Learning feedforward control based on the available dynamic/kinematic system model and sensor information is generally effective for reducing the tracking error for a learned trajectory. For new trajectories, however, the system cannot benefit from previous learning data and it has to go through the learning process again to regain its performance. In industrial applications, this means production line has to stop for learning, and the overall productivity of the process is compromised. To solve this problem, this paper proposes a feedforward input generation scheme based on neural network (NN) prediction. Learning/training is performed for the NNs for a set of trajectories in advance. Then the feedforward torque input for any trajectory in the predefined workspace can be calculated according to the predicted error from multiple NNs managed with expert logic. Experimental study on a 6-DOF industrial robot has shown the superior performance of the proposed NN based feedforward control scheme in the position tracking as well as the residual vibration reduction, without any further learning or end-effector sensors during operation.

References

References
1.
Asensio
,
J.
,
Chen
,
W.
, and
Tomizuka
,
M.
,
2012
, “
Robot Learning Control Based on Neural Network Prediction
,”
Proceedings of the ASME 2012 Dynamic Systems and Control Conference
, pp.
1489
1497
.
2.
Bristow
,
D. A.
, and
Tharayil
,
M.
,
2006
, “
A Survey of Iterative Learning Control: A Learning-Based Method for High-Performance Tracking Control
,”
IEEE Control Systems Magazine
, (June), pp.
96
114
.10.1109/MCS.2006.1636313
3.
Cuiyan
,
L.
, and
Dongchun
,
Z.
,
2004
, “
A Survey of Repetitive Control
,”
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
, pp.
1160
1166
.
4.
Gopinath
,
S.
,
Kar
,
I.
, and
Bhatt
,
R.
,
2008
, “
Experience Inclusion in Iterative Learning Controllers: Fuzzy Model Based Approaches
,”
Eng. Applic. Artif. Intell.
,
21
(
4
), pp.
578
590
.10.1016/j.engappai.2007.05.008
5.
Arif
,
M.
,
Ishihara
,
T.
, and
Inooka
,
H.
,
2002
, “
Generalization of Iterative Learning Control for Multiple Desired Trajectories in Robotic Systems
,”
PRICAI 2002: Trends in Artificial Intelligence
, Vol.
2417
, pp.
29
38
.10.1007/3-540-45683-X
6.
Chien
,
C.-j.
,
2008
, “
A Combined Adaptive Law for Fuzzy Iterative Learning Control of Nonlinear Systems With Varying Control Tasks
,”
IEEE Trans. Fuzzy Syst.
,
16
(
1
), pp.
40
51
.10.1109/TFUZZ.2007.902021
7.
Freeman
,
C. T.
,
Alsubaie
,
M. A.
,
Cai
,
Z.
,
Rogers
,
E.
, and
Lewin
,
P. L.
,
2011
, “
Initial Input Selection for Iterative Learning Control
,”
ASME J. Dyn. Syst., Meas., Control
,
133
, p.
054504
.10.1115/1.4003096
8.
Moody
,
J.
, and
Darken
,
C.
,
1989
, “
Fast Learning in Networks of Locally-Tuned Processing Units
,”
Neural Comput.
,
1
, pp.
281
294
.10.1162/neco.1989.1.2.281
9.
Poggio
,
T.
, and
Girosi
,
F.
,
1990
, “
Networks for Approximation and Learning
,”
Proc. IEEE
,
78
, pp.
1481
1497
.10.1109/5.58326
10.
Viñuela
,
P. I.
, and
Galván
,
I. M.
,
2004
,
Redes de Neuronas Artificiales. Un Enfoque Práctico
,
Pearson Education
, Madrid, Spain.
11.
Chen
,
W.
, and
Tomizuka
,
M.
,
2012
, “
Load Side State Estimation in Elastic Robots With End-effector Sensing
,”
IEEE/ASME International Conference on Advanced Intelligent Mechatronics
, pp.
598
603
.
12.
de Wit
,
C. C.
,
Bastin
,
G.
, and
Siciliano
,
B.
,
1996
,
Theory of Robot Control
,
1st ed.
Springer-Verlag New York, Inc.
,
Secaucus, NJ
.
13.
Chen
,
W.
, and
Tomizuka
,
M.
,
2012
, “
Iterative Learing Control With Sensor Fusion for Robots with Mismatched Dynamics and Mismatched Sensing
,”
Proceedings of the ASME 2012 Dynamic Systems and Control Conference
, pp.
1480
1488
.
14.
Bovik
,
A. C.
,
2009
,
The Essential Guide to Image Processing
,
Elsevier
,
Burlington, MA
.
15.
Rumelhart
,
D.
,
Hintont
,
G.
, and
Williams
,
R.
,
1986
, “
Learning Representations by Back-Propagating Errors
,”
Nature
,
323
(
6088
), pp.
533
536
.10.1038/323533a0
16.
Torii
,
M.
, and
Hagan
,
M.
,
2002
, “
Stability of Steepest Descent With Momentum for Quadratic Functions
,”
IEEE Trans. Neural Netw.
,
13
(
3
), pp.
752
756
.10.1109/TNN.2002.1000143
You do not currently have access to this content.