國立高雄大學圖資館 |

Language: English

Back

Monocular depth perception and robot...

Saxena, Ashutosh.

Monocular depth perception and robotic grasping of novel objects.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Monocular depth perception and robotic grasping of novel objects.
Author:	Saxena, Ashutosh.
Description:	195 p.
Notes:	Source: Dissertation Abstracts International, Volume: 70-10, Section: B, page: .
Notes:	Adviser: Andrew Y. Ng.
Contained By:	Dissertation Abstracts International70-10B.
Subject:	Engineering, Electronics and Electrical.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3382821
ISBN:	9781109447392

Monocular depth perception and robotic grasping of novel objects.
Saxena, Ashutosh.

Monocular depth perception and robotic grasping of novel objects. - 195 p.

Source: Dissertation Abstracts International, Volume: 70-10, Section: B, page: .

Thesis (Ph.D.)--Stanford University, 2009.

The ability to perceive the 3D shape of the environment is a basic ability for a robot. We present an algorithm to convert standard digital pictures into 3D models.

ISBN: 9781109447392Subjects--Topical Terms:

226981
Engineering, Electronics and Electrical.

Monocular depth perception and robotic grasping of novel objects.
LDR:01856nmm 2200301 4500 001 240306
005 20100310090844.5
008 100410s2009 ||||||||||||||||| ||eng d
020 $a 9781109447392
035 $a (UMI)AAI3382821
035 $a AAI3382821
040 $a UMI $c UMI
100 1 $a Saxena, Ashutosh. $3 384341
245 1 0 $a Monocular depth perception and robotic grasping of novel objects.
300 $a 195 p.
500 $a Source: Dissertation Abstracts International, Volume: 70-10, Section: B, page: .
500 $a Adviser: Andrew Y. Ng.
502 $a Thesis (Ph.D.)--Stanford University, 2009.
520 $a The ability to perceive the 3D shape of the environment is a basic ability for a robot. We present an algorithm to convert standard digital pictures into 3D models.
520 $a 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 accurate 3D models.
520 $a We then 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.
590 $a School code: 0212.
650 4 $a Engineering, Electronics and Electrical. $3 226981
650 4 $a Computer Science. $3 212513
690 $a 0544
690 $a 0984
710 2 $a Stanford University. $3 212607
773 0 $t Dissertation Abstracts International $g 70-10B.
790 1 0 $a Ng, Andrew Y., $e advisor
790 $a 0212
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3382821