DocumentCode
2043129
Title
Comparison of neural network architectures for the modeling of robot inverse kinematics
Author
Driscoll, Joseph A.
Author_Institution
Dept. of Electr. Eng. & Comput. Sci., Vanderbilt Univ., Nashville, TN, USA
fYear
2000
fDate
2000
Firstpage
44
Lastpage
51
Abstract
Describes the use of neural networks to model the inverse kinematics of robot manipulators, including a redundant manipulator The use of multiple cooperating networks for the overall modeling of inverse kinematics was explored. A variety of network architectures was used, and their performance was compared. Neural networks were also used to train robots in specified obstacle-avoidance trajectories
Keywords
collision avoidance; learning (artificial intelligence); manipulator kinematics; neural net architecture; radial basis function networks; robot programming; cooperating networks; obstacle-avoidance trajectories; robot inverse kinematics; Closed-form solution; Computer architecture; Computer networks; Delay; Inverse problems; Iterative methods; Kinematics; Manipulators; Neural networks; Robot control;
fLanguage
English
Publisher
ieee
Conference_Titel
Southeastcon 2000. Proceedings of the IEEE
Conference_Location
Nashville, TN
Print_ISBN
0-7803-6312-4
Type
conf
DOI
10.1109/SECON.2000.845423
Filename
845423
Link To Document