Simulation of Visual Servoing in Grasping Objects Moving by Newtonian Dynamics
(2002) In MSc ThesesDepartment of Automatic Control
- Abstract
- Robot control systems and other manufacturing equipment are traditionally closed systems. This circumstance has hampered system integration of manipulators, sensors as well as other equipment, and such system integration has often been made at an unsuitably high hierarchical level. With the aid of vision, visual feedback is used to guide the robot manipulator to the target. This hand-to-target task is fairly easy if the target is static in Cartesian space. However, if the target is dynamic in motion, a model of the dynamics behaviour is required in order for the robot to track and intercept the target. The purpose of this project is to simulate in a virtual environment to show how to organise robot control systems with sensor integration.... (More)
- Robot control systems and other manufacturing equipment are traditionally closed systems. This circumstance has hampered system integration of manipulators, sensors as well as other equipment, and such system integration has often been made at an unsuitably high hierarchical level. With the aid of vision, visual feedback is used to guide the robot manipulator to the target. This hand-to-target task is fairly easy if the target is static in Cartesian space. However, if the target is dynamic in motion, a model of the dynamics behaviour is required in order for the robot to track and intercept the target. The purpose of this project is to simulate in a virtual environment to show how to organise robot control systems with sensor integration. This project is a simulation that involves catching a thrown virtual ball using a six degree-of-freedom virtual robot and two virtual digital cameras. Tasks to be executed in this project include placement of virtual digital cameras, segmentation and tracking of the moving virtual ball as well as model-based prediction of the virtual ball's trajectory. <p> Consideration have to be given to the placement of the virtual digital cameras so that the whole trajectory of the ball can be captured by both the virtual digital cameras simultaneously. In order to track the trajectory of the virtual ball, the image of the ball captured by the digital cameras has to be segmented from its background. Then a model is to be developed to predict the trajectory of the virtual ball so that the virtual robot can be controlled to align itself to grasp the moving virtual ball. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8848191
- author
- Wong, Jee Hui
- supervisor
- organization
- year
- 2002
- type
- H3 - Professional qualifications (4 Years - )
- subject
- publication/series
- MSc Theses
- report number
- TFRT-5694
- ISSN
- 0280-5316
- language
- English
- id
- 8848191
- date added to LUP
- 2016-03-19 17:48:46
- date last changed
- 2016-03-19 17:48:46
@misc{8848191,
abstract = {{Robot control systems and other manufacturing equipment are traditionally closed systems. This circumstance has hampered system integration of manipulators, sensors as well as other equipment, and such system integration has often been made at an unsuitably high hierarchical level. With the aid of vision, visual feedback is used to guide the robot manipulator to the target. This hand-to-target task is fairly easy if the target is static in Cartesian space. However, if the target is dynamic in motion, a model of the dynamics behaviour is required in order for the robot to track and intercept the target. The purpose of this project is to simulate in a virtual environment to show how to organise robot control systems with sensor integration. This project is a simulation that involves catching a thrown virtual ball using a six degree-of-freedom virtual robot and two virtual digital cameras. Tasks to be executed in this project include placement of virtual digital cameras, segmentation and tracking of the moving virtual ball as well as model-based prediction of the virtual ball's trajectory. <p> Consideration have to be given to the placement of the virtual digital cameras so that the whole trajectory of the ball can be captured by both the virtual digital cameras simultaneously. In order to track the trajectory of the virtual ball, the image of the ball captured by the digital cameras has to be segmented from its background. Then a model is to be developed to predict the trajectory of the virtual ball so that the virtual robot can be controlled to align itself to grasp the moving virtual ball.}},
author = {{Wong, Jee Hui}},
issn = {{0280-5316}},
language = {{eng}},
note = {{Student Paper}},
series = {{MSc Theses}},
title = {{Simulation of Visual Servoing in Grasping Objects Moving by Newtonian Dynamics}},
year = {{2002}},
}