Sie sind hier: Startseite › Publications

Publications

2022

  • Maria Kalweit, Gabriel Kalweit, Moritz Werling and Joschka Boedecker. Deep Surrogate Q-Learning for Autonomous Driving. Accepted at ICRA 2022.
  • Jessica Borja-Diaz*, Oier Mees*, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker and Wolfram Burgard. Affordance Learning from Play for Sample-Efficient Policy Learning. Accepted at ICRA 2022.
  • Gabriel Kalweit, Maria Kalweit, Joschka Boedecker. Robust and Data-efficient Q-learning by Composite Value-estimation. Accepted at TMLR 2022.
  • Erick Rosete-Beas*, Oier Mees*, Gabriel Kalweit, Joschka Boedecker and Wolfram Burgard. Latent Plans for Task-Agnostic Offline Reinforcement Learning. Accepted at CoRL 2022.

2021

  • Branka Mirchevska, Maria Hügle, Gabriel Kalweit, Moritz Werling, Joschka Boedecker (2021) Amortized Q-learning with Model-based Action Proposals for Autonomous Driving on Highways, IEEE International Conference on Robotics and Automation (ICRA), pp. 1028-1035, doi: 10.1109/ICRA48506.2021.9560777.
  • Maria Hügle, Ulrich A Walker, Axel Finckh, Ruediger Mueller, Gabriel Kalweit, Almut Scherer, Joschka Boedecker, Thomas Hügle (2021)  Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network. PLoS ONE 16(6): e0252289. doi: https://doi.org/10.1371/journal.pone.0252289
  • Maria Kalweit, Gabriel Kalweit and Joschka Boedecker. AnyNets: Adaptive Deep Neural Networks for Medical Data with Missing Values. Accepted at IJCAI 2021 Workshop on Artificial Intelligence for Function, Disability, and Health. PDF
  • Maria Kalweit, Gabriel Kalweit, Moritz Werling and Joschka Boedecker. Deep Surrogate Q-Learning for Autonomous Driving. Accepted at IJCAI 2021 Workshop on Artificial Intelligence for Autonomous Driving.
  • Gabriel Kalweit, Maria Kalweit, Mansour Alyahyay, Zoe Jaeckel, Florian Steenbergen, Stefanie Hardung, Ilka Diester and Joschka Boedecker (2021) NeuRL: Closed-form Inverse Reinforcement Learning for Neural Decoding. Accepted at ICML 2021 Workshop on Computational Biology.

  • Gabriel Kalweit, Maria Huegle, Moritz Werling and Joschka Boedecker (2021) Q-learning with Long-term Action-space Shaping to Model Complex Behavior for Autonomous Lane Changes, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5641-5648, doi: 10.1109/IROS51168.2021.9636668.

  • A. Ranjbar, N. A. Vien, H. Ziesche, J. Boedecker and G. Neumann (2021) Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2383-2390, doi: 10.1109/IROS51168.2021.9636176.

2020

  • Lukas A. W. Gemein, Robin T. Schirrmeister, Patryk Chrabaszcz, Daniel Wilson, Joschka Boedecker, Andreas Schulze-Bonhage, Frank Hutter, Tonio Ball (2020). Machine-Learning-Based Diagnostics of EEG Pathology, NeuroImage, volume 220, 15 October 2020, p. 117021, doi: 10.1016/j.neuroimage.2020.117021
  • Lilli Frison, Sweetin Paul, Torsten Koller, David Fischer, Gianluca Frison, Joschka Boedecker, Peter Engelmann (2020). Hardware-In-The-Loop Test of Learning-Based Controllers for Grid-Supportive Building Heating Operation. Accepted at the 21st IFAC World Congress.
  • Maria Hügle, Gabriel Kalweit, Thomas Hügle and Joschka Boedecker (2020). A Dynamic Deep Neural Network For Multimodal Clinical Data Analysis. AAAI 2020 Workshop on Health Intelligence. Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, Springer. web arxiv
  • Maria Hügle, Patrick Omoumi, Jaap van Laar, Joschka Boedecker and Thomas Hügle (2020). Applied Machine Learning and Artificial Intelligence in Rheumatology. Rheumatology Advances in Practice. web
  • Maria Huegle, Gabriel Kalweit, Moritz Werling and Joschka Boedecker (2020). Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving. IEEE International Conference on Robotics and Automation (ICRA). arxiv
  • Kalweit, G., Huegle, M., & Boedecker, J. (2020). Composite Q-learning: Multi-scale Q-function Decomposition and Separable Optimization. arXiv preprint arXiv:1909.13518. arxiv
  • Kalweit, G.*, Huegle, M.*, Werling, M. & Boedecker, J. (2020). Deep Inverse Q-learning with Constraints. Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pp. 14291-14302. PDF

2019

  • J Wülfing, SS Kumar, J Boedecker, M Riedmiller, U Egert (2018) Adaptive Long-term Control of Biological Neural Networks with Deep Reinforcement Learning. Neurocomputing, Volume 342, pp. 66-74. web
  • D. Kuhner, L.D.J. Fiederer, J. Aldinger, F. Burget, M. Völker, R.T. Schirrmeister, C. Do, J. Boedecker, B. Nebel, T. Ball, W. Burgard (2019) A service assistant combining autonomous robotics, flexible goal formulation, and deep-learning-based brain–computer interfacing, Robotics and Autonomous Systems, Volume 116, pp. 98-113. web bioRxiv
  • Mohamed Abouhussein, Stefan Müller, Joschka Boedecker (2019) Multimodal Spatio-Temporal Information in End-To-End Networks for Automotive Steering Prediction. In Proc. of the IEEE International Conference on Robotics and Automation (ICRA). 
  • J. Zhang, L. Tai, P. Yun, Y. Xiong, M. Liu, J. Boedecker & W. Burgard (2019). Vr-goggles for robots: Real-to-sim domain adaptation for visual control. IEEE Robotics and Automation Letters, 4(2), pp. 1148-1155. web  arXiv
  • J. Zhang, N. Wetzel, N. Dorka, J. Boedecker, and W. Burgard (2019). Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration. In Proc. of the Workshop of Exploration in Reinforcement Learning at IEEE International Conference on Machine Learning (ICML), 2019.
  • Maria Huegle*, Gabriel Kalweit*, Branka Mirchevska, Moritz Werling and Joschka Boedecker (2019). Dynamic Input for Deep Reinforcement Learning in Autonomous Driving.  In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). arXiv
  • Fiederer, L. D., Völker, M., Schirrmeister, R. T., Burgard, W., Boedecker, J., and Ball, T. (2019). Hybrid Brain-Computer-Interfacing for Human-Compliant Robots: Inferring Continuous Subjective Ratings with Deep Regression. Frontiers in Neurorobotics, 13, 76. web
  • Koller, T., Berkenkamp, F., Turchetta, M., Bödecker, J., and Krause, A. (2019). Learning-based Model Predictive Control for Safe Reinforcement Learning. Extended abstract at RSS 2019 Workshop on Robust Autonomy. web
  • Gabriel Kalweit, Maria Huegle and Joschka Boedecker. Composite Q-Learning. Extended abstract at RSS 2019 Workshop on Combining Learning and Reasoning – Towards Human-Level Robot Intelligence. web
  • Maria Hügle, Gabriel Kalweit, Moritz Werling, and Joschka Boedecker. Learning Dynamic Representations for Deep Reinforcement Learning in Autonomous Driving. Extended abstract at RSS 2019 Workshop on Scene and Situation Understanding for Autonomous Driving. web
  • Maria Hügle, Joschka Boedecker and Thomas Hügle. Clinical Event-based Adaptive Deep Learning for the Prediction of Disease Progression in Rheumatoid Arthritis (Abstract at Frontier of AI-Assisted Care Scientific Symposium, Stanford 2019).

2018

  • B. Mirchevska, C. Pek, M. Werling, M. Althoff, & J. Boedecker (2018). High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning. In Proc. of the IEEE Int. Conf. on Intelligent Transportation Systems. PDF
  • J Wülfing, SS Kumar, J Boedecker, M Riedmiller, U Egert (2018) Controlling Biological Neural Networks with Deep Reinforcement Learning. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018)  ("Best Student Paper Award") PDF
  • Maria Hügle, Simon Heller, Manuel Watter, Manuel Blum, Farrokh Manzouri, Matthias Dümpelmann, Andreas Schulze-Bonhage, Peter Woias, Joschka Boedecker (2018) Early Seizure Detection with an Energy-Efficient Convolutional Neural Network on an Implantable Microcontroller. International Joint Conference on Neural Networks (IJCNN 2018) ("Best Paper Award") web
  • Simon Heller, Maria Hügle, Iman Nematollahi, Farrokh Manzouri, Matthias Dümpelmann, Andreas Schulze-Bonhage, Joschka Boedecker, Peter Woias. Hardware Implementation of a Performance and Energy-Optimized Convolutional Neural Network for Seizure Detection (EMBC 2018)
  • Robert Dürichen, Keshav Deep Verma, Seow Yuen Yee, Thomas Rocznik, Philip Schmidt, Joschka Boedecker, Christian Peters (2018). Prediction of electrocardiography features points using seismocardiography data: a machine learning approach. Proceedings of the 2018 ACM International Symposium on Wearable Computers (UbiComp 2018), pp. 96-99.

2017

  • Groß, Wolfgang, Sascha Lange, Joschka Bödecker, and Manuel Blum. (2017) Predicting Time Series with Space-Time Convolutional and Recurrent Neural Networks. Proc. of the 25th ESANN: 71-76.
  • Zhang, Jingwei, Lei Tai, Joschka Boedecker, Wolfram Burgard, and Ming Liu (2017) Neural SLAM. arXiv preprint arXiv:1706.09520
  • Burget, F., Fiederer, L.D.J., Kuhner, D., Völker, M., Aldinger, J., Schirrmeister, R.T., Do, C., Boedecker, J., Nebel, B., Ball, T. and Burgard, W. (2017) Acting thoughts: Towards a mobile robotic service assistant for users with limited communication skills. In Mobile Robots (ECMR), 2017 European Conference on (pp. 1-6). IEEE.
  • Zhang, Jingwei, Jost Tobias Springenberg, Joschka Boedecker, and Wolfram Burgard. (2017) Deep reinforcement learning with successor features for navigation across similar environments. In Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference on, pp. 2371-2378. IEEE.
  • Gabriel Kalweit, Joschka Boedecker (2017) Uncertainty-driven Imagination for Continuous Deep Reinforcement Learning. Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:195-206. PDF
  • B. Mirchevska, M. Blum, L. Louis, J. Boedecker, M. Werling (2017) Reinforcement Learning for Autonomous Maneuvering in Highway Scenarios. 11. Workshop Fahrerassistenz und automatisiertes Fahren. PDF

2016

  • SS Kumar, J Wülfing, S Okujeni, J Boedecker, M Riedmiller, U Egert (2016) Autonomous Optimization of Targeted Stimulation of Neuronal Networks. PLoS Comput Biol 12 (8) pp. e1005054. web
  • Jost Tobias Springenberg, Katharina Wilmes, Joschka Boedecker (2016) Towards Local Learning and MCMC Inference in Biologically Plausible Deep Generative Networks. In NIPS Workshop Brains and Bits: Neuroscience Meets Machine Learning. PDF
  • Heller, Simon, Michael Kroener, Peter Woias, Christian Donos, Farrokh Manzouri, Daniel Lachner-Piza, Andreas Schulze-Bonhage, Matthias Duempelmann, Manuel Blum, and Joschka Boedecker (2016) On the way to a self-sufficient closed-loop implant for early seizure detection. Biomedical Engineering/Biomedizinische Technik 61, no. s1: 133-136.

2015

  • Wendelin Böhmer, Jost Tobias Springenberg, Joschka Boedecker, Martin Riedmiller, Klaus Obermayer (2015) Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations. KI - Künstliche Intelligenz pp. 1-10. Springer Berlin Heidelberg. doi web
  • Manuel Watter, Jost Springenberg, Joschka Boedecker, Martin Riedmiller (2015) Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images. In Advances in Neural Information Processing Systems 28. pp. 2728–2736. PDF

2014

  • Oliver Obst, Joschka Boedecker (2014) Guided Self-Organization of Input-Driven Recurrent Neural Networks. In Guided Self-Organization: Inception. pp. 319-340. Springer Berlin Heidelberg. doi web
  • Joschka Boedecker, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2014) Approximate Real-Time Optimal Control Based on Sparse Gaussian Process Models. In Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). PDF
  • Sreedhar Saseendran Kumar, Jan Wülfing, Joschka Boedecker, Ralf Wimmer, Martin Riedmiller, Bernd Becker, and Ulrich Egert (2014) Autonomous control of network activity. In Proc. of the 9th Int’l Meeting on Substrate-Integrated Microelectrode Arrays (MEA).

2013

  • Joschka Boedecker, Thomas Lampe, Martin Riedmiller (2013) Modeling effects of intrinsic and extrinsic rewards on the competition between striatal learning systems. Frontiers in Psychology 4 (739) doi web
  • Oliver Obst, Joschka Boedecker, Benedikt Schmidt, Minoru Asada (2013) On active information storage in input-driven systems. arXiv.org. web

2012

  • Oliver Obst, Joschka Boedecker, Benedikt Schmidt, Minoru Asada (September 2012) Computing local active information storage in input-driven systems.
  • Christoph Hartmann, Joschka Boedecker, Oliver Obst, Shuhei Ikemoto AND Minoru Asada (July 2012) Real-Time Inverse Dynamics Learning for Musculoskeletal Robots based on Echo State Gaussian Process Regression. In Proceedings of Robotics: Science and Systems. Sydney, Australia.
  • Joschka Boedecker, Oliver Obst, Yuki Kashima, Minoru Asada (March 29-30 2012) Intrinsic computational capabilities of reservoir computing networks in different dynamics regimes and their relation to task performance. Lyon, France.
  • Joschka Boedecker, Oliver Obst, Joseph T Lizier, N Michael Mayer, Minoru Asada (2012) Information processing in echo state networks at the edge of chaos.. Theory in Biosciences 131 (3) pp. 205–213. Springer Berlin / Heidelberg. doi web

2011

  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil (September 2011) Elevated activation of dopaminergic brain areas facilitates behavioral state transition. In IROS 2011 Workshop on Cognitive Neuroscience Robotics.
  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil, Linda B. Smith (2011) Between Frustration and Elation: Sense of Control Regulates the Intrinsic Motivation for Motor Learning.
  • Beata J. Grzyb, Joschka Boedecker, Minoru Asada, Angel P. del Pobil, Linda B. Smith (2011) Trying anyways: how ignoring the errors may help in learning new skills. In First Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics.
  • Joschka Boedecker (2011) Echo State Network Reservoir Shaping and Information Dynamics at the Edge of Chaos. Osaka, Japan.

2010

  • Oliver Obst, Joschka Boedecker, Minoru Asada (2010) Improving Recurrent Neural Network Performance Using Transfer Entropy. In Neural Information Processing Models and Applications. pp. 193–200. Springer. web

2009

  • Joschka Boedecker, Oliver Obst, Norbert Michael Mayer, Minoru Asada (Oct 2009) Initialization and Self-Organized Optimization of Recurrent Neural Network Connectivity. HFSP Journal 3 (5) pp. 340–349. doi web
  • Joschka Boedecker, Oliver Obst, Norbert Michael Mayer, Minoru Asada (apr 2009) Studies on Reservoir Initialization and Dynamics Shaping in Echo State Networks. In Proceedings of the 17th European Symposium On Artificial Neural Networks ({ESANN}'09). pp. 227–232. D-Side Publications. Evere, Belgium. web 
  • Norbert Michael Mayer, Joschka Boedecker, Minoru Asada (2009) Robot motion description and real-time management with the Harmonic Motion Description Protocol. Robotics and Autonomous Systems 57 (8) pp. 870-876. web

2008

  • Rodrigo da Silva Guerra, Joschka Boedecker, Norbert Michael Mayer, Shinzo Yanagimachi, Yasuji Hirosawa, Kazuhiko Yoshikawa, Masaaki Namekawa, Minoru Asada (2008) Introducing Physical Visualization Sub-League. In RoboCup 2007: Robot Soccer World Cup XI. pp. 496–503. Springer.
  • Norbert Michael Mayer, Joschka Boedecker, Kazuhiro Masui, Masaki Ogino, Minoru Asada (2008) HMDP: A new protocol for motion pattern generation towards behavior abstraction. In RoboCup 2007: Robot Soccer World Cup XI. pp. 184-195. Springer. web 
  • Joschka Boedecker, Minoru Asada (2008) SimSpark – Concepts and Application in the 3D Soccer Simulation League. In Workshop on The Universe of RoboCup Simulators at SIMPAR 2008. web 

2007

  • Norbert Michael Mayer, Joschka Boedecker, Rodrigo da Silva Guerra, Minoru Asada (2007) 3D2Real: Simulation League Finals in Real Robots. In RoboCup 2006: Robot Soccer World Cup X. pp. 25-34. web
  • Rodrigo da Silva Guerra, Joschka Boedecker, Minoru Asada (2007) Physical Visualization Sub-League: A New Platform for Research and Edutainment. pp. 15–20.
  • Rodrigo da Silva Guerra, Joschka Boedecker, Shinzo Yanagimachi, Minoru Asada (2007) Introducing a New Minirobotics Platform for Research and Edutainment. In Proceedings of the 4th International Symposium on Autonomous Minirobots for Research and Edutainment.
  • Rodrigo da Silva Guerra, Joschka Boedecker, Norbert Michael Mayer, Shinzo Yanagimachi, Hiroshi Ishiguro, Minoru Asada (2007) A new minirobotics system for teaching and researching agent-based programming. In CATE '07: Proceedings of the 10th IASTED International Conference on Computers and Advanced Technology in Education. pp. 39–44. ACTA Press. Anaheim, CA, USA. 
  • Michael Mayer, Joschka Boedecker, Minoru Asada (2007) On Standardization in the RoboCup Soccer Humanoids Leagues. web 

2006

  • Minoru Asada, Norbert Michael Mayer, Joschka Boedecker, Masaki Ogino, Sawa Fuke (2006) The RoboCup Soccer Humanoid League: Overview and Outlook. web Bibtex
  • Oliver Obst, Joschka Boedecker (2006) Flexible Coordination of Multiagent Team Behavior using HTN Planning. In RoboCup 2005: Robot Soccer World Cup IX. pp. 521-528. Springer. web Bibtex
  • Joschka Boedecker, Norbert Michael Mayer, Masaki Ogino, Rodrigo da Silva Guerra, Masaki Kikuchi, Minoru Asada (2006) Getting closer: How Simulation and Humanoid League can benefit from each other. In Proceedings of the 3rd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE 2005). pp. 93-98. Springer. web

2005

  • Oliver Obst, Anita Maas, Joschka Boedecker (Jul 2005) HTN Planning for Flexible Coordination Of Multiagent Team Behavior. pp. 87–94. Edinburgh, Scotland.