            |
GRASP Special Seminar: Fall 2008
October 20th , 2:00 p.m., 307 Levine Hall (3330 Walnut Street)
Ashutosh Saxena
Stanford University
Joint work with Prof. Andrew Y. Ng
"Robotic Grasping and Depth Perception: Learning 3D Models from a Single Image"
Abstract: We present an algorithm to convert standard digital pictures into 3D models.
This is a challenging problem, since an image is formed by a projection of the 3D scene onto two dimensions, thus losing the depth information. We take a supervised learning approach to this problem, and use a Markov Random Field (MRF) to model the scene depth as a function of the image features. We show that, even on unstructured scenes of a large variety of environments, our algorithm is frequently able to recover fairly accurate 3D models. To convert your own image of an outdoor scene, landscape, etc. to a 3D model, please visit: http://make3d.stanford.edu
We also apply our methods to robotics applications: (a) obstacle avoidance for autonomously driving a small electric car, and (b) robot manipulation, where we develop vision-based learning algorithms for grasping novel objects. This enables our robot to perform tasks such as open new doors, clear up cluttered tables, and unload items from a dishwasher.
Biography: Ashutosh Saxena is a PhD Candidate in the Computer Science Department at Stanford University. He is in the Stanford AI Lab under his advisor Professor Andrew Y. Ng. Ashutosh received his B. Tech in Electrical Engineering at IIT Kapur in India and his MS in Electrical Engineering from Stanford University. His research interests include machine learning, robotics and computer vision.
GRASP
Laboratory
Site maintained by graspadm@grasp.cis.upenn.edu
Last update:9 October, 2008