Jeroen van Baar

- Phone: 617-621-7523
- Email:
-
Position:
Research / Technical Staff
Senior Principal Research Scientist, Team Leader -
Education:
Ph.D., ETH Zurich, 2013 -
Research Areas:
External Links:
Jeroen's Quick Links
-
Biography
Jeroen came to MERL in 1997 as intern, and was subsequently hired as research associate. He temporarily left MERL to pursue a Ph.D. and returned early 2013. At MERL he has made contributions in the areas of computer graphics, computer vision and computational photography. His interests include 3D reconstruction, medical imaging, GP-GPU for computational photography and computer vision.
-
Recent News & Events
-
EVENT MERL Virtual Open House 2020 Date & Time: Wednesday, December 9, 2020; 1:00-5:00PM EST
MERL Contacts: Elizabeth Phillips; Jeroen van Baar; Anthony Vetro
Location: Virtual
Research Areas: Applied Physics, Artificial Intelligence, Communications, Computational Sensing, Computer Vision, Control, Data Analytics, Dynamical Systems, Electric Systems, Electronic and Photonic Devices, Machine Learning, Multi-Physical Modeling, Optimization, Robotics, Signal Processing, Speech & AudioBrief- MERL will host a virtual open house on December 9, 2020. Live sessions will be held from 1-5pm EST, including an overview of recent activities by our research groups and a talk by Prof. Pierre Moulin of University of Illinois at Urbana-Champaign on adversarial machine learning. Registered attendees will also be able to browse our virtual booths at their convenience and connect with our research staff on engagement opportunities including internship, post-doc and research scientist openings, as well as visiting faculty positions.
Registration: https://mailchi.mp/merl/merl-virtual-open-house-2020
Schedule: https://www.merl.com/events/voh20
Current internship and employment openings:
https://www.merl.com/internship/openings
https://www.merl.com/employment/employment
Information about working at MERL:
https://www.merl.com/employment
- MERL will host a virtual open house on December 9, 2020. Live sessions will be held from 1-5pm EST, including an overview of recent activities by our research groups and a talk by Prof. Pierre Moulin of University of Illinois at Urbana-Champaign on adversarial machine learning. Registered attendees will also be able to browse our virtual booths at their convenience and connect with our research staff on engagement opportunities including internship, post-doc and research scientist openings, as well as visiting faculty positions.
-
NEWS New robotics benchmark system Date: November 16, 2020
MERL Contacts: Devesh Jha; Daniel Nikovski; Diego Romeres; Alan Sullivan; Jeroen van Baar
Research Areas: Artificial Intelligence, Machine Learning, RoboticsBrief- MERL researchers, in collaboration with researchers from MELCO and the Department of Brain and Cognitive Science at MIT, have released simulation software Circular Maze Environment (CME). This system could be used as a new benchmark for evaluating different control and robot learning algorithms. The control objective in this system is to tip and the tilt the maze so as to drive one (or multiple) marble(s) to the innermost ring of the circular maze. Although the system is very intuitive for humans to control, it is very challenging for artificial intelligence agents to learn efficiently. It poses several challenges for both model-based as well as model-free methods, due to its non-smooth dynamics, long planning horizon, and non-linear dynamics. The released Python package provides the simulation environment for the circular maze, where movement of multiple marbles could be simulated simultaneously. The package also provides a trajectory optimization algorithm to design a model-based controller in simulation.
See All News & Events for Jeroen -
-
Research Highlights
-
Internships with Jeroen
-
CV1546: Vibration analysis in video sequences
MERL is looking for a self-motivated intern to work on vibration analysis in video sequences. The ideal candidate would be a Ph.D. student with a strong background in machine learning, optimization and computer vision. Experience in computational photography and MATLAB/Python is a plus. You are expected to collaborate with MERL researchers to develop algorithms and prepare manuscripts for scientific publications. The internship is for a minimum of 3 months and the start date is flexible. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.
-
CV1569: Robot learning from videos of human demonstrations
MERL is looking for a highly motivated and qualified intern to work on developing algorithms for robot learning from videos of human demonstrations. The ideal candidate would be a current Ph.D. student with a strong background in computer vision, deep learning, and robotics. Familiarity with imitation learning, learning from demonstrations (LfD), reinforcement learning, and machine learning for robotics will be valued. Proficiency in Python programming is necessary and experience in working with a physics engine simulator like Mujoco or pyBullet is a plus. A successful candidate will collaborate with MERL researchers and publication of the relevant results is expected. Start date is flexible and the expected duration of the internship is 3-4 months. Interested candidates are encouraged to apply with their recent CV and list of publications in related topics. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.
-
-
MERL Publications
- "Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty", Advances in Neural Information Processing Systems (NeurIPS)-workshop, January 2021.BibTeX TR2021-009 PDF
- @inproceedings{Russel2021jan,
- author = {Russel, Reazul Hasan and Benosman, Mouhacine and van Baar, Jeroen},
- title = {Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty},
- booktitle = {Advances in Neural Information Processing Systems (NeurIPS)-workshop},
- year = 2021,
- month = jan,
- url = {https://www.merl.com/publications/TR2021-009}
- }
, - "Towards Human-Level Learning of Complex Physical Puzzles", arXiv, December 2020.BibTeX
- @article{Ota2020dec,
- author = {Ota, Kei and Jha, Devesh and Romeres, Diego and van Baar, Jeroen and Smith, Kevin and Semistsu, Takayuki and Oiki, Tomoaki and Sullivan, Alan and Nikovski, Daniel N. and Tenanbaum, Joshua},
- title = {Towards Human-Level Learning of Complex Physical Puzzles},
- journal = {arXiv},
- year = 2020,
- month = dec
- }
, - "Interactive Tactile Perception for Classification of Novel Object Instances", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), DOI: 10.1109/IROS45743.2020.9341795, November 2020, pp. 9861-9868.BibTeX TR2020-143 PDF
- @inproceedings{Corcodel2020nov,
- author = {Corcodel, Radu and Jain, Siddarth and van Baar, Jeroen},
- title = {Interactive Tactile Perception for Classification of Novel Object Instances},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2020,
- pages = {9861--9868},
- month = nov,
- publisher = {IEEE},
- doi = {10.1109/IROS45743.2020.9341795},
- url = {https://www.merl.com/publications/TR2020-143}
- }
, - "DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies", IEEE Pacific Visualization Symposium (PacificVis), DOI: 10.1109/PacificVis48177.2020.7127, January 2020, pp. 36-45.BibTeX TR2020-011 PDF
- @inproceedings{He2020jan,
- author = {He, Wenbin and Lee, Teng-Yok and van Baar, Jeroen and Wittenburg, Kent B. and Shen, Han-Wei},
- title = {DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies},
- booktitle = {IEEE Pacific Visualization Symposium (PacificVis)},
- year = 2020,
- pages = {36--45},
- month = jan,
- doi = {10.1109/PacificVis48177.2020.7127},
- url = {https://www.merl.com/publications/TR2020-011}
- }
, - "Learning from Trajectories via Subgoal Discovery", Advances in Neural Information Processing Systems (NeurIPS), pp. 8409-8419, October 2019.BibTeX TR2019-128 PDF
- @article{Paul2019oct,
- author = {Paul, Sujoy and van Baar, Jeroen and Roy-Chowdhury, Amit K.},
- title = {Learning from Trajectories via Subgoal Discovery},
- journal = {Advances in Neural Information Processing Systems (NeurIPS)},
- year = 2019,
- pages = {8409--8419},
- month = oct,
- url = {https://www.merl.com/publications/TR2019-128}
- }
,
- "Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty", Advances in Neural Information Processing Systems (NeurIPS)-workshop, January 2021.
-
Software Downloads
-
Videos
-
MERL Issued Patents
-
Title: "System and Method for Multimodal, Motion-Aware Radar Imaging"
Inventors: Boufounos, Petros T.; Mansour, Hassan; Srinivasa, Rakshith Sharma; Van Baar, Jeroen
Patent No.: 10,768,294
Issue Date: Sep 8, 2020 -
Title: "Method for Registering Deformable Images Using Random Markov Fields"
Inventors: Van Baar, Jeroen; Seo, Dohyung
Patent No.: 9,449,384
Issue Date: Sep 20, 2016 -
Title: "Method for Deformable Image Registration"
Inventors: Van Baar, Jeroen; Seo, Dohyung
Patent No.: 9,449,246
Issue Date: Sep 20, 2016 -
Title: "Image Denoising Using a Library of Functions"
Inventors: Tuzel, Oncel; Thornton, Jay E.; Van Baar, Jeroen
Patent No.: 9,262,810
Issue Date: Feb 16, 2016 -
Title: "Motion-Based Text Input"
Inventors: Van Baar, Jeroen; Beardsley, Paul A.
Patent No.: 7,355,583
Issue Date: Apr 8, 2008 -
Title: "System and Method for Mechanically Adjusting Projector Posewith Six Degrees of Freedom for Image Alignment"
Inventors: Raskar, Ramesh N.; Van Baar, Jeroen
Patent No.: 7,252,387
Issue Date: Aug 7, 2007 -
Title: "Interactive Wireless Tag Location and Identification System"
Inventors: Beardsley, Paul A.; Dietz, Paul H.; Van Baar, Jeroen; Raskar, Ramesh N.
Patent No.: 7,154,395
Issue Date: Dec 26, 2006 -
Title: "Projector-Camera System with Laser Pointers"
Inventors: Van Baar, Jeroen; Beardsley, Paul A.; Raskar, Ramesh N.
Patent No.: 7,137,707
Issue Date: Nov 21, 2006 -
Title: "Self-Configurable Ad-Hoc Projector Cluster"
Inventors: Beardsley, Paul A.; Van Baar, Jeroen; Raskar, Ramesh N.
Patent No.: 6,834,965
Issue Date: Dec 28, 2004 -
Title: "Geometrically Aware Projector"
Inventors: Van Baar, Jeroen; Raskar, Ramesh N.; Beardsley, Paul A.
Patent No.: 6,811,264
Issue Date: Nov 2, 2004 -
Title: "Projecting Warped Images onto Curved Surfaces"
Inventors: Raskar, Ramesh N.; Van Baar, Jeroen; Willwacher, Thomas; Rao, Srinivasa
Patent No.: 6,793,350
Issue Date: Sep 21, 2004 -
Title: "Method for Globally Aligning Multiple Projected Images"
Inventors: Raskar, Ramesh N.; Van Baar, Jeroen; Beardsley, Paul A.
Patent No.: 6,755,537
Issue Date: Jun 29, 2004 -
Title: "Rendering Discrete Sample Points Projected to a Screen Space with a Continuous Resampling Filter"
Inventors: Van Baar, Jeroen; Zwicker, Matthias B.; Gross, Markus H.; Pfister, Hans Peter
Patent No.: 6,744,435
Issue Date: Jun 1, 2004 -
Title: "Method for Determining a Largest Inscribed Rectangular Image within a Union of Projected QuadrilateralImages"
Inventors: Raskar, Ramesh N.; Van Baar, Jeroen; Willwacher, Thomas
Patent No.: 6,729,733
Issue Date: May 4, 2004 -
Title: "Method and System for Displaying Images on Curved Surfaces"
Inventors: Raskar, Ramesh N.; Van Baar, Jeroen; Willwacher, Thomas
Patent No.: 6,715,888
Issue Date: Apr 6, 2004 -
Title: "Rendering Pipeline for Surface Elements"
Inventors: Gross, Markus H.; Pfister, Hans Peter; Van Baar, Jeroen; Zwicker, Matthias B.
Patent No.: 6,583,787
Issue Date: Jun 24, 2003 -
Title: "A Method for Generating Graphical Objects Represented as Surface Elements"
Inventors: Van Baar, Jeroen; Pfister, Hans Peter; Oosterbaan, Collin E.
Patent No.: 6,498,607
Issue Date: Dec 24, 2002 -
Title: "Graphical Objects Represented as Surface Elements"
Inventors: Pfister, Hans Peter; Van Baar, Jeroen; Oosterbaan, Collin E.
Patent No.: 6,480,190
Issue Date: Nov 12, 2002 -
Title: "Method for Rendering Graphical Objects Represented as Surface Elements"
Inventors: Van Baar, Jeroen; Pfister, Hans Peter; Oosterbaan, Collin E.
Patent No.: 6,448,968
Issue Date: Sep 10, 2002 -
Title: "A Method for Modeling Graphical Objects Represented as Surface Elements"
Inventors: Oosterbaan, Collin E.; Van Baar, Jeroen; Pfister, Hans Peter
Patent No.: 6,396,496
Issue Date: May 28, 2002 -
Title: "Method for Interactively Modeling Graphical Objects with Linked and Unlinked Surface Elements"
Inventors: Pfister, Hans Peter; Oosterbaan, Collin E.; Van Baar, Jeroen
Patent No.: 6,342,886
Issue Date: Jan 29, 2002
-
Title: "System and Method for Multimodal, Motion-Aware Radar Imaging"