An approach to simplify the learning space for robot learning control

Although learning controllers are considered to be capable of generalization, most robot learning control schemes either need to include conventional controllers, or need to repeat the learning process each time a new trajectory is encountered. The main reason for this deficiency is that the learning space for executing general motions of multi-joint robot manipulators is too large. In this paper, we propose an approach, motivated by the equilibrium-point hypothesis in human motor control, to simplify the learning space when learning controllers are used to govern robot motions. In the proposed approach, the motion command is formulated in the form of three square pulses in alternate directions with adjustable heights and widths. When the motion command is specified in this simple form, the learning space for dealing with variations exhibited in different movements is dramatically simplified. Thus, we can then implement a fuzzy system for robot motion control, which generates appropriate controlled parameters for the motion commands by using a reasonable number of rules. Theoretical analyses and simulations are performed to demonstrate the feasibility of the proposed approach.

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

[2]  Piero P. Bonissone,et al.  Integrating case- and rule-based reasoning , 1993, Int. J. Approx. Reason..

[3]  Fuzzy Logic in Control Systems : Fuzzy Logic , 2022 .

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

[5]  Steven L. Lehman,et al.  Input Identification Depends on Model Complexity , 1990 .

[6]  Chuen-Chien Lee FUZZY LOGIC CONTROL SYSTEMS: FUZZY LOGIC CONTROLLER - PART I , 1990 .

[7]  Jack M. Winters,et al.  Multiple Muscle Systems , 1990, Springer New York.

[8]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[9]  C.-H. Wu,et al.  Voluntary movements for robotic control , 1992, IEEE Control Systems.

[10]  Kuu-Young Young,et al.  Control of voluntary limb movements by using a fuzzy system , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[11]  Timothy D. Lee,et al.  Motor Control and Learning: A Behavioral Emphasis , 1982 .

[12]  D M Corcos,et al.  Organizing principles for single-joint movements. I. A speed-insensitive strategy. , 1989, Journal of neurophysiology.

[13]  A. Nedungadi,et al.  A novel approach to robot control using fuzzy logic , 1991, Conference Proceedings 1991 IEEE International Conference on Systems, Man, and Cybernetics.

[14]  D. Corcos,et al.  Organizing principles for single-joint movements. II. A speed-sensitive strategy. , 1989, Journal of neurophysiology.

[15]  H. Zimmermann,et al.  Fuzzy Set Theory and Its Applications , 1993 .

[16]  Choo Min Lim,et al.  Application of fuzzy logic control to a manipulator , 1991, IEEE Trans. Robotics Autom..

[17]  J. Houk,et al.  Nonlinear damping of limb motion , 1990 .

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

[19]  K. F. Gill,et al.  Use of fuzzy logic in robotics , 1988 .

[20]  Phillip J. McKerrow,et al.  Introduction to robotics , 1991 .

[21]  E. Bizzi,et al.  Characteristics of motor programs underlying arm movements in monkeys. , 1979, Journal of neurophysiology.