News

  • Our paper, Towards Assistive Robotic Pick and Place in Open World Environments (PDF), was presented at ISRR 2019. Here's a video of our experiments.
  • Our grasp pose detection package is now available as a C++14 library. Check out this repository!

Address

College of Computer and Information Science
Northeastern University
805 Columbus Ave
ISEC, #560-574
Boston, MA 02120, USA

Short Biography

I'm currently a Ph.D. candidate in the Helping Hands Lab in the Khoury College of Computer Sciences at Northeastern University, advised by Professor Robert Platt.

My main interest is in the field of perception for robotics. In particular, I'm focussing on applying computer vision and machine learning methods to robotic grasping and manipulation problems.

I started my PhD in the Computer Science and Engineering Department at the University at Buffalo.

Research Interests

Present: Perception for robotic grasping and manipulation, deep learning, simulation based planning.

Past: Game theory, fairness in multi-agent systems.

Publications

Preprints

Dian Wang, Colin Kohler, Andreas ten Pas, Alexander Wilkinson, Maozhi Liu, Holly Yanco, Robert Platt.
Towards Assistive Robotic Pick and Place in Open World Environments.
Accepted at ISRR 2019.
(PDF) (Video) (Project page)


Journals

Andreas ten Pas, Marcus Gualtieri, Kate Saenko, Robert Platt.
Grasp Pose Detection in Point Clouds.
The International Journal of Robotics Research, October 2017.
(PDF) (UR5 Video) (Baxter Video) (Code)


Conferences

Yuchen Xiao, Sammie Katt, Andreas ten Pas, Shengjian Chen, Christopher Amato.
Online Planning for Target Object Search in Clutter under Partial Observability.
IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, May 2019.
(PDF) (Video)


Marcus Gualtieri, Andreas ten Pas, Robert Platt.
Pick and Place Without Geometric Object Models.
IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 2018.
(PDF) (Video)


Ulrich Viereck, Andreas ten Pas, Kate Saenko, Robert Platt.
Learning a visuomotor controller for real world robotic grasping using simulated depth images.
Conference on Robot Learning (CoRL), USA, November 2017.
(PDF) (Video)


Marcus Gualtieri, James Kuczynski, Abraham M. Shultz, Andreas ten Pas, Robert Platt, Holly Yanco.
Open World Assistive Grasping Using Laser Selection.
IEEE International Conference on Robotics and Automation (ICRA), Singapore, June 2017.
(PDF) (Video)


Marcus Gualtieri, Andreas ten Pas, Kate Saenko, and Robert Platt.
High precision grasp pose detection in dense clutter.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), South Korea, October 2016.
(PDF) (UR5 Video) (Baxter Video) (Code)


Andreas ten Pas and Robert Platt.
Using Geometry to Detect Grasp Poses in 3D Point Clouds.
International Symposium on Robotics Research (ISRR), Italy, September 2015.
(PDF) (Video) (ROS Package)


Giulia Franchi, Andreas ten Pas, Robert Platt and Stefano Panzieri.
The Baxter Easyhand: A Robot Hand That Costs $150 US in Parts.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Germany, September 2015.
(PDF)

Andreas ten Pas and Robert Platt.
Localizing Handle-Like Grasp Affordances in 3D Point Clouds.
International Symposium on Experimental Robotics (ISER), Morocco, June 2014.
(PDF) (Baxter Video) (Robonaut Video) (ROS Package)

Rui Li, Robert Platt, Wenzhen Yuan, Andreas ten Pas, Nathan Roscup, Edward Adelson.
Localization and Manipulation of Small Parts Using GelSight Tactile Sensing.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), USA, September 2014.
(PDF)

Workshops

  1. Andreas ten Pas, Kate Saenko, and Robert Platt. Combining Grasp Pose Detection with Object Detection.
    R:SS 2016 workshop on Bootstrapping Manipulation Skills (poster). June 2016. University of Michigan in Ann Arbor, Michigan, USA.
    (PDF)

  2. Marcus Gualtieri, James Kuczynski, Abraham M. Shultz, Andreas ten Pas, Holly Yanco, and Robert Platt.
    Open World Assistive Grasping Using Laser Selection.
    Northeast Robotics Colloquium, Fifth Edition (poster). October 2016. Cornell University. Ithaca, New York, USA.
    (PDF)

  3. Andreas ten Pas and Robert Platt. Localizing Grasp Affordances in 3-D Point Clouds Using Machine Learning.
    Northeast Robotics Colloquium, Third Edition (poster). October 2014. Brown University. Providence, Rhode Island, USA.
    (PDF)

  4. Andreas ten Pas and Robert Platt. Localizing Grasp Affordances in 3-D Points Clouds Using Taubin Quadric Fitting.
    Northeast Robotics Colloquium, Second Edition (poster). October 2013. Harvard University. Cambridge, Massachusetts, USA.
    (PDF)

Theses

  1. Simulation Based Planning for POMDPs with Continuous Observation Spaces.
    M.Sc. Thesis. August 2012. Department of Knowledge Engineering, Maastricht University. Maastricht, The Netherlands.
    Third place in the Master Artificial Intelligence category for best faculty thesis.
    (PDF)

  2. Metastrategies in the Colored Trails Game.
    B.Sc. Thesis. August 2010. Department of Knowledge Engineering, Maastricht University. Maastricht, The Netherlands.
    (PDF)

Education

Professional Experience

Videos

Gesture Recognition

with Nathaniel Mahowald, Ali Elgabri, and Dimitrios Kanoulas

Software

All of my software is available on github.
  1. ROS package to detect grasp poses in 3D point clouds using CNNs.
  2. ROS package to localize antipodal 2-finger grasps in 3D point clouds using SVMs (instructions).
  3. ROS package to localize enveloping grasps in 3D point clouds (instructions).