Abstract
This paper presents a review of self-organizing feature maps (SOFMs), in particular, those based on the Kohonen algorithm, applied to adaptive modeling and control of robotic manipulators. Through a number of references we show how SOFMs can learn nonlinear input–output mappings needed to control robotic manipulators, thereby coping with important robotic issues such as the excess degrees of freedom, computation of inverse kinematics and dynamics, hand–eye coordination, path-planning, obstacle avoidance, and compliant motion. We conclude the paper arguing that SOFMs can be a much simpler, feasible alternative to MLP and RBF networks for function approximation and for the design of neurocontrollers. Comparison with other supervised/unsupervised approaches and directions for further work on the field are also provided.
Similar content being viewed by others
References
Alhoniemi, E., Hollmén, J., Simula, O., and Vesanto, J.: 1999, Process monitoring and modeling using the self-organizing map, Integrated Comput. Aided Engrg. 6(1), 3–14.
AraÚjo, A. F. R. and Barreto, G. A.: 2002, Context in temporal sequence processing: A selforganizing approach and its application to robotics, IEEE Trans. Neural Networks 13(1), 45–57.
Arras, M. K., Protzel, P. W., and Palumbo, D. L.: 1992, Automatic learning rate adjustment for selfsupervising autonomous robot control, in: K. Schuster (ed.), Applications of Neural Networks, VCH Verlag, Weinheim.
Balakrishnan, S. N. and Weil, R. D.: 1996, Neurocontrol: A literature survey, Math. Comput. Modelling 23(1/2), 101–107.
Barreto, G. A. and AraÚjo, A. F. R.: 2001a, Time in self-organizing maps: An overview of models, Internat. J. Comput. Res. 10(2), 139–179.
Barreto, G. A. and AraÚjo, A. F. R.: 2001b, A self-organizing NARX network and its application to prediction of chaotic time series, in: Proc. of the IEEE-INNS Internat. Joint Conf. on Neural Networks (IJCNN'01), Vol. 3, Washington, DC, pp. 2144–2149.
Barreto, G. A. and AraÚjo, A. F. R.: 2002, Temporal associative memory and function approximation with the self-organizing map, in: IEEE Workshop on Neural Networks for Signal Processing, IEEE Press, New York.
Behera, L., Gopal, M., and Chaudhury, S.: 1995, Self-organizing neural networks for learning inverse dynamics of robot manipulator, in: Proc. of the IEEE/IAS Internat. Conf. on Industrial Automation and Control, pp. 457–460.
Bekey, G. A.: 1992, Robotics and neural networks, in: B. Kosko (ed.), Neural Networks for Signal Processing, Prentice-Hall, Englewood Cliffs, NJ, pp. 161–187.
Bernstein, N. A.: 1967, The Coordination and Regulation of Movements, Pergamon Press, Oxford.
Buessler, J.-L. and Urban, J.-P.: 1998, Visually guided movements: Learning with modular neural maps in robotics, Neural Networks 11(7/8), 1395–1415.
Buessler, J. L., Kara, R., Wira, P., Kihl, H., and Urban, J. P.: 1999, Multiple self-organizing maps to facilitate the learning of visuo-motor correlations, in: Proc. of the IEEE Internat. Conf. on Systems, Man, and Cybernetics, Vol. III, Tokyo, Japan, pp. 470–475.
Bullock, D. and Grossberg, S.: 1988, Neural dynamics of planned arm movements: Emergent invariants and speed-accuracy properties during trajectory formation, Psycholog. Review 95, 49–90.
Bullock, D., Grossberg, S., and Guenther, F.: 1993, A self-organizing neural model of motor equivalent reaching and tool use by a multijoint arm, J. Cognitive Neurosci. 5(4), 408–435.
Carpenter, G. A., Grossberg, S., and Rosen, D. B.: 1991, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Networks 4, 759–771.
Cervera, E., Pobil, A. P., Marta, E., and Serna, M. A.: 1996, Perception-based learning for motion in contact in task planning, J. Intelligent Robotic Systems 17(3), 283–308.
Cimponeriu, A. and Kihl, H.: 1998, Intelligent control with the growing competitive linear local mapping neural network for robotic hand–eye coordination, in: Proc. of the 2nd Internat. Conf. on Knowledge-based Intelligent Electronic Systems (KES'98), Vol. 3, Adelaide, Australia, pp. 46–52.
Cohen, M. A. and Grossberg, S.: 1983, Absolute stability of global pattern formation and parallel memory storage by competitive neural networks, IEEE Trans. Systems Man Cybernet. 13, 815–826.
Coiton, Y., Gilhodes, J. C., Velay, J. L., and Roll, J. P.: 1991, A neural network model for the intersensory coordination involved in goal-directed movements, Biological Cybernet. 66, 167–176.
Cottrell, M.: 1998, Theoretical aspects of the SOM algorithm, Neurocomputing 21, 119–138.
Craig, J. J.: 1989, Introduction to Robotics: Mechanics and Control, 2nd ed., Addison-Wesley, Reading, MA.
Cruse, H., Wischmeyer, E., Brüwer, M., Brockfeld, P., and Dress, A.: 1990, On the cost functions for the control of the human arm movement, Biological Cybernet. 62, 519–528.
de Angulo, V. R. and Torras, C.: 1996, Automatic recalibration of a space robot: An industrial prototype, in: Proc. of the Internat. Conf. on Artificial Neural Networks (ICANN'96), Bochum, Germany, pp. 635–640.
de Angulo, V. R. and Torras, C.: 1997, Self-calibration of a space robot, IEEE Trans. Neural Networks 8(4), 951–963.
Delgado, A.: 2000, Control of nonlinear systems using a self-organising neural network, Neural Comput. Appl. 9(2), 113–123.
DeMers, D. and Kreutz-Delgado, K.: 1996, Canonical parameterization of excess motor degrees of freedom with self-organizing maps, IEEE Trans. Neural Networks 7(1), 43–55.
Deo, A. S. and Walker, I. D.: 1995, Overview of damped least-squares methods for inverse kinematics of robot manipulators, J. Intelligent Robotic Systems 14(1), 43–68.
Faldella, E., Fringuelli, B., Passeri, D., and Rosi, L.: 1997, A neural approach to robotic haptic recognition of 3-d objects based on a Kohonen self-organizing feature map, IEEE Trans. Industr. Electronics 44(2), 267–269.
Flash, T. and Hogan, N.: 1995, Optimization principles in motor control, in: M. A. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, MA, pp. 682–685.
Gaudiano, P. and Grossberg, S.: 1991, Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories, Neural Networks 4, 147–183.
Glasius, R., Komoda, A., and Gielen, S.: 1996, A biologically inspired neural net for trajectory formation and obstacle avoidance, Biological Cybernet. 84, 511–520.
Golnazarian, W. and Hall, E. L.: 2000, Intelligent industrial robots, in: R. L. Shell and E. L. Hall (eds), The Handbook of Industrial Automation, Marcel Dekker, New York.
Grossberg, S.: 1988, Nonlinear neural networks: Principles, mechanisms, and architectures, Neural Networks 1, 17–61.
Grossberg, S. and Kuperstein, M.: 1986, Neural Dynamics of Adaptive Sensory-Motor Control, Elsevier, Amsterdam.
Heikkonen, J. and Koikkalainen, P.: 1997, Self-organization and autonomous robots, in: O. Omidvar and P. van der Smagt (eds), Neural Systems for Robotics, Academic Press, New York, pp. 297–337.
Hesselroth, T., Sarkar, K., van der Smagt, P., and Schulten, K.: 1994, Neural network control of a pneumatic robot arm, IEEE Trans. Systems Man Cybernet. 24(1), 28–38.
Hunt, K. J., Sbarbaro, D., Zbikowski, R., and Gawthrop, P. J.: 1992, eural networks for control systems – A survey, Automatica 28(6), 1083–1112.
Hutchinson, S., Hager, G., and Corke, P.: 1996, A tutorial on visual servo control, IEEE Trans. Robotics Automat. 12(5), 651–670.
Jockusch, J.: 2000, Exploration based on neural networks with applications in manipulator control, Unpublished doctoral dissertation, Faculty of Technology, Neuroinformatic Group, University of Bielefeld, Bielefeld, Germany.
Jockusch, J. and Ritter, H.: 1999, An instantaneous topological mapping model for correlated stimuli, in: Proc. of the Internat. Joint Conf. on Neural Networks (IJCNN'99),Washington, pp. 529–534.
Jones, M. and Vernon, D.: 1994, Using neural networks to learn hand–eye co-ordination, Neural Computing Appl. 2, 2–12.
Kathib, O.: 1986, Real-time obstacle avoidance for manipulators and mobile robots, Internat. J. Robotics Res. 5, 90–98.
Kihl, H., Urban, J.-P., Gresser, J., and Hagmann, S.: 1995, Neural network based hand–eye positioning with a transputer-based system, in: Proc. of the Internat. Conf. on High Performance Computing and Networking, Milan, Italy, pp. 281–286.
Kohonen, T.: 1990, The self-organizing map, Proc. IEEE 78, 1464–1480.
Kohonen, T.: 1997, Self-Organizing Maps, 2nd extended ed., Springer, Berlin/Heidelberg.
Kohonen, T., Oja, E., Simula, O., Visa, A., and Kangas, J.: 1996, Engineering applications of the self-organizing map, Proc. IEEE 84(10), 1358–1384.
Kosko, B.: 1990, Unsupervised learning in noise, IEEE Trans. Neural Networks 1(1), 44–57.
Kung, S.-Y. and Hwang, J.-N.: 1989, Neural network architectures for robotic applications, IEEE Trans. Robotics Automat. 5(5), 641–657.
Kuperstein, M.: 1991, INFANT neural controller for adaptive sensory-motor coordination, Neural Networks 4, 131–145.
Kuperstein, M. and Rubistein, J.: 1989, Implementation of an adaptive neural controller for sensory-motor coordination, IEEE Control Systems Mag. 9(3), 25–30.
Martinetz, T. M. and Schulten, K. J.: 1991, A “neural-gas” network learns topologies, in: T. Kohonen, K. Makisara, O. Simula, and J. Kangas (eds), Artificial Neural Networks, North-Holland, Amsterdam, pp. 397–402.
Martinetz, T. and Schulten, K.: 1993, A neural network for robot control: Cooperation between neural units as a requirement for learning, Comput. Electrical Engrg. 19(4), 315–332.
Martinetz, T. and Schulten, K.: 1994, Topology representing networks, Neural Networks 7(3), 507–522.
Martinetz, T. M., Ritter, H. J., and Schulten, K. J.: 1990, Three-dimensional neural net for learning visuomotor coordination of a robot arm, IEEE Trans. Neural Networks 1(1), 131–136.
Massone, L. L. E.: 1995, Sensorimotor learning, in: M. A. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, MA, pp. 860–864.
Medler, D. A.: 1998, A brief history of connectionism, Neural Computing Surveys 1, 61–101.
Menzel, R., Woelfl, K., and Pfeiffer, F.: 1993, The development of a hydraulic hand, in: Proc. of the 2nd Conf. on Mechatronics and Robotics, Duisburg/Moers, Germany, pp. 225–238.
Miller, W. T., Sutton, R. S., and Werbos, P. J.: 1990, Neural Networks for Control, MIT Press, Cambridge, MA.
Morasso, P. and Sanguineti, V.: 1995, Self-organizing body schema for motor planning, J. Motor Behavior 27(1), 52–66.
Morasso, P., Sanguineti, V., and Spada, G.: 1997, A computational theory of targeting movements based on force fields and topology representing networks, Neurocomputing 15, 411–434.
Murray, R. M., Li, Z., and Sastry, S. S.: 1994, A Mathematical Introduction to Robotics: Mechanics and Control, CRC Press, Boca Raton, FL.
Narendra, K. S. and Annaswamy, A. M.: 1989, Stable Adaptive Systems, Prentice-Hall, Englewood Cliffs, NJ.
Nehmzow, U.: 1998, Self-supervised and supervised acquisition of smooth sensory-motor competences in mobile robots, in: H. Cruse, H. Ritter, and J. Dean (eds), Prerational Intelligence in Robotics, Kluwer Academic, Dordrecht.
Prabhu, S. M. and Garg, D. P.: 1996, Artificial neural network based robot control: An overview, J. Intelligent Robotic Systems 15, 333–365.
Psaltis, D., Sideris, A., and Yamamura, A. A.: 1988, A multilayered neural network controller, IEEE Control Systems Mag. 8(2), 17–21.
Raibert, M. H. and Horn, B. K. P.: 1978, Manipulator control using the configuration space method, Industr. Robot 5, 69–73.
Ritter, H.: 1991, Learning with the self-organizing map, in: T. Kohonen, K. Makisara, O. Simula, and J. Kangas (eds), Artificial Neural Networks, Vol 1, North-Holland, Amsterdam, pp. 379–384.
Ritter, H.: 1993, Parametrized self-organizing maps, in: Proc. of the Internat. Conf. on Artificial Neural Networks (ICANN'93), Springer, Berlin, pp. 568–575.
Ritter, H. and Schulten, K.: 1987, Planning a dynamic trajectory via path finding in discretized phase space, in: Parallel Processing: Logic, Organization, and Technology, Vol. 253, Springer, Berlin, pp. 29–39.
Ritter, H., Martinetz, T., and Schulten, K.: 1989, Topology conserving maps for learning visuomotor coordination, Neural Networks 2, 159–168.
Ritter, H., Martinetz, T., and Schulten, K.: 1992, Neural Computation and Self-Organizing Maps: An Introduction, Addison-Wesley, Reading, MA.
Roy, A.: 2000, Artificial neural networks: A science in trouble, SIGKDD Explorations 1(2), 33–38.
Rylatt, M., Czarnecki, C., and Routen, T.: 1998, Connectionist learning in behaviour-based mobile robots: A survey, Artificial Intelligence Rev. 12, 445–468.
Sbarbaro, D. and Bassi, D.: 1995, A nonlinear controller based on self-organizing maps, in: Proc. of the IEEE Internat. Conf. on Systems, Man, and Cybernetics, Vancouver, CA, pp. 1774–1777.
Sciavicco, L. and Siciliano, B.: 2000, Modelling and Control of Robot Manipulators, 2nd edn, Springer, Berlin.
Simula, O., Ahola, J., Alhoniemi, E., Himberg, J., and Vesanto, J.: 1999, Self-organizing map in analysis of large-scale industrial systems, in: E. Oja and S. Kaski (eds), Kohonen Maps, Elsevier, Amsterdam, pp. 375–387.
Srinivasa, N. and Sharma, R.: 1997, SOIM: A self-organizing invertible map with applications in active vision, IEEE Trans. Neural Networks 8(3), 758–773.
Szepesvári, C. and Lörincz, A.: 1998, An integrated architecture for motion-control and path-planning, J. Robotic Systems 15(1), 1–15.
Torras, C.: 1995, Robot control, in: M. A. Arbib (ed.), The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, MA, pp. 820–823.
Tzafestas, S. G.: 1995, Neural networks in robot control, in: S. G. Tzafestas and H. B. Verbruggen (eds), Artificial Intelligence in Industrial Decision Making, Control and Automation, Kluwer, Dordrecht, pp. 327–387.
Vesanto, J. and Alhoniemi, E.: 2000, Clustering of the self-organizing map, IEEE Trans. Neural Networks 11(3), 586–600.
Vukobratovic, M.: 1997, How to control robots interacting with dynamic environment, J. Intelligent Robotic Systems 19(2), 119–152.
Vukobratovic, M. and Tuneski, A.: 1996, Adaptive control of single rigid robotic manipulators interacting with dynamic environment – An overview, J. Intelligent Robotic Systems 17(1), 1–30.
Walter, J.: 1996, Rapid Learning in Robotics, Cuvillier Verlag, Göttingen.
Walter, J.: 1998, PSOM network: Learning with few examples, in: Proc. of the Internat. Conf. on Robotics and Automation (ICRA'98), Leuven, Belgium, pp. 2054–2059.
Walter, J. and Ritter, H.: 1995, Investment learning with hierarchical PSOM, in: D. Touretzky, M. Mozer, and M. Hasselmo (eds), Advances in Neural Information Processing Systems 8 (NIPS'95), MIT Press, Bradford, pp. 570–576.
Walter, J. and Ritter, H.: 1996, Rapid learning with parametrized self-organizing maps, Neurocomputing 12, 131–153.
Walter, J. A. and Schulten, K. J.: 1993, Implementation of self-organizing networks for visuo-motor control of an industrial robot, IEEE Trans. Neural Networks 4(1), 86–95.
Wu, C. M., Jiang, B. C., and Wu, C. H.: 1993, Using neural networks for robot positioning control, Robotics Comput.-Integrated Manufacturing 10(3), 153–168.
Yang, S. X. and Meng, M.: 2001, Neural network approaches to dynamic collision-free trajectory generation, IEEE Trans. Systems Man Cybernet. B 31(3), 302–318.
Zeller, M., Wallace, K. R., and Schulten, K.: 1995, Biological visuo-motor control of a pneumatic robot arm, in: Dagli, Akay, Chen, Fernandez, and Gosh (eds), Intelligent Engineering Systems through Artificial Neural Networks, ASME Press, New York, pp. 645–650.
Zeller, M., Sharma, R., and Schulten, K.: 1996, Topology representing network for sensor-based robot motion planning, in: Proc. of the World Congress on Neural Networks (WCNN'96), San Diego, CA, pp. 100–103.
Zeller, M., Sharma, R., and Schulten, K.: 1997, Motion planning of a pneumatic robot using a neural network, IEEE Control Systems Mag. 17, 89–98.
Zomaya, A. Y. and Nabhan, T. M.: 1994, Trends in neuroadaptive control for robot manipulators, in: R. Dorf and A. Kusiak (eds), Handbook of Design, Manufacturing and Automation, Wiley, New York, pp. 889–917.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
de A. Barreto, G., Araújo, A.F.R. & Ritter, H.J. Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators. Journal of Intelligent and Robotic Systems 36, 407–450 (2003). https://doi.org/10.1023/A:1023641801514
Issue Date:
DOI: https://doi.org/10.1023/A:1023641801514