University of Illinois Urbana-Champaign

Reaching Algorithm Implemented Using Gradient Descent

Law, Allan

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/46496

Description

Title
Reaching Algorithm Implemented Using Gradient Descent
Author(s)
Law, Allan
Contributor(s)
Levinson, Stephen
Issue Date
2012-05
Keyword(s)
  • robotics
  • artificial intelligence
  • humanoid robots
  • robot vision
  • robotic control
  • gradient descent algorithms
Abstract
The aim of this thesis is to provide a simple visual closed loop control method to enable a humanoid robot to reach out towards an object in its visual field in 3D space. To achieve this task, the robot utilizes stereo vision to estimate the relative depths of its end-effector and the desired gripping location of the object. Gradient descent will be applied to the output obtained from the stereo vision to enable the robot to correctly position its end-effector at a desired position. By utilizing this gradient decent method, we will be able control the robot’s end-effectors without the need to map the robot’s end-effectors in world coordinates to the spatial locations found using stereo vision.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/46496

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research