Objects Centroid Correlation Using MATLAB's Neural Network Toolbox for Visually-Guided Object Manipulation

2014 ◽  
Vol 931-932 ◽  
pp. 1417-1421
Author(s):  
Sujin Wanchat ◽  
Supattra Plermkamon ◽  
Danaipong Chetchotsak
Keyword(s):  
Neural Network ◽  
Least Squares ◽  
Feedforward Neural Network ◽  
Automatic Process ◽  
Visually Guided ◽  
Linear Least Squares ◽  
Pick And Place ◽  
Place Task ◽  
Neural Network Toolbox ◽  
Practicable Method

Since a pick-and-place task plays an important role in an automatic process, it normally requires machine vision to locate an object for grasping. This paper presents a practicable method used to visually guide an object grasping a group of small, 1.1 mm diameter, screws by using an inexpensive webcam with a resolution of 640 x 480. A basic feedforward neural network is utilized to make a fitting function which associates pixel coordinates of the camera to the physical coordinates of the robot while the method of linear least squares is used for comparison in parallel. The result from the feedforward neural network shows that fifty screws can be completely manipulated from a tray after their physical coordinates are loaded into the robot while the result from the method of linear least squares shows failure when picking two of the samples.

Near-Minimum Time Visual Servoing of an Underactuated Robotic Manipulator

2013 ◽  
Vol 373-375 ◽  
pp. 217-220
Author(s):  
Yacine Benbelkacem ◽  
Rosmiwati Mohd-Mokhtar
Keyword(s):  
Rate Of Convergence ◽  
Visual Information ◽  
Visual Servoing ◽  
Open Loop ◽  
Minimum Time ◽  
Robotic Arm ◽  
Speed Of Convergence ◽  
Visually Guided ◽  
Pick And Place ◽  
Place Task

Rate of convergence to the desired pose to grasp an object using visual information may be important in some applications, such as a pick and place routine in assembly where the time between two stops of the conveyor is very short. The visually guided robot is required to move fast if vision is to bring the sought benefits to industrial setups. In this paper, the three most famous techniques to visual servoing, mainly the image-based, position-based and hybrid visual servoing are evaluated in terms of their speed of convergence to the grasping pose in a pick and place task of a momentarily motionless target. An alternative open-loop near-minimum time approach is also presented and tested on a 5DOF under-actuated robotic arm. The performance is compared and result shows significant reduction for its time of convergence, to the aforementioned techniques.

Operational Determination of the Activated Sludge Process Using Neural Networks

1992 ◽  
Vol 26 (9-11) ◽  
pp. 2461-2464 ◽  
Author(s):  
R. D. Tyagi ◽  
Y. G. Du
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Activated Sludge ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Activated Sludge Process

A steady-statemathematical model of an activated sludgeprocess with a secondary settler was developed. With a limited number of training data samples obtained from the simulation at steady state, a feedforward neural network was established which exhibits an excellent capability for the operational prediction and determination.

Sign in / Sign up

Export Citation Format

Share Document