Tucker Hermans

Quick Info

Research Interests

Learning for Robotic Manipulation, Robot Perception, Affordance Learning, Robot Tactile Sensing, Computer Vision

More Information

Curriculum Vitae Publications Google Citations DBLP

Contact Information

Mail. TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt

Tucker Hermans is an assistant professor in the School of Computing at the University of Utah. You can see his most up to date information at his Utah website.

Tucker was a postdoctoral researcher in the Intelligent Autonomous System (IAS) lab at TU Darmstadt working on tactile manipulation and robot learning from April 2014 to July 2015. He was the team leader at TU Darmstadt for the European Commission TACMAN project. Tucker joined the lab after receiving his PhD in robotics from Georgia Tech in Atlanta, Georgia, USA.

Tucker's research focuses on autonomous learning and perception in robots. His dissertation research dealt with robots learning to discover and manipulate previously unknown objects. The learning was performed on a Willow Garage PR2 robot, which performed pushing tasks through visual feedback control.

Prior to coming to TU Darmstadt Tucker was at Georgia Tech from 2009 to 2014. There he earned his PhD in Robotics under the supervision of Aaron Bobick and Jim Rehg in the Computational Perception Laboratory. At Georgia Tech Tucker also earned an MSc in Computer Science with specialization in Computational Perception and Robotics. Tucker earned his bachelors from Bowdoin College, where he double majored in Computer Science and German. At Bowdoin Tucker was a member and team captain of the Northern Bites SPL RoboCup team, who placed first in the world in 2007, placed third in 2008, and were runner-up in 2009. Tucker has additionally developed computer forensics software for the Maine State Police.

Workshop at RSS 2015

I'm co-organizing a workshop at RSS this summer on Visual and Tactile Learning for Interaction and Manipulation.

Moving to Utah

I'm excited to announce I'm starting as an assistant professor in the School of Computing at the University of Utah in August!

Research interests

  • Learning for robotic manipulation
  • Affordance learning
  • Real-world robot manipulation
  • Never-ending robot learning
  • Robot grasping and manipulation in clutter
  • Tactile sensing for robotics
  • Computer and robot vision

Key References

  1. Hermans, T.; Li, F.; Rehg, J. M.; Bobick, A. F. (2013). Learning Contact Locations for Pushing and Orienting Unknown Objects, International Conference on Humanoid Robots (HUMANOIDS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
  2. Hermans, T.; Rehg, J. M.; Bobick, A. F. (2012). Guided Pushing for Object Singulation, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
  3. Hermans, T.; Rehg, J. M.; Bobick, A. F. (2011). Affordance Prediction via Learned Object Attributes, IEEE International Conference on Robotics and Automation (ICRA): Workshop on Semantic Perception, Mapping, and Exploration.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]
  4. Hoelscher, J.; Peters, J.; Hermans, T. (2015). Evaluation of Interactive Object Recognition with Tactile Sensing, Proceedings of the International Conference on Humanoid Robots (HUMANOIDS).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

For a full list of Tucker's publications please see his Publication Page

Videos and Data

Details and data from my work on visual saliency from RGB-D data can be found here.

  1. Video for our IROS 2011 paper on push planning.
  2. Video for our IROS 2012 paper on singulation of cluttered scenes.
  3. Video for our ICRA 2013 paper on affordance representations and exploration.
  4. Video demonstrating our work on learning stable pushing locations. Associated with our ICDL 2013 and Humanoids 2013 papers.

Supervised Theses at IAS

2014Janine HoelscherB.Sc.Tactile Exploration of Object Propertiespdf


zum Seitenanfang