Learning arm kinematics and dynamics.

In this review I have discussed how the form of representation used in internal models of the motor apparatus affects how and what a system can learn. Tabular models and structured models have benefits and drawbacks. Structured models incorporate knowledge of the structure of the controlled motor apparatus. If that knowledge is correct, or close to the actual system structure, the structured models will support global generalization and rapid, efficient learning. Tabular models can play an important role in learning to control systems when either the system structure is not known or only known approximately. Tabular models are general and flexible. Techniques for combining these different representations to attain the benefits of both are currently under investigation. In the control of multijoint systems such as the human arm, internal models of the motor apparatus are necessary to interpret performance errors. In the study of movements restricted to one joint, the problem of interpreting performance errors is greatly simplified and often overlooked, as performance errors can usually be related to command corrections by a single gain. When multijoint movements of the same motor systems are examined, however, the complex nature of the control and coordination problems faced by the nervous system become evident, as well as the sophistication of the brain's solutions to these problems. Recent progress in the understanding of adaptive control of eye movements provides a good example of this (Berthoz & Melvill-Jones 1985). Experimental studies of the psychophysics of motor learning can play an important role in bridging the gap between computational theories of how abstract motor systems might learn and physiological exploration of how actual nervous systems implement learning. Quantitative analyses of the patterns of motor learning of biological systems may help distinguish alternative hypotheses about the representations used for motor control and learning. What a system can and cannot learn, the amount of generalization, and the rate of learning give clues as to the underlying performance architecture. It is also important to know the actual performance level of the motor system (Loeb 1983). Different proposed control strategies will be able to attain different performance levels, and the use of simplifying control strategies may be evident in the control and learning performance of motor systems.

[1]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[2]  Stephen Grossberg,et al.  On Learning of Spatiotemporal Patterns by Networks with Ordered Sensory and Motor Components 1. Excitatory Components of the Cerebellum , 1969 .

[3]  J. Albus A Theory of Cerebellar Function , 1971 .

[4]  W. T. Singleton,et al.  Man-machine systems , 1974 .

[5]  James S. Albus,et al.  Data Storage in the Cerebellar Model Articulation Controller (CMAC) , 1975 .

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

[7]  M. Raibert Analytical equations vs. table look-up for manipulation: A unifying concept , 1977, 1977 IEEE Conference on Decision and Control including the 16th Symposium on Adaptive Processes and A Special Symposium on Fuzzy Set Theory and Applications.

[8]  M. H. Raibert,et al.  Manipulator control using the configuration space method , 1978 .

[9]  Masaru Uchiyama,et al.  Formation of High-Speed Motion Pattern of a Mechanical Arm by Trial , 1978 .

[10]  E. Bizzi,et al.  Effect of load disturbances during centrally initiated movements. , 1978, Journal of neurophysiology.

[11]  A. Pellionisz,et al.  Brain modeling by tensor network theory and computer simulation. The cerebellum: Distributed processor for predictive coordination , 1979, Neuroscience.

[12]  Elliot Saltzman,et al.  Levels of sensorimotor representation , 1979 .

[13]  A. Pellionisz,et al.  Tensorial approach to the geometry of brain function: Cerebellar coordination via a metric tensor , 1980, Neuroscience.

[14]  Teuvo Kohonen,et al.  Content-addressable memories , 1980 .

[15]  D A Robinson,et al.  The use of control systems analysis in the neurophysiology of eye movements. , 1981, Annual review of neuroscience.

[16]  K. Preston White,et al.  Systems engineering models of human-machine interaction , 1981, Proceedings of the IEEE.

[17]  James S. Albus,et al.  Brains, behavior, and robotics , 1981 .

[18]  Kamesh Ramakrishna Review of "Systems Engineering Models of Human-Machine Interaction by William B. Rouse", North Holland. , 1981, SGAR.

[19]  J. Hollerbach Computers, brains and the control of movement , 1982, Trends in Neurosciences.

[20]  F. J. Clark,et al.  Signaling of kinesthetic information by peripheral sensory receptors. , 1982, Annual review of neuroscience.

[21]  P. Matthews Where does Sherrington's "muscular sense" originate? Muscles, joints, corollary discharges? , 1982, Annual review of neuroscience.

[22]  A. Pellionisz,et al.  Space-time representation in the brain. The cerebellum as a predictive space-time metric tensor , 1982, Neuroscience.

[23]  Hendrik Van Brussel,et al.  A self-learning automaton with variable resolution for high precision assembly by industrial robots , 1982 .

[24]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[25]  G. Loeb Finding common groud between robotics and physiology , 1983, Trends in Neurosciences.

[26]  John J. Craig,et al.  Adaptive control of manipulators through repeated trials , 1984 .

[27]  A. Wing,et al.  The Psychology of human movement , 1984 .

[28]  J. Adams Learning of movement sequences , 1984 .

[29]  R. Schmidt,et al.  Knowledge of results and motor learning: a review and critical reappraisal. , 1984, Psychological bulletin.

[30]  T. Poggio,et al.  The analysis of stereopsis. , 1984, Annual review of neuroscience.

[31]  Geoffrey E. Hinton,et al.  Parallel computations for controlling an arm. , 1984, Journal of motor behavior.

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

[33]  J. F. Soechting,et al.  Psychophysical determination of coordinate representation of human arm orientation , 1984, Neuroscience.

[34]  Marc H. Raibert,et al.  Tabular control of balance in a dynamic legged system , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[35]  Enis Ersü,et al.  A New Concept for Learning Control Inspired by Brain Theory , 1984 .

[36]  John M. Hollerbach,et al.  The Computational Approach to Vision and Motor Control , 1985 .

[37]  George A. Bekey,et al.  Identification of parameters in models of robots with rotary joints , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[38]  S. Arimoto,et al.  Learning control theory for dynamical systems , 1985, 1985 24th IEEE Conference on Decision and Control.

[39]  F A Miles,et al.  Visually induced adaptive changes in primate saccadic oculomotor control signals. , 1985, Journal of neurophysiology.

[40]  Amitabha Mukerjee Adaptation In Biological Sensory-Motor Systems: A Model For Robotic Control. , 1985, Other Conferences.

[41]  S. Hara,et al.  Synthesis of repetitive control systems and its application , 1985, 1985 24th IEEE Conference on Decision and Control.

[42]  Richard S. Sutton,et al.  Training and Tracking in Robotics , 1985, IJCAI.

[43]  A. Berthoz,et al.  Adaptive mechanisms in gaze control : facts and theories , 1985 .

[44]  R. Liscano,et al.  A Sensor Based Approach For Robot Programming , 1985, Other Conferences.

[45]  S. Amari,et al.  Sensori-motor transformations in the brain (with a critique of the tensor theory of cerebellum). , 1985, Journal of theoretical biology.

[46]  John Annett,et al.  Motor Learning: A Review , 1985 .

[47]  S. Wray Adaptive mechanisms in gaze control. , 1986, Reviews of oculomotor research.

[48]  Amitabha Mukerjee,et al.  Self-calibration in robot manipulators , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[49]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[50]  A. Pellionisz,et al.  Tensor network theory of the metaorganization of functional geometries in the central nervous system , 1985, Neuroscience.

[51]  A. G. Feldman Once More on the Equilibrium-Point Hypothesis (λ Model) for Motor Control , 1986 .

[52]  A. Georgopoulos On reaching. , 1986, Annual review of neuroscience.

[53]  M. Togai,et al.  Learning control and its optimality: Analysis and its application to controlling industrial robots , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[54]  C. Gielen,et al.  Coordination of arm muscles during flexion and supination: Application of the tensor analysis approach , 1986, Neuroscience.

[55]  Christopher G. Atkeson,et al.  Estimation of Inertial Parameters of Manipulator Loads and Links , 1986 .

[56]  S Ullman,et al.  Artificial intelligence and the brain: computational studies of the visual system. , 1986, Annual review of neuroscience.

[57]  O. I. Fukson,et al.  Adaptability of innate motor patterns and motor control mechanisms , 1986, Behavioral and Brain Sciences.

[58]  Christopher G. Atkeson,et al.  Robot trajectory learning through practice , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[59]  Marc H. Raibert,et al.  Legged Robots That Balance , 1986, IEEE Expert.

[60]  Katsuhisa Furuta,et al.  Iterative generation of optimal input of a manipulator , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[61]  Luca Maria Gambardella,et al.  Learning of movements in robotic manipulators , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[62]  E. G. Harokopos Optimal learning control of mechanical manipulators in repetitive motions , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[63]  Geoffrey E. Hinton Learning in massively parallel nets , 1986, AAAI 1986.

[64]  Daniel E. Whitney,et al.  Industrial Robot Forward Calibration Method and Results , 1986 .

[65]  Michael Kuperstein,et al.  Adaptive visual-motor coordination in multijoint robots using parallel architecture , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[66]  Pradeep K. Khosla,et al.  Estimation of Robot Dynamics Parameters: Theory and Application , 1987 .

[67]  C. Koch,et al.  The analysis of visual motion: from computational theory to neuronal mechanisms. , 1986, Annual review of neuroscience.

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

[69]  J. Adams Historical review and appraisal of research on the learning, retention, and transfer of human motor skills. , 1987 .

[70]  W. Thomas Miller,et al.  A Nonlinear Learning Controller for Robotic Manipulators , 1987, Other Conferences.

[71]  E. Bizzi,et al.  Controlling multijoint motor behavior. , 1987, Exercise and sport sciences reviews.

[72]  E I Knudsen,et al.  Computational maps in the brain. , 1987, Annual review of neuroscience.

[73]  Christopher G. Atkeson,et al.  Model-Based Control of a Robot Manipulator , 1988 .

[74]  Christopher G. Atkeson,et al.  Experimental evaluation of feedforward and computed torque control , 1989, IEEE Trans. Robotics Autom..