Title :
Delta rule-based neural networks for inverse kinematics: error gradient reconstruction replaces the teacher
Author :
Werntges, Heinz W.
Abstract :
Control tasks which feed back a scalar error signal (critic) to a controlling neural network form a more general class than those which provide a teacher that is ordinarily required by delta-rule-based networks like backpropagation or CMAC networks. The author introduces an interface that builds teacher vectors from critic values by reconstruction of the gradient of the critic function. Backpropagation networks have been trained by this method to learn the inverse kinematics of simulated planar manipulators. Different strategies for efficient sampling of critic values with respect to restrictions imposed by a real robot arm are proposed, and simulation results are reported
Keywords :
kinematics; neural nets; robots; CMAC networks; back-propagation networks; backpropagation; controlling neural network; critic function; critic values; delta-rule-based networks; error gradient reconstruction; feedback; interface; inverse kinematics; robot arm; scalar error signal; simulated planar manipulators; teacher vectors;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137877