Robotized Moving Line Assembly Based on Sensor Fusion

gurgleplayAI and Robotics

Oct 18, 2013 (3 years and 9 months ago)

51 views

Robotized Moving Line Assembly Based on Sensor Fusion


Heping Chen
*
, Thomas Fuhlbrigge and George Zhang

ABB Corporate Research Center

2000 Day Hill Road

Windsor, Connecticut 06095


*
heping.chen@us.abb.com

Te
l: 860 285
-
6925


A
ssembly
task
s
using industrial robots
have increased in both number and complexity
over the years because of the increasing requirements of product quality and quantity.

However, assembly robots are still a small portion of total robot sa
les each year. One of
the main reasons is that it is difficult for conventional industrial robots to adjust to any
sort of change. Therefore, more

intelligent

industrial robotic systems

are
rapidly
expanding

the realms of possibility in assembly applicatio
ns because they

can perform
assembly tasks with high autonomy and adaptability to the environments.


Moving line assembly (Assembly is performed while the part is moving) is an intelligent
robotic system based on vision, force and position sensor fusion. T
he robot can track the
moving object while performing the assembly process.

Moving line assembly receives
more and more attention in both academia and industry because the work cells are fully
automated without stopping the assembly line. Therefore, it can

save huge amounts of
manufacturing resources by replacing "Stop
-
stations" where robots work in a stationary
and fully calibrated environment.


There is some research work in the moving line assembly. Some researchers used stereo
vision systems. The proc
essing of stereo information enables a robot to determine the
position and orientation of an object in the robot coordinate frame. However, an accurate
calibration between the camera coordinate system and robot coordinate system has to be
realized. Because

the stereo vision system requires high quality camera and accurate
calibrations, the existing systems are costly, error prone and not robust enough for daily
use at the workshop. Also the complicated computation for determining the position and
orientatio
n of an object makes the system difficult to be implemented in real time
applications.


This paper

discusses an assembly technology

while the object is moving using visual and
force servoing. The wheel loading process, which assemblies the wheel into the
wheel
hub of a vehi
cle on a moving assembly line,
is used as an example

to demonstrate the
developed technology
.
A working system has been set up and experiments of loading
wheels onto the wheel hub have been implemented and performed successfully. The
exp
erimental results demonstrate that the developed technology can be used for assembly
while the assembly line is moving randomly.



P
resenting author biography


Heping Chen

is a research scientist at Robotics and Automation Lab, ABB Corporate
Research Cen
te
r, ABB Inc. He

received
his

Ph.D. in Electrical and Computer
Engineering from Michigan State University, Michigan, in 2004.
He published more than

40 journal/conference papers

and several patents
. He received several awards including

the Best Paper Award
from the distinguished IEEE Transactions on Automation Science
and Engineering,
Quality Salute Award from ABB

Inc.
, the Most Outstanding Graduate
Student Award from Michigan State University and the Highly Commended Award
s

from
the Journal of Industrial Ro
bots. His research interests include

industrial robotics and
automation, machine vision
,
sensor fusion,
micro/nano robotics, and control system
design and

implementation.