Acceleration based learning control of robotic manipulators using a multi-layered neural network

This paper presents a nonlinear compensation method based on neural networks for trajectory control of robotic manipulators. A multi-layered perceptron neural network (MLP) is used to predict the required actuator torques of a robot to follow a desired trajectory, and these predicted torques are applied to the robot as feedforward compensations in parallel to a linear feedback controller. An acceleration based learning scheme is proposed to adjust the connection weights in the neural network to form an approximated dynamic model of the robot. Simulation results show that the proposed learning scheme improves the speed of error convergence of the system and reduces the convergent error with the efficient adaptation to the changing system dynamics. The validity of the proposed learning scheme is verified through experiments. >

[1]  Steven K. Rogers,et al.  Neural network payload estimation for adaptive robot control , 1991, IEEE Trans. Neural Networks.

[2]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[3]  J. Y. S. Luh,et al.  Resolved-acceleration control of mechanical manipulators , 1980 .

[4]  Tae-Yong Kuc,et al.  An iterative learning control of robot manipulators , 1991, IEEE Trans. Robotics Autom..

[5]  Suguru Arimoto,et al.  Realization of robot motion based on a learning method , 1988, IEEE Trans. Syst. Man Cybern..

[6]  Steven Dubowsky,et al.  The application of model-referenced adaptive control to robotic manipulators , 1979 .

[7]  C. Atkeson,et al.  Learning arm kinematics and dynamics. , 1989, Annual review of neuroscience.

[8]  Mitsuo Kawato,et al.  Feedback-error-learning neural network for trajectory control of a robotic manipulator , 1988, Neural Networks.

[9]  B. H. Lee,et al.  Resolved Motion Adaptive Control for Mechanical Manipulators , 1984, 1984 American Control Conference.

[10]  Filson H. Glanz,et al.  Application of a General Learning Algorithm to the Control of Robotic Manipulators , 1987 .

[11]  Yoshiki Uchikawa,et al.  Trajectory control of robotic manipulators using neural networks , 1991 .

[12]  M. Kawato,et al.  Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[13]  Richard Paul Collins Paul,et al.  Modelling, trajectory calculation and servoing of a computer controlled arm , 1972 .

[14]  Suguru Arimoto,et al.  Bettering operation of Robots by learning , 1984, J. Field Robotics.

[15]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[16]  W. Thomas Miller,et al.  Real-time dynamic control of an industrial manipulator using a neural network-based learning controller , 1990, IEEE Trans. Robotics Autom..

[17]  Ten-Huei Guo,et al.  Adaptive linear controller for robotic manipulators , 1983 .

[18]  C.s.g. Lee,et al.  An adaptive control strategy for mechanical manipulators , 1984 .