It is normal when programming a robotic manipulator to provide the end effe
ctor's orientation and position at the pick up and drop off locations. Addi
tional sensory information and intelligence is needed, however, to detect t
he presence of a part as well as its location if the assembly site cannot b
e controlled precisely by employing expensive jigs or fixtures. This paper
investigates, for this purpose, the application of solely an inexpensive la
ser sensor mounted unobtrusively to the end effector of a CRS robot having
customized hardware and open software. Data from the sensor is converted in
to a single "Feature Value Vector" to recognize a part and accurately deter
mine its location by using a neural network and back propagation training.
The procedure's viability is tested by assembling a set of tightly meshing
gears under poor ambient lighting. (C) 2000 Elsevier Science Ltd. All right
s reserved.