PARALLEL MANIPULATOR KINEMATICS LEARNING USING HOLOGRAPHIC NEURAL-NETWORK MODELS

The forward kinematic problem of parallel manipulators is resolved usi ng a holographic neural paradigm. In a holographic neural model, stimu lus-response (input-output) associations are transformed from the doma in of real numbers to the domain of complex vectors. An element of inf ormation within the holographic neural paradigm has a semantic content represented by phase information and a confidence level assigned in t he magnitude of the complex scalar. Networks are trained on a database generated from the closed-form inverse kinematic solutions. After the learning phase, the networks are tested on trajectories which were no t part of the training data. The simulation results, given for a plana r three-degree-of-freedom parallel manipulator with revolute joints an d for a spherical three-degree-of-freedom parallel manipulator, show t hat holographic neural network models are feasible to solve the forwar d kinematic problem of parallel manipulators. (C) 1998 Elsevier Scienc e Ltd. All rights reserved.