Cinque Terre

Chaitanya Mitash

Ph.D Candidate, Computer Science
Rutgers University


I am a Ph.D Candidate in the Computer Science department at Rutgers, co-advised by professors Abdeslam Boularias and Kostas Bekris . My research interests lie in the field of Robotics, Computer Vision and Machine Learning. Specifically, I am working on problems related to perception for Robotic Manipulation.


Links to my GitHub, LinkedIn, Google Scholar profiles and my CV:


News

New Our paper Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects has been accepted to appear at the Conference on Robot Learning (CoRL) - 2019.
New I will be spending my summer at Amazon Robotics in North Reading, MA working on challenges related to task-driven perception for robotic manipulation.
New Selected to be a part of the RSS Pioneers workshop at the Robotics: Science and Systems conference in Freiburg, Germany.
New Our paper Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter has been accepted to appear in the International Journal of Robotics Research (IJRR) 2019. It will be a part of the Special Issue on Robot Vision.
► Our work on robotic bin picking and packing Towards Robust Product Packing with a Minimalistic End-Effector has been accepted to appear at the IEEE International Conference on Robotics and Automation (ICRA) 2019. It has been nominated as a Finalist for Best Paper Award in Automation
► Our work in collaboration with Laval University Learning Object Localization and 6D Pose Estimation from Simulation and Weakly Labeled Real Images has been accepted to appear at the IEEE International Conference on Robotics and Automation (ICRA) 2019.
► Our paper Robust 6D Object Pose Estimation with Stochastic Congruent Sets has been accepted at the British Machine Vision Conference (BMVC) 2018. The code is available now.
► I will be working as a Research Intern with the HoloLens team at Microsoft, Redmond, WA, USA from June 4 to August 31, 2018.
► Our paper Improving 6D Pose Estimation of Objects in Clutter via Physics-aware Monte Carlo Tree Search has been accepted to appear at IEEE International Conference on Robotics and Automation (ICRA) 2018.
► Starting Research collaboration with JD.COM (January, 2018).
► I will be presenting a poster at the Northeast Robotics Colloquium (NERC) to be held at Northeeastern University on October 21, 2017.
► Our paper A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation has been accepted to appear at International Conference on Intelligent Robots and Systems (IROS) 2017.
► Started as a PhD student at Rutgers University, NJ, USA (September, 2015).
► Working at Samsung Research, Suwon, South Korea (February - April, 2015).
► Started working as Senior Software Engineer at Samsung R&D India, Bangalore (April, 2014).
► Started working as an R&D Engineer at Tejas Networks, Bangalore (August, 2012).
► Completed B.E. in Computer Science from Birla Institute of Technology, Mesra (May, 2012).


Publications

[Conference] Chaitanya Mitash, Bowen Wen, Kostas Bekris, and Abdeslam Boularias, "Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects", In Proceedings of the Conference on Robot Learning (CoRL), Osaka, Japan, 2019 [ArXiV] [Poster] [Slides] [Video]

[Conference] Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Robust 6D Object Pose Estimation with Stochastic Congruent Sets", In Proceedings of the British Machine Vision Conference (BMVC), Newcastle, England, UK, 2018 [ArXiV] [Video] [PDF] [Poster]

[Journal] Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter", at the International Journal of Robotics Research (IJRR) 2019[ArXiV]

[Conference] Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Improving 6D Pose Estimation of Objects in Clutter via Physics-aware Monte Carlo Tree Search", In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 2018 [ArXiV] [Webpage] [IEEE] [Video] [Poster]

[Conference] Chaitanya Mitash, Kostas Bekris and Abdeslam Boularias, "A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation", In Proceedings of IEEE International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017 [ArXiV] [Webpage] [IEEE] [Video]

[Conference] Rahul Shome, Wei N. Tang, Changkyu Song, Chaitanya Mitash, Chris Kourtev, Jingjin Yu, Abdeslam Boularias, and Kostas E. Bekris, "Towards Robust Product Packing with a Minimalistic End-Effector", In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019 [ArXiV] [Webpage]

[Conference] Jean-Philippe Mercier, Chaitanya Mitash, Philippe Giguere and Abdeslam Boularias, "Learning Object Localization and 6D Pose Estimation from Simulation and Weakly Labeled Real Images", In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019 [ArXiV]


Workshops and talks

► Chaitanya Mitash, Bowen Wen, Kostas Bekris, and Abdeslam Boularias, "Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects", RSS Pioneers Workshop, Robotics: Science and Systems (RSS), Freiburg, Germany, 2019 [Abstract]
► Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Robust 6D Object Pose Estimation with Stochastic Congruent Sets", 4th International Workshop on Recovering 6D Object Pose, European Conference on Computer Vision (ECCV), Munich, Germany, 2018 [Poster]
► Rahul Shome, Wei Tang, Chaitanya Mitash, Abdeslam Boularias, Jingjin Yu, Kostas Bekris, "An Efficient Pipeline for Pick-and-Place Between Bins for Warehouse Automation", Robotics for logistics in warehouses and environments shared with humans, IEEE International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 2018 [Abstract]
► Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Physics-aware Simulation and a Self-Supervised Learning System for Object Detection and Pose Estimation", Workshop on Warehouse Picking Automation, IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017 [Abstract] [PPT]
► Chaitanya Mitash, Abdeslam Boularias and Kostas Bekris, "Object Detection and Pose Estimation for Robotic Manipulation using Physics Simulation and Monte Carlo Tree Search", Northeast Robotics Colloquium (NERC), Boston, 2017 [Poster]