Connectionist approaches to the control of manipulation robots at the executive hierarchical level: An overview | Journal of Intelligent & Robotic Systems Skip to main content
Springer Nature Link
Log in

Connectionist approaches to the control of manipulation robots at the executive hierarchical level: An overview

  • Published:
Journal of Intelligent and Robotic Systems Aims and scope Submit manuscript

Abstract

One of the most interesting and important properties of connectionist systems is their ability to control sophisticated manipulation robots, i.e. to produce a large number of efficient control commands in real-time. This paper represents an attempt to give a comprehensive report of the basic principles and concepts of connectionism in robotics, with an outline of a number of recent algorithms used in learning control of a manipulation robot. A major concern in this paper is the application of neural networks for off-line and on-line learning of kinematic and dynamic relations used in robot control at the executive hierarchical level.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Saridis, G.N.,Self-Organization Control of Stochastic Systems, Marcel Dekker, New York, 1977.

    Google Scholar 

  2. Meystel, A., Intelligent Control: Issues and perspective,Proc. IEEE Sympos. Intelligent Control, Troy, 1985.

  3. Saridis, G.N., Intelligent robotic control,IEEE Trans. Automat. Control AC-28(5) May 1983.

  4. Meystel, A., Intelligent control in robotics,J. Robot. Systems 5 (1988), 269–308.

    Google Scholar 

  5. Bavarian, B., Introduction to neural networks for intelligent control,IEEE Control Systems Magazine 8 (2) (1988), 3–7.

    Google Scholar 

  6. Rumelhart, D.E. and McClelland, J.L.,Parallel Distributed Processing (PDP):Exploration in the Microstructure of Cognition, vols 1 and 2, MIT Press, Cambridge, 1986.

    Google Scholar 

  7. Wasserman, P.D.,Neural Computing:Theory and Practice, Van Nostrand Reinhold, New York, 1989.

    Google Scholar 

  8. Hopfield, J., Neural networks and physical systems with emergent collectional computational abilities,Proc. National Academy of Science (April 1988), 2554–2558.

  9. Albus, J., A new approach to manipulator control: The cerebellar model articulation controller,Trans. ASME, J. Dynam. Systems, Meas. Control 97 (1975), 220–227.

    Google Scholar 

  10. Widrow, B. and Hoff, M.E., Adaptive switching circuits,Proc. IRE Western Electronic Show and Conference, vol. 4 (1960), pp. 96–104.

    Google Scholar 

  11. Miller, W.T., Box, B.A., and Whitney, E.C., Design and implementation of a high speed CMAC neural network using programmable CMOS logic arrays, Report ICE. IS 90.01, University of New Hampshire, February 1980.

  12. Pineda, F.J., Generalization of back propagation to recurrent networks,Phys. Rev. Lett. 59(19) (1987), 2229–2232.

    Google Scholar 

  13. Cybenko, G., Approximation by superposition of a sigmoidal function,Math. Control Signals Systems 2(2) (1989), 303–315.

    Google Scholar 

  14. Funahashi, K.-I., On the approximate realization of continuous mappings by neural networks,Neural Networks 2(3) (1989), 183–192.

    Google Scholar 

  15. Hornik, K., Stinchcombe, M., and White, A., Multilayer feedforward fetworks are universal approximators,Neural Networks 2(5) (1989), 359–366.

    Google Scholar 

  16. Poggio, T. and Girosi, F., Regularization algorithm for learning that are equivalent to multilayer networks,Science 247 (1990), 978–982.

    Google Scholar 

  17. Bassi, D.F., Connectionist dynamic control of robot manipulators, PhD. dissertation, University of Southern California, Los Angeles, December 1990.

    Google Scholar 

  18. 80170NW Electrically Trainable Analog Neural Network, Data sheet of INTEL, March 1990.

  19. BALBOA 860 Coprocessor Board, Data sheet of HNC, 1991.

  20. DeWeerth, S., Nielsen, L., Mead, C., and Astrom, K., A neuron-based pulse servo for motion control,Proc. 1990 IEEE Internat. Conf. Robot. Automat., Cincinnati, May 1990, pp. 1698–1703.

  21. Mead, C.,Analog VLSI and Neural Systems, Addison-Wesley, Reading, Mass, 1989.

    Google Scholar 

  22. Farhat, N.H., Psaltis, D., Prato, A., and Peak, E., Optical implementation of the Hopfield model,Applied Optics, vol. 24, May 1985, pp. 1469–1475.

    Google Scholar 

  23. Reyneri, L.M. and Filippi, E., An analysis on the preformance of silicon implementations of backpropagation algorithms for artificial neural networks,IEEE Trans. Computers 40(12) (1991), 1380–1389.

    Google Scholar 

  24. Murray, A.F. and Smith, A.V.W., Asynchronous VLSI neural networks using pulse-stream arithmetic,IEEE J. Solid State Circuits 23(3) (1988), 688–697.

    Google Scholar 

  25. Treleaven, P., Pacheco, M., and Vellasco, M., VLSI architectures for neural networks, inLecture Notes in Computer Science 412, Springer-Verlag, Berlin, pp. 244–266.

  26. Narendra, K.S. and Partasarathy, K., Identification and control of dynamical systems using neural networks,IEEE Trans. Neural Networks 1(1) (1990), 4–27.

    Google Scholar 

  27. Polycarpou, M.M. and Ioannou, P., Identification and control of nonlinear systems using neural network models: Design and stability analysis, USC Technical Report91-09-01, September 1991.

  28. Sanner, R.M. and Slotine, J.J., Stable adaptive control and recursive identification using radial Gaussian networks,Proc. 30th IEEE CDC, Brighton, December 1991, vol. 3, pp. 2116–2123.

    Google Scholar 

  29. Werbos, P.J., An overview of neural networks for control,Proc. 1990 Amer. Control Conf., San Diego, May 1990.

  30. Werbos, P.J., Consistency of HDP applied to a simple reinforcement learning problem,Neural Networks 3 (1990), 179–189.

    Google Scholar 

  31. Kung, S.-Y. and Hwang, J.-N., Neural network architectures for robotic applications,IEEE Trans. Robot. Automat. 5(5) (1989), 641–657.

    Google Scholar 

  32. Jorgensen, C.C., Neural network representation of sensor sraphs for autonomous robot navigation,Proc. 1st Internat. Conf. Neural Networks, San Diego, June 1987, pp. 507–515.

  33. Kung, S.-Y. and Hwang, J.-N, Parallel architectures for artificial neural networks,Proc. 1st Internat. Conf. Neural Networks, San Diego, June 1987, pp. 165–172.

  34. Zhou, Y.T. and Chellapa, R., Stereo matching using a neural network,Proc. IEEE ICASSP'88, New York, April 1988, pp. 940–943.

  35. Shen, W., Shen, J., and Lallemand, J.P., Finding the shortest path by use of neural networks,Proc. 5th Internat. Conf. Adv. Robot. Pisa, June 1991, pp. 1164–1169.

  36. Miller, W.T.: Sensor-based control of manipulation robots using a general learning algorithm,IEEE J. Robot. Automat. RA-3 (1987), 157–165.

    Google Scholar 

  37. Kuperstein, M., Adaptive visual-motor coordination in multijoint robots using parallel architecture,Proc. 1987 IEEE Internat. Conf. Robot. Automat., Raleigh, March 1987, pp. 1595–1601.

  38. Kuperstein, M. and Rubinstein, J., Implementation of an adaptive neural controller for sensorymotor coordination,IEEE Control Systems Magazine 9(3) (1989), 25–30.

    Google Scholar 

  39. Harashima, F., Hashimoto, H., and Kubota, T., Sensor based robot control systems,Proc. IEEE Internat. Workshop Intell. Motion Control, Istanbul, August 1990.

  40. Kawato, M., Furukawa, K., and Suzuki, R., A hierarchical neural network model for control and learning of voluntary movement,Biological Cybernetics 57 (1987), 169–185.

    Google Scholar 

  41. Psaltis, D., Sideris, A., and Yamamura, A., A hierarchical model for voluntary movement and its application to robotics,Proc. 1st IEEE Internat. Conf. Neural Networks, San Diego, 1987, pp. 551–558.

  42. Horne, B., Jamshidi, M., and Vadiee, N., Neural networks in robotics: A survey,J. Intell. Robot. Systems 3(1) (1990), 51–66.

    Google Scholar 

  43. Vukobratović, M., Stokić, D., and Kirćanski, N.,Non-Adaptive and Adaptive Control of Manipulation Robots, Springer-Verlag, Berlin, 1985.

    Google Scholar 

  44. Arimoto, S., Kawamura, S., and Miyazaki, F., Bettering operation of robots by learning,J. Robot. Systems 1 (1984), 123–140.

    Google Scholar 

  45. Sadegh, N., Horowitz, R., Kao, W.-W., and Tomizuka, M., A unified approach to design of adaptive and repetitive controllers for robotic manipulators,Proc. USA-Japan Sympos. Flexible Automat. Minneapolis, 1988, pp. 223–231.

  46. Oh, S.R., Bien, Z., and Suh, I.H., An iterative learning control method with application for the robot manipulators,IEEE J. Robot. Automat. 4(5) (1988), 498–507.

    Google Scholar 

  47. Atkeson, C.G. and Reinkensmeyer, D.J., Using associative-addressable memories to control robots,Proc. 1989 IEEE Internat. Conf. Robot. Automat., Scottsdale, May 1989, pp. 1859–1864.

  48. Ahmad, Z. and Guez, A., On the solution to the inverse kinematic problem,Proc. 1990 IEEE Internat. Conf. Robot. Automat., Cincinnati, May 1990, 1692–1697.

  49. Barhen, J., Gulati, S., and Zak, M., Neural learning of constrained nonlinear transformations,IEEE Computer (June 1989), 67–76.

  50. Jordan, M.I., Supervised learning and systems with excess degrees of freedom, COINS Technical Report 88-27, MIT, May 1988.

  51. Josin, G., Chartney, D., and White, D., Robot control using neural networks,Proc. IEEE Internat. Conf. Neural Networks, San Diego, July 1988, pp. 625–631.

  52. Eckmiller, R., Neural network mechanisms for generation and learning of motor programs,Proc. IEEE Internat. Conf. Neural Networks, San Diego, June 1987, pp. 545–550.

  53. Tsutsumi, K. and Matsumoto, H., Neural computation and learning strategy for manipulator position control,Proc. IEEE Internat. Conf. Neural Networks, San Diego, June 1987, pp. 539–544.

  54. Chen, C.L.P. and McAulay, A.D., Robot kinematics learning computations using polynomial neural networks,Proc. 1991 IEEE Internat. Conf. Robot. Automat., Sacramento, May 1991, pp. 2638–2643.

  55. Ivakhnenko, A.G., The group method of data handling in prediction problems,Soviet Automat. Control 9(6) (1976), 21–30.

    Google Scholar 

  56. Guo, J. and Cherkassky, V., A solution to the inverse kinematic problem in robotics using neural network processing,Proc. IEEE Internat. Joint Conf. Neural Networks, Washington, June 1989, pp. 299–304.

  57. Elsey, R.K., A learning architecture for control based on backpropagation neural network,Proc. IEEE Internat. Conf. Neural Networks, San Diego, July 1988, pp. 587–594.

  58. Yeung, D.-Y. and Bekey, G.A., Using a contex-sensitive learning network for robot arm control,Proc. 1989 IEEE Internat. Conf. Robot. Automat., Scottsdale, May 1989, pp. 1441–1447.

  59. Gardner, J.F., Brandt, A., and Luecke, G., Applications of neural networks for trajectory control of robots,Proc. 5th Internat. Conf. Adv. Robot., Pisa, June 1991, pp. 487–492.

  60. Miller, W.T., Glanz, F.H., and Kraft, L.G., CMAC: An associative neural network alternative to backpropagation,Proc. IEEE 78(10) (1990), 1561–1567.

    Google Scholar 

  61. Geng, Z. and Haynes, L., Neural network solution for the forward kinematics problem of a Stewart platform,Proc. 1991 IEEE Internat. Conf. Robot. Automat., Sacramento, May 1991, pp. 2650–2655.

  62. Miller, W.T., Hewes, R.P., Glanz, F.H., and Kraft, L.G., Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller,IEEE Trans. Robot. Automat. 6 (1990), 1–9.

    Google Scholar 

  63. Ritter, H., Martinetz, T., and Schulten, K., Topology-conserving maps for learning visuomotor coordination,Neural Netwoks 2 (1988), 159–168.

    Google Scholar 

  64. Martinetz, T., Ritter, H., and Schulten, K., Three-dimensional neural net for learning visuomotor coordination of a robot arm,IEEE Trans. Neural Networks 1(1) (1990), 131–136.

    Google Scholar 

  65. Kieffer, S., Morellas, V., and Donath, M., Neural network learning of the inverse kinematic relationship for a robot arm,Proc. 1991 IEEE Internat. Conf. Robot. Automat., Sacramento, 1991, pp. 2418–2423.

  66. Grossberg, S. and Kuperstein, M.,Neural Dynamics of Adaptive Sensory-Motor Control: Ballistic Eye Movements, Elsevier/North-Holland, Amsterdam, 1986.

    Google Scholar 

  67. Kohonen, T., Self-organized formation of topology correct feature maps,Biol. Cybernet. 43 (1982), 59–69.

    Google Scholar 

  68. Kohonen, T., Analysis of a simple self-organizing process,Biol. Cybernet. 44 (1982), 135–140.

    Google Scholar 

  69. Krose, B.J.A., van der Korst, M.J., and Groen, F.C.A., Learning strategies for a vision based neural controller for a robot arm,Proc. IEEE Internat. Workshop Intell. Motion Control, Istanbul, August 1990, pp. 199–203.

  70. Asada, H., Teaching and learning of compliance using neural nets: Representation and generation of neural compliance,Proc. 1990 IEEE Internat. Conf. Robot. Automat., Cincinnati, May 1990, pp. 1237–1244.

  71. Liu, H., Iberall, T., and Bekey, G.A., Neural network architecture for robot hand control,IEEE Control Systems Magazine (April 1989), pp. 38–43.

  72. Hanes, M.D., Ahalt, S.C., Mirza, K., and Orin, D.E., Neural network control of force distribution for power grasp,Proc. 1991 IEEE Internat. Conf. Robot. Automat., Sacramento, 1991, pp. 746–751.

  73. Fukuda, T., Shibata, T., Tokita, M., and Mitsuoka, T., Adaptation and learning by neural network for robotic manipulator,Proc. IMACS Internat. Sympos. Math. Intell. Models in System Simulation, Brussels, September 1990.

  74. Sperduti, A. and Starita, A., Hand control by a neural network using tactile and positional information,Proc. 5th Internat. Conf. Adv. Robot., Pisa, June 1991, pp. 1747–1751.

  75. Miyamato, H., Kawato, M., Setoyama, T., and Suzuki, R., Feedback-error-learning neural network for trajectory control of a robotic manipulator,Neural Networks 1 (1988), 251–265.

    Google Scholar 

  76. Kawato, M., Uno, Y., Isobe, R., and Suzuki, R., Hierarchical neural network model for voluntary movement with application to robotics,IEEE Control Systems Magazine 57 (1987), 169–185.

    Google Scholar 

  77. Guez, A. and Selinsky, J., Neurocontroller design via supervised and unsupervised learning,J. Intell. Robot. Systems 2 (2 and 3) (1989), 307–335.

    Google Scholar 

  78. Katić, D., Connectionist learning models for intelligent control of manipulation robots,Proc. IMACS Internat. Sympos. Math. Intell. Models in System Simulation, Brussels, September 1990.

  79. Goldberg, K. and Pearlmutter, B., Using a neural network to learn the dynamics of the CMU direct-drive arm II, Technical Report CMU-CS-88-160, Carnegie Mellon University, Pittsburgh, August 1988.

    Google Scholar 

  80. Kosmatopoulos, E.B., Chassiakos, A.K., and Christodoulou, M.A., Robot identification using dynamical neural networks,Proc. 30th IEEE CDC, Brighton, December 1991, vol. 3, pp. 2934–2935.

  81. Ozaki, T., Suzuki, T., Furuhashi, T., Okuma, S., and Uchikawa, Y., Trajectory control of robotic manipulators using neural networks,IEEE Trans. Industrial Electronics 38(3) (1991), 195–202.

    Google Scholar 

  82. Bassi, D.F. and Bekey, G.A., Decomposition of neural networks models of robot dynamics: A feasibility study, in Wade Webster (ed.).Simulation and AI, 1989, vol. 20, The Society for Computer Simulation International, 1989, pp. 8–13.

  83. Katić, D. and Vukobratović, M., Decomposed connectionistarchitecture for fast and robust learning of robot dynamics,Proc. 1992 IEEE Internat. Conf. Robot. Automat., Nice, May 1992.

  84. Psaltis, D., Sideris, A., and Yamamura, A.A., A multilayered neural network controller,IEEE Control Systems Magazine 8(2) (1988), 17–21.

    Google Scholar 

  85. Saerens, M. and Soquet, A.; Neural controller based on back-propagation algorithm,IEE Proc. F,138(1) (February 1991).

  86. Chen, V.C. and Pao, Y.-H., Learning control with neural networks,Proc. 1989 IEEE Internat. Conf. Robot. Automat., Scottsdale, 1989, pp. 1448–1453.

  87. Jordan, M.I., Generic constraints on underspecified target trajectories,Proc. Internat. Joint. Conf. Neural Networks, Washington, 1989, pp. 217–225.

  88. Nguyen, D. and Widrow, B., Neural networks for self-learning control systems,IEEE Control Systems Magazine 10(3) (1990), 18–23.

    Google Scholar 

  89. Guglielmetti, P. and Longchamp, R., Real-time identification of a robot manipulators using a ‘Neural network’ approach,Proc. IEEE Internat. Workshop Intell. Motion Control, Istanbul, August 1990, pp. 217–222.

  90. Renders, J.-M., A new approach of adaptive neural controller design with application to robotics control,Proc. IMACS Internat. Sympos. Math. Intell. Models in System Simulation, Brussels, September 1990.

  91. Guez, A., Eilbert, J., and Kam, M., Neuromorphic architectures for fast adaptive robot control,Proc. 1988 IEEE Internat. Conf. Robot. Automat., Raleigh, April 1988, pp. 145–149.

  92. Kuperstein, M. and Wang, J., Neural controller for adaptive movements with unforeseen payloads,IEEE Trans. Neural Networks 1(1) (1990), 137–142.

    Google Scholar 

  93. Leahy Jr., M.B., Johnson, M.A., and Rogers, S.K., Neural network payload estimation for adaptive robot control,IEEE Trans. Neural Networks 2(1) (1991), 93–100.

    Google Scholar 

  94. Katić, D. and Vukobratović, M., Contribution to the indirect decentralized adaptive control of manipulation robots,J. Intell. Robot. Systems 9 (1994), 235–271.

    Google Scholar 

  95. Barto, A.G., Sutton, R.S., and Anderson, C.W., Neuron-like adaptive elements that can solve difficult learning control problem,IEEE Trans. Systems Man Cybernet. 13 (1983), 834–846.

    Google Scholar 

  96. Gullapalli, V., A stochastic reinforcement learning algorithm for learning real-valued functions,Neural Networks 3 (1990), 671–692.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Robotics Department, Mihajlo Pupin Institute, Belgrade, Yugoslavia

    Duško Katić & Miomir Vukobratović

Authors
  1. Duško Katić
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Miomir Vukobratović
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Katić, D., Vukobratović, M. Connectionist approaches to the control of manipulation robots at the executive hierarchical level: An overview. J Intell Robot Syst 10, 1–36 (1994). https://doi.org/10.1007/BF01276703

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01276703

Key words

Search

Navigation