Marcus Gualtieri. Robotic Pick-and-Place of Partially Visible and Novel Objects Ph.D. Thesis, 2021. (PDF)
Marcus Gualtieri and Robert Platt. Robotic Pick-and-Place With Uncertain Object Instance Segmentation and Shape Completion IEEE Robotics and Automation Letters, 2021. (PDF)(Video)(Code)(Supplementary Results)
Marcus Gualtieri and Robert Platt. Learning Manipulation Skills Via Hierarchical Spatial Attention IEEE Transactions on Robotics, 2020. (PDF)(Video)(Code)
Robert Platt, Colin Kohler, and Marcus Gualtieri. Deictic Image Mapping: An Abstraction For Learning Pose Invariant Manipulation Policies AAAI Conf. on Artificial Intelligence, 2019. (PDF)(Video)
Marcus Gualtieri and Robert Platt. Learning 6-DoF Grasping and Pick-Place Using Attention Focus Conf. on Robot Learning, 2018. (PDF)(Video)(Code)(Slides)
Marcus Gualtieri, Andreas ten Pas, and Robert Platt. Pick and Place Without Geometric Object Models IEEE Int'l Conf. on Robotics and Automation, 2018. (PDF)(Video)(Code)
Andreas ten Pas, Marcus Gualtieri, Kate Saenko, Robert Platt. Grasp Pose Detection in Point Clouds The Int'l Journal of Robotics Research, 2017. (PDF)(Video)
Marcus Gualtieri and Robert Platt. Viewpoint selection for grasp detection IEEE/RSJ Int'l Conf. on Intelligent Robots and Systems, 2017. (PDF)(Video)
Marcus Gualtieri, James Kuczynski, Abraham M. Shultz, Andreas ten Pas, Holly Yanco, Robert Platt. Open world assistive grasping using laser selection IEEE Int'l Conf. on Robotics and Automation, 2017. (PDF)(Video)
Marcus Gualtieri, Andreas ten Pas, Kate Saenko, and Robert Platt. High precision grasp pose detection in dense clutter IEEE/RSJ Int'l Conf. on Intelligent Robots and Systems, 2016. (PDF)(Video)
Code
PointCloudsPython. Simple PCL bindings for Python and other utilities for processing point clouds. (GitHub)
MentalMath. Educational tool for practicing mental addition, subtraction, and multiplication. (GitHub)
(2017 July) Received a paper award at the RSS 2017 workshop, New Frontiers for Deep Learning in Robotics! Thanks to the workshop organizers. The conference version of the awarded paper is Pick and Place without Geometric Object Models shown above.