Modular Learning Schemes for Visual Robot Control

This chapter explores modular learning in artificial neural networks for intelligent robotics. Mainly inspired from neurobiological aspects, the modularity concept can be used to design artificial neural networks. The main theme of this chapter is to explore the organization, the complexity and the learning of modular artificial neural networks. A robust modular neural architecture is then developed for the position/orientation control of a robot manipulator with visual feedback. Simulations prove that the modular learning enhances the artificial neural networks capabilities to learn and approximate complex problems. The proposed bidirectional modular learning architecture avoids the neural networks well-known limitations. Simulation results on a 7 degrees of freedom robot-vision system are reported to show the performances of the modular approach to learn a high-dimensional nonlinear problem. Modular learning is thus an appropriate solution to robot learning complexity due to limitations on the amount of available training data, the real-time constraint, and the real-world environment.

[1]  Ling Guan,et al.  Modularity in neural computing , 1999, Proc. IEEE.

[2]  A. P. Thakoor,et al.  Neural networks for robotic control , 1988, Neural Networks.

[3]  Yasuharu Koike,et al.  PII: S0893-6080(96)00043-3 , 1997 .

[4]  Constantinos S. Pattichis,et al.  Classification capacity of a modular neural network implementing neurally inspired architecture and training rules , 2004, IEEE Transactions on Neural Networks.

[5]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[6]  James M. Bower,et al.  Computation and Neural Systems , 2014, Springer US.

[7]  Michael I. Jordan,et al.  Learning piecewise control strategies in a modular neural network architecture , 1993, IEEE Trans. Syst. Man Cybern..

[8]  Ling Guan,et al.  Modularity in neural 1 computing : Special issue on computational intelligence , 1999 .

[9]  Richard J. Duro,et al.  Biologically inspired robot behavior engineering , 2003 .

[10]  J. L. Buessler,et al.  Modular neural architectures for robotics , 2003 .

[11]  Jean-Luc Buessler,et al.  Visually guided movements: learning with modular neural maps in robotics , 1998, Neural Networks.

[12]  Peter I. Corke,et al.  A tutorial on visual servo control , 1996, IEEE Trans. Robotics Autom..

[13]  Stefano Nolfi,et al.  Duplication of Modules Facilitates the Evolution of Functional Specialization , 1999, Artificial Life.

[14]  B. Widrow,et al.  Adaptive inverse control , 1987, Proceedings of 8th IEEE International Symposium on Intelligent Control.

[15]  Enrique Castillo,et al.  Functional Networks , 1998, Neural Processing Letters.

[16]  Helge J. Ritter,et al.  Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[17]  Mitsuo Kawato,et al.  Recognition of manipulated objects by motor learning with modular architecture networks , 1991, Neural Networks.

[18]  Patrice Wira,et al.  Neural networks organizations to learn complex robotic functions , 2003, ESANN.

[19]  Günther Palm,et al.  Towards Biomimetic Neural Learning for Intelligent Robots , 2005, Biomimetic Neural Learning for Intelligent Robots.

[20]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[21]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[22]  Enrique F. Castillo,et al.  Functional networks with applications: a neural-based paradigm [Book Review] , 1999, IEEE Transactions on Neural Networks.

[23]  D M Wolpert,et al.  Multiple paired forward and inverse models for motor control , 1998, Neural Networks.