This paper presents a genetic algorithm approach for the synthesis of plana
r three-degree-of-freedom parallel manipulators. A genetic algorithm is an
optimization method inspired by natural evolution. As in nature, the fittes
t members of a population are given better chances of reproducing and trans
mitting part of their genetic heritage to the next generation. This leads t
o stronger and stronger generations which evolve towards the solution of th
e problem. for the application studied here, the individuals in the populat
ion consist of the architectural parameters of the manipulators. The algori
thm optimizes these parameters to obtain a workspace as close as possible t
o a prescribed working area. For each individual of the population, the geo
metric description of the workspace can be obtained. The algorithm then det
ermines the intersection between the prescribed workspace and the actual wo
rkspace, and minimizes the area of the regions that do not intersect. The m
ethod is applied to two planar three-degree-of-freedom parallel manipulator
s, one wit prismatic joints and one with revolute joints.