DocumentCode :
2786536
Title :
Neuromorphic control for robotic manipulators-position, force and impact control
Author :
Fukuda, Toshio ; Shibata, Takanori
Author_Institution :
Nagoya Univ., Japan
fYear :
1990
fDate :
5-7 Sep 1990
Firstpage :
310
Abstract :
Neural network applications for robotic motion control are considered. The `neural servocontroller´ is based on a neural network which has integrated time-delay elements so that it can learn the nonlinear dynamical system The controller is applicable to position and force control of robotic manipulators. Because they have strong nonlinearity and are high-speed phenomena, it is difficult to sense collisions and to control robotic manipulators suffering collisions. Therefore, the neural servocontroller is effective against collision phenomena. A Herz-type model with an energy loss parameter was adopted to express the impact force between the manipulator and unknown objects. Simulation results show that the proposed neural servocontroller can sense collision phenomena and control robotic manipulators suffering collision
Keywords :
collision processes; force control; impact (mechanical); learning systems; neural nets; nonlinear systems; position control; robots; servomechanisms; Herz-type model; collision phenomena; energy loss parameter; force control; high-speed phenomena; impact control; integrated time-delay elements; learning system; neural network; neural servocontroller; neuromorphic control; nonlinear dynamical system; position control; robotic manipulators; robotic motion control; simulation; Force control; Manipulator dynamics; Motion control; Neural networks; Neuromorphics; Nonlinear control systems; Nonlinear dynamical systems; Robot control; Robot motion; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on
Conference_Location :
Philadelphia, PA
ISSN :
2158-9860
Print_ISBN :
0-8186-2108-7
Type :
conf
DOI :
10.1109/ISIC.1990.128474
Filename :
128474
Link To Document :
بازگشت