DocumentCode :
2197854
Title :
Modular neural-visual servoing using a neural-fuzzy decision network
Author :
Wu, Q. M Jonathan ; Stanley, Kevin
Author_Institution :
Inst. for Sensor & Control Technol., Nat. Res. Council of Canada, BC, Canada
Volume :
4
fYear :
1997
fDate :
20-25 Apr 1997
Firstpage :
3238
Abstract :
Visual servoing is a growing research area. One of the key problems of feature based visual servoing is calculating the inverse Jacobian, relating change in features to change in robot position. Neural networks can learn to approximate the inverse feature Jacobian. However, the neural network approach can only approximate the feature Jacobian for a small workspace. In order to overcome this problem, we propose using a modular approach, where several networks are trained over a small area. Furthermore, we use a neural-fuzzy counterpropagation network to decide which subspace the robot is currently occupying. The neural fuzzy network provides smoother transitions between subspaces than hard switching. Preliminary results of the system´s operation are also presented
Keywords :
Jacobian matrices; backpropagation; fuzzy neural nets; manipulators; robot vision; servomechanisms; feature-based visual servoing; inverse Jacobian; inverse feature Jacobian; modular neural-visual servoing; neural networks; neural-fuzzy counterpropagation network; neural-fuzzy decision network; robot position change; Backpropagation algorithms; Control systems; Councils; Difference equations; Indexing; Jacobian matrices; Sensor phenomena and characterization; Sensor systems; Visual servoing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-7803-3612-7
Type :
conf
DOI :
10.1109/ROBOT.1997.606782
Filename :
606782
Link To Document :
بازگشت