The put-pose of this paper is to show how statistical procedures can be use
d to design robotic assembly cells. The proposed methodology has two stages
. In the first stage, a fuzzy clustering algorithm is employed to group sim
ilar tasks together so that they can be assigned to robots while maintainin
g a balanced cell and achieving a desired production cycle time. In the sec
ond stage, a Mahalanobis distance procedure is used to select robots approp
riate for the task groups. The proposed approach recognizes and exploits th
e flexibility of robots. It also recognizes that the manufacturer specifica
tions of robots do not hold simultaneously under normal operating condition
s. A numerical example is presented and a small experiment is conducted to
test die procedures.