A new adaptive learning algorithm for robot manipulator control

Abstract

This paper is devoted to the development and implementation of neural network technology to solve the inverse kinematics problems for serial robot manipulators, given the desired Cartesian path of the end effector of the manipulator in a free-of-obstacles workspace. Offline smooth geometric paths in the joint space of the manipulator are obtained.

The proposed technique does not require any prior knowledge of the kinematics model of the system being controlled; the main idea of this approach is the use of an artificial neural network to learn the robot system characteristics rather than having to specify an explicit robot system model.

Since one of the most important problems in using artificial neural networks is the choice of the appropriate network configuration, two different configurations were compared; they were trained to learn the desired set of joint angles positions from a given set of end effector positions.

The generality and efficiency of the proposed algorithm are demonstrated through simulations of a general six-degrees-of-freedom serial robot manipulator.

Keywords

neural networks inverse kinematics back propagation robot control

Get full access to this article

View all access options for this article.

References

K. S.

Gonzalez

R. C.

Lee

C. S. G.

Robotics control, sensing, vision and intelligence, 1987 (McGraw-Hill, New York).

Denavit

Hertenberg

R. S. A.

Kinematics notation for lower pair mechanism based on matrices

Appl. Mechanics, 1955, 77, 215–221.

Lee

H. Y.

Liang

C. G. A.

New vector theory for the analysis of spatial mechanism

Mechanism Mach. theory, 1988, 23 (3), 209–217.

Lee

H. Y.

Liang

C. G.

Displacement analysis of the general spatial 7-link 7R mechanism

Mechanism Mach. theory, 1988, 23 (3), 219–226.

Duffy

Rooney

J. A.

Foundation for a unified theory of analysis of spatial mechanism

Trans. ASME, J. Engng Industry, 1975, 97 (4), 1159–1164.

Duffy

Analysis of mechanism and robot manipulators, 1980 (John Wiley, New York).

Pennock

G. R.

Yang

A. T.

Application of dual-number matrices to the inverse kinematics problem of robot manipulators

J. Mechanisms, Transmissions, Automn Des., 1985, 107 (2), 201–208.

Yang

A. T.

Displacement analysis of spatial five-link mechanism using (3 × 3) matrices with dual-number element

Trans. ASME, J. Engng Industry, 1969, 9 (1), 152–157.

Albala

Angeles

Numerical solution to the input-output displacement equation of the general 7R spatial mechanism

In Proceedings of the Fifth World Congress on the Theory of machines and mechanisms, 1979, pp. 1008–1011.

10.

Uicker

J. J.

Denavit

Hartenberg

R. S.

An iterative method for displacement analysis of spatial mechanisms

Trans. ASME, J. Appl. Mechanics, 1964, 86 (2), 309–314.

11.

Yuan

M. S.C.

Freudenstein

Kinematics analysis of spatial mechanisms by means of screw coordinate

Trans. ASME, J. Engng Industry, 1971, 93 (1), 61–73.

12.

Kohli

Soni

A. H.

Kinematics analysis of spatial mechanisms via successive screw displacements

Trans. ASME, J. Engng Industry, 1975, 97 (2), 739–747.

13.

Yang

A. T.

Freudenstein

Application of dual number quarterian algebra to the analysis of spatial mechanisms

Trans. ASME, J. Appl. Mechanics, 1964, 86, 300–308.

14.

Martins

Guenther

Hierarchical kinematics analysis of robots

Mechanism Mach. theory, 2003, 33, 497–518.

15.

Omid

Patrick

V. D. S.

Neural systems for robotics, 1997 (Academic Press, New York).

16.

Ananthraman

Garg

D. P.

Training back-propagation and CMAC neural network for control of a SCARA robot

Engng Applic. Artif. Intell., 1993, 6 (2), 105–115.

17.

Ananthraman

Nagchaudhuri

Garg

D. P.

Control of a robotic manipulator using a neural controller In Proceedings of the 22nd Modeling and Simulation Conference, Pittsburgh, Pennsylvania, USA, 1991, pp. 1846–1853.

18.

Atkeson

C. G.

Reinkensmeyer

D. J.

Using content addressable memories to control robots

In Proceedings of the 27th IEEE Conference on Decision and control, Austin, Texas, USA. 1988, pp. 792–797 (IEEE, New York).

19.

Miller

W. T.

III Hewes

R. P.

Glanz

F. H.

Kraft

L. G.

III

Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller

IEEE Trans. Robotics Automn, 1990, 6, 1–9.

20.

Kalorgirou

S. A.

Artificial neural networks in renewable energy systems applications: A review

Renewable Sustainable Energy Rev., 2001, 5, 373–401.

21.

Tevatia

Schaal

Inverse kinematics for humanoid robots

In Proceedings of the IEEE International Conference on Robotics and automation, 2000 (IEEE, New York).

22.

Köker

Öz

Cakar

Ekiz

A study of neural network based inverse kinematics solution for a three-joint robot

Robotics Autonomous Systems, 2004, 49, 227–234.

23.

Oyama

Tachi

Modular neural net system for inverse kinematics learning

In Proceedings of the IEEE International Conference on Robotics and automation, 2000 (IEEE, New York).

24.

Oyama

Chong

N. Y.

Agah

Meada

Tachi

Inverse kinematics learning by modular architecture neural networks with performance prediction networks

In Proceedings of the IEEE International Conference on Robotics and automation, 2001 (IEEE, New York).

25.

Oyama

Agah

MacDorman

K. F.

Meada

Tachi

A modular neural network architecture for inverse kinematics model learning

Neuro-computing, 2001, 38-40, 797–805.

26.

Karilk

Aydin

An improved approach to the solution of inverse kinematics problems for robot manipulators

Engng Applic. Artif. Intell., 2000, 13, 159–164.

27.

Craig

J. J.

Introduction to robotics, mechanics and control, 1986 (Addison-Wesley, Reading, Massachusetts).

28.

Haykin

Neural networks. A comprehensive foundation, 1994 (Macmillan, London).