This paper deals with the problem of locating a part moving on a rotating d
isc conveyor with the aid of a single CCD camera and conveyor encoders and
subsequently manipulating the part with a robot manipulator. The precise po
sition and orientation of the disc conveyor with respect to the robot manip
ulator is assumed to be a priori unknown. Likewise the position and orienta
tion of the camera with respect to the robot is also assumed to be a priori
unknown. In order to manipulate the rotating part, the robot controller re
lies on data obtained from multiple sensors. Among the various sensors that
have been used in this paper, we have a single CCD camera which is held fi
xed in the workspace of the robot and which is able to detect features of t
he part as it rotates with the conveyor. Likewise, the camera is also able
to detect features of the end-effector as it moves in the workspace. Additi
onally, the conveyor is assumed to be equipped with an encoder that measure
s the angular position of the rotating disc. What makes the robotic manipul
ation problem hard is that the precise position of the camera and the robot
are priori assumed to be unknown. Thus, the path that the end effector nee
ds to follow is not a priori known in the coordinates of the robot but need
s to be computed during the course of the manipulation. In this paper, a ne
w multisensor fusion scheme is proposed that performs this computation. The
advantage of the scheme is that it greatly weakens requirement on the imag
e processing speed. Overall, our algorithm is able to handle lack of calibr
ation between the robot, the camera and the conveyor, advantage of which is
that it significantly shortens the setup time of the manufacturing workcel
l. The paper touches upon both the theory and the experiments. ((C), 1998 T
he Franklin Institute. Published by Elsevier Science Ltd.