Verhaltenssteuerung autonomer Agenten in dynamischen Umgebungen}, type = {Diploma Thesis}, year = {2006} }