Curriculum Vitae

Herke van Hoof

Research Interests

Machine Learning Algorithms ensure suitable and adaptive information processing. Reinforcement learning and active learning couple an agent's actions to its learning experiences, necessitating effective exploration strategies. Bayesian approaches and information-theoretic strategies are suitable for problems with scarce training data.

Autonomous Robots explore their environment and learn by interacting rather than from human labels or demonstration. Such exploration can be guided by external rewards or intrinsic motivation. Autonomous robots can navigate to, grasp, and manipulate tools and objects in their environment. Algorithms for robot learning and control should exploit knowledge of physical properties of robot systems.

Machine Perception is critical to understanding the environment through e.g. tactile sensing or vision. Sensory processing can be facilitated by interactive perception: exploiting tight coupling of actions selected to yield informative percepts. High-dimensional sensory data can be handled by learning task relevant features.

Current Position
Since 2016 Postdoctoral Fellow at McGill University, Montreal, Canada
The fellowship focuses on allowing robots to learn new tasks more efficiently using prior knowledge about robotics and experience with similar tasks. This research is performed in collaboration with Professors J. Pineau, D. Meger and G. Dudek
Educational Background
2011-2016 Ph.D. in Computer Science (with distinction)
Technische Universität Darmstadt, Germany
Thesis: "Machine Learning through Exploration for Perception-Driven Robotics" (2016).
Supervisor: Prof. Dr. J. Peters.
2008-2011 Master of Science in Artificial Intelligence (with honors)
"Autonomous Perceptive Systems" track.
University of Groningen, the Netherlands
Thesis: "Interaction between Face Detection and Learning Tracking Systems for Autonomous Robots" (2011).
Supervisors: Dr. T. van der Zant, Dr. M. Wiering, Dr. P.F. Dominey and Prof. Dr. L. Schomaker.
2005-2008 Bachelor of Science in Artificial Intelligence (with honors)
University of Groningen, the Netherlands.
Thesis: "Using Different Methods to Direct a Robot's Attention" (2008) .
Supervisors: G. Kootstra and S. de Jong.
Internships and Visitorships
2015 Visiting graduate student, Biomimetic Robotics and Machine Learning Lab, Technische Universität München
During my visit at TUM in the framework of the TACMAN FP7 European Union-funded project, I worked together with Prof. Dr. P. van der Smagt, N. Chen, and M. Karl on policy search for manipulation with tactile feedback.
2010 Research internship,Robot Cognition Laboratory, INSERM U846, Lyon, France.
During this internship I applied machine learning and computer vision techniques to humanoid robots. With the "Radical Dudes" team, we participated in the international RoboCup@Home competitions with a NAO robot.
Extracurricular activities
2010-2011 Member of RoboCup-team "BORG", which participated in international RoboCup@Home competitions. These competitions focus on benchmarking abilities of domestic service robots in realistic environments.
2008-2010 Team leader RoboCup-team "the little green BATS". This team participated in the 3D-soccer simulation league using simulated NAO robots.
Teaching
Guest lectures, McGill University
Machine Learning, lecture on inference in time series models2017
Teaching assistant, Technische Universität Darmstadt
Technical Foundations of Computer Science2014-2015
Computational Engineering2013-2014
Machine Learning Lecture2013
Robot Learning Lecture2012-2013
Robot Learning Project2011-2012, 2012-2013, 2013, 2014, 2014-2015, 2015-2016
Guest lectures, Technische Universität Darmstadt
Technical Foundations of Computer Science2014-2015
Teaching assistant, Rijksuniversiteit Groningen
Multi-agent Systems Lecture2011
Robotics Lab Course2010-2011
Language and Speech Technology Lab Course2009
Introduction to Logic Lecture2008
Organized Events
Workflow co-chair, International Conference on Machine Learning (ICML) 2017
R:SS 2016 Workshop on Robot-Environment Interaction for Perception and Manipulation. Website
Humanoids 2014 Workshop on Active Learning in Robotics. Website
Reviewing
Journals 
2016IEEE Transactions on Robotics
2016Autonomous Robots
2016Transactions on Automation Science and Engineering (T-ASE)
2013Autonomous Robots: Special Issue `Beyond Grasping'
2014Journal of Machine Learning Research (JMLR)
Conferences and Workshops 
2017Program Committee, International Joint Conference on Artificial Intelligence (IJCAI) 2017
2017Associate Editor, International Conference on Intelligent Robots and Systems (IROS) 2017
2017Robotics: Science and Systems (RSS) 2017
2016International Conference on Humanoid Robots (Humanoids) 2016
2016International Symposium on Experimental Robotics (ISER) 2016
2016International Conference on Intelligent Robots and Systems (IROS) 2016
2016Robotics: Science and Systems (RSS) 2016
2016Program Committee, International Joint Conference on Artificial Intelligence (IJCAI) 2016
2015AAAI Conference on Artificial Intelligence (AAAI) 2016
2015Neural Information Processing Systems (NIPS) 2015
2015International Conference on Intelligent Robots and Systems (IROS) 2015
2015Robotics: Science and Systems (R:SS) 2015
2014International Conference on Robotics and Automation (ICRA) 2015
2014Neural Information Processing Systems (NIPS) 2014
2014International Conference on Intelligent Robots and Systems (IROS) 2014
2013NIPS 2013 Workshop on Advances in Machine Learing for Sensorimotor Control
2013International Conference on Robotics and Automation (ICRA) 2014
2013Neural Information Processing Systems (NIPS) 2013
2013Program Committee, International Joint Conference on Artificial Intelligence (IJCAI) 2013
2011International Conference on Robotics and Automation (ICRA) 2012
Invited talks
2016Center for Systems and Control, TU Delft
2016RLL & MRL labs, McGill University
2016CSAIL, Massachusetts Institute of Technology
2016Rijksuniversiteit Groningen, the Netherlands
2015Max Planck Institute for Intelligent Systems
2015Robot learning lab, UC Berkeley
2015RESL & CLMC labs, University of Southern California
2014Machine Learning and Robotics Lab, Universitaet Stuttgart
2014Department of Computing, Imperial College London
2013Robotics and Biology Group, TU Berlin
Supervision
Finished Theses
M.Sc.Jan Reubold (with Heni Ben Amor)Reubold, J. (2014). 3D Object Reconstruction from Partial Views, Master Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
B.Sc.Sebastian SchoengenSchoengen, S. (2013). Visual feature learning for interactive segmentation, Bachelor Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
B.Sc.Dominik NotzNotz, D. (2013). Reinforcement Learning for Planning in High-Dimensional Domains, Bachelor Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
B.Sc.Mike SmykSmyk, M. (2014). Learning Generalizable Models for Compliant Robots, Bachelor Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
B.Sc.Niko Huhnstock (with Filipe Veiga)Huhnstock, N. (2014). Tactile Sensing for Manipulation, Bachelor Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
B.Sc.Valerian MargMarg, V. (2016). Reinforcement Learning for a Dexterous Manipulation Task, Bachelor Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
Publications

van Hoof, H.; Tanneberg, D.; Peters, J. (accepted). Generalized Exploration in Policy Search, Machine Learning (MLJ).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Tangkaratt, V.; van Hoof, H.; Parisi, S.; Neumann, G.; Peters, J.; Sugiyama, M. (2017). Policy Search with High-Dimensional Context Variables, Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Neumann, G.; Peters, J. (2017). Non-parametric Policy Search with Limited Information Loss, Journal of Machine Learning Research (JMLR), 18, 73, pp.1-46.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Daniel, C.; van Hoof, H.; Peters, J.; Neumann, G. (2016). Probabilistic Inference for Determining Options in Reinforcement Learning, Machine Learning (MLJ), 104, 2-3, pp.337-357.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Chen, N.; Karl, M.; van der Smagt, P.; Peters, J. (2016). Stable Reinforcement Learning with Autoencoders for Tactile and Visual Data, Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Yi, Z.; Calandra, R.; Veiga, F.; van Hoof, H.; Hermans, T.; Zhang, Y.; Peters, J. (2016). Active Tactile Object Exploration with Gaussian Processes, Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H. (2016). Machine Learning through Exploration for Perception-Driven Robotics, PhD Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Peters, J.; Neumann, G. (2015). Learning of Non-Parametric Control Policies with High-Dimensional State Features, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Kroemer, O.; Daniel, C.; Neumann, G; van Hoof, H.; Peters, J. (2015). Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks, Proceedings of the International Conference on Robotics and Automation (ICRA).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Veiga, F.F.; van Hoof, H.; Peters, J.; Hermans, T. (2015). Stabilizing Novel Objects by Learning to Predict Tactile Slip, Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Hermans, T.; Neumann, G.; Peters, J. (2015). Learning Robot In-Hand Manipulation with Tactile Features, Proceedings of the International Conference on Humanoid Robots (HUMANOIDS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Bischoff, B.; Nguyen-Tuong, D.; van Hoof, H. McHutchon, A.; Rasmussen, C.E.; Knoll, A.; Peters, J.; Deisenroth, M.P. (2014). Policy Search For Learning Robot Control Using Sparse Data, Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Kroemer, O.; van Hoof, H.; Neumann, G.; Peters, J. (2014). Learning to Predict Phases of Manipulation Tasks as Hidden States, Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Kroemer, O; Peters, J. (2014). Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments, IEEE Transactions on Robotics (TRo), 30, 5, pp.1198-1209.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Hermans, T.; Veiga, F.; Hölscher, J.; van Hoof, H.; Peters, J. (2014). Demonstration: Learning for Tactile Manipulation, Advances in Neural Information Processing Systems (NIPS), Demonstration Track., MIT Press.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Kroemer, O; Peters, J. (2013). Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments , Proceedings of the International Conference on Humanoid Robots (HUMANOIDS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; Kroemer, O.;Ben Amor, H.; Peters, J. (2012). Maximally Informative Interaction Learning for Scene Exploration, Proceedings of the International Conference on Robot Systems (IROS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

van Hoof, H.; van der Zant, T. ; Wiering, M.A. (2011). Adaptive Visual Face Tracking for an Autonomous Robot, Proceedings of the Belgian-Dutch Artificial Intelligence Conference (BNAIC 11).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

  

zum Seitenanfang