GRASP Special Seminar: Dimitrios Kanoulas, Northeastern University, "From Noisy Point Clouds To Curved Contact Patches"

Presenter: Dimitrios Kanoulas (Homepage)

Event Dates:
  Monday June 10, 2013 from 11:00am to 12:00pm

* Alternate Location: Levine 512 (3330 Walnut Street)*

In this talk I describe perception algorithms that use curved patches to model contact surfaces in uneven environments like rocky trails. First I introduce a set of 10 patch models for contact areas both in the environment and on an articulated robot, and an algorithm for fitting these to point cloud data with estimated uncertainty both in the input points and the output patch. Then I describe an algorithm for sparsely covering nearby environment surfaces with patches appropriate for a robot to touch. The algorithm keeps only those patches which pass several validation checks to ensure fidelity to the sensed point cloud data. I also introduce a notion of saliency of a patch with respect to a locomotion task using local surface properties like normal vectors and curvatures. I present results on datasets of natural rocky terrain taken with a Kinect and compare point neighborhoods based on k-d trees vs. triangle meshes.

Presenter's Biography:

Dimitrios Kanoulas is a Ph.D. student at the College of Computer and Information Science at Northeastern University, working with Prof. Marsette Vona in the Geometric and Physical Computing Lab. His research focuses on 3D perception for robotics, in particular for uncertain natural environments. Prior to that he was member of the Algorithms and Theory group at Northeastern University working on algorithmic aspects of Game Theory.