This paper discusses the use of artificial neural networks (ANNs) as a method of trajectory tracking control for a robotic system. Using an ANN does not require any prior knowledge of the kinematics model of the system being controlled; the basic idea of this concept is the use of the ANN to learn the characteristics of the robot system rather than to specify an explicit robot system model.
In this approach, disadvantages of some schemes such as the fuzzy learning control, for example, have been elevated. Off-line training was performed for a geometric trajectory that is free of obstacles.
Studying the kinematics Jacobian of serial manipulators by using ANNs has two problems: one of these is the selection of the appropriate configuration of the network and the other is the generation of a suitable training dataset. In this approach, although this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint to overcome the effect of kinematics uncertainties present in the real world such as ill-defined linkage parameters, links flexibility, and backlashes in the gear train. Then two network configurations were compared to find the best configuration to be used. Finally, the simulation results were verified experimentally using a general six-degree-of-freedom (DOF) serial robot manipulator.
KuroeY.NakaiY.MoriT.‘A new neural network learning on inverse kinematics of robot manipulators.’ In the International Conference onNeural networks, IEEE World Congress on Computational intelligence
2.
FuK. S.GonzalezR. C.LeeC. S. G.Robotics: control, vision, and intelligence. International edition, (McGraw-Hill Book Company, Singapore.1987)
3.
TsaiL. W.Robot analysis, the mechanics of serial and parallel manipulators, International edition, (John Wiley & Sons, New York.1999)
4.
CheahC. C.LeeK.KawamuraS.ArimotoS.‘Asymptotic stability of robot control with approximate Jacobian matrix and its application to visual servoing.’In Proceedings of the 39th IEEE Conference on Decision and control, Sydney, Australia, 2000, pp. 3939–3944.
5.
AntonelliG.ChiaveriniS.FuscoG.‘A new on-line algorithm for inverse kinematics of robot manipulators ensuring path-tracking capability under joint limits.’IEEE Trans. on Robotics and Automn19 (1) (2003): 162–167
6.
KarilkB.AydinS.‘An improved approach to the solution of inverse kinematics problems for robot manipulators.’Int. J. Engng Applics of Artif. Intell.13 (2000): 159–164
7.
DahlO.NielsenL.‘Torque-limited path following by on line trajectory time scaling.’IEEE Trans. on Robotics and Automn6 (1990): 554–561
8.
Kirc'anskiM.Kirc'anskiN.‘Resolved-rate and resolved-acceleration based robot control in the presence of actuators constraints.’In Proceedings of the IEEE International Conference on Robotics and automation, Albuquerque, New Mexico, 1997, pp. 235–240.
9.
FaizN.AgrawalS. K.‘Trajectory planning of robots with dynamics and inequalities.’In Proceedings of the IEEE International Conference on Robotics and automation, San Francisco, California, 2000, pp. 3977–3983.
10.
WhitneyE.‘Resolved motion rate control of manipulators and human prostheses.’IEEE Trans. on Man-Mach. Systems MMS-10 (1969): 47–53
11.
HuZ.FuZ.FangH.‘Study of singularity robust inverse of Jacobian matrix for manipulator.’In Proceedings of the First International Conference on Machine learning and cybernetics, Beijing, 2002, pp. 406–410.
12.
NakamuraY.HanafusaH.‘Inverse kinematics solutions with singularity robustness for robot manipulator control.’Int. J. Dynamic Systems Measmts Control108 (1986): 163–171
13.
WamplerC. W.‘Manipulator inverse kinematics solutions based on vector formulations and damped least-squares methods.’IEEE Trans. on Systems Man, and Cybernetics16 (1986): 93–101
14.
WamplerC. W.LeiferL. J.‘Applications of damped least-squares methods to resolved-rate and resolved-acceleration control of manipulators.’Int. J. Dynamic Systems Measmts Control110 (1988): 31–38
15.
D'SouzaA.VijayakumarS.SchaalS.‘Learning inverse kinematics.’In Proceedings of the 2001 IEEE/RSJ International Conference on Intelligent robots and systems, Maui, Hawaii, 2001, pp. 298–303.
16.
OgawaT.MatsuuraH.KanadaH.‘A solution of inverse kinematics of robot arm using network inversion.’In Proceedings of the International Conference on Computational intelligence for modelling, control and automation, Vienna, Austria, 28-30 November 2005, pp. 858–862
17.
KökerR.‘Reliability-based approach to the inverse kinematics solution of robots using Elman's networks.’Int. J. Engng Applics of Artif. Intell.18 (2005): 685–693
18.
HasanA. T.HamoudaA. M. S.IsmailN.Al-AssadiH. M. A. A.‘An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 D.O.F serial robot manipulator.’Int. J. Advances in Engng Software37 (2006): 432–438
19.
Al-AssadiH. M. A. A.HamoudaA. M. S.IsmailN.ArisI.‘An adaptive learning algorithm for controlling a two-degree-of-freedom serial ball-and-socket actuator.’Proc. IMechE, Part I: J. Systems and Control Engineering221 (I7) (2007): 1001–1006
20.
BingualZ.ErtuncH. M.OysuC.‘Comparison of inverse kinematics solutions using neural network for 6R robot manipulator with offset.’ In ICSC Congress onComputational intelligence, Turkey, 15-17 December 2005, pp. 5–10
21.
GracaR. A.GuY.‘A fuzzy learning algorithm for kinematic control of a robotic system.’In Proceedings of the 32nd Conference on Decision and control, San Antonio, Texas, 1993, pp. 1274–1279.
22.
FunahashiK. I.‘On the approximate realization of continuous mapping by neural networks.’Neural Networks2 (3) (1998): 183–192
23.
HasanA. T.HamoudaA. M. S.IsmailN.Al-AssadiH. M. A. A.‘A new adaptive learning algorithm for robot manipulator control.’Proc. IMechE, Part I: J. System and Control Engineering221 (I4) (2007): 663–672
24.
KökerR.ÖzC.ÇakarT.EkizH.‘A study of neural network based inverse kinematics solution for a three-joint robot.’Robotics and Autonomous Systems49 (2004): 227–234
25.
DriscollJ. A.‘Comparison of neural network architectures for the modeling of robot inverse kinematics.’ In Proceedings of the IEEE, Southeaston Astcon, 2000, pp. 44–51.
26.
HornikK.‘Approximation capabilities of multi-layer feed forward networks.’Proc. IEEE Trans. on Neural Networks4 (2) (1991): 251–257
27.
DenavitJ.HartenbergR. S. A.‘Kinematics notation for lower pair mechanism based on matrices.’Appl. Mechanics77 (1955): 215–221
28.
DulębaI.SasiadekJ. Z.‘Modified Jacobian method of transversal passing through singularities of nonredundant manipulators.’ In Proceedings of the American Control Conference, Chicago, Illinois, June, 2000, pp. 2839–2843.
29.
ZuradaJ. M.Introduction to artificial neural systems, (West Publishing Company, Singapore.1992)
