This paper presents a genetic algorithm approach to determine the architect
ural parameters of a Stewart-Gough platform that has a workspace as close a
s possible to a prescribed workspace. The algorithm used determines the int
ersection between the actual workspace and the prescribed one. The genetic
algorithm then optimizes 26 architectural parameters to minimize the area o
f the regions that do not intersect. The optimization can be performed for
a fixed orientation of the platform, for an orientation that varies about a
certain axis, or for different platform elevations. (C) 2001 Published by
Elsevier Science Ltd. All rights reserved.