A SELF-ORGANIZING NEURAL NETWORK

We propose an unsupervised neural network model to learn and recall complex robot trajectories. Two cases are considered: (1) A single trajectory in which a particular arm configuration may occur more than once, and (2) trajectories sharing states with other ones – they are said to contain a shared state. Hence, ambiguities occur in both cases during recall of such trajectories. The proposed model consists of two groups of synaptic weights trained by competitive and Hebbian learning laws. They are responsible for encoding spatial and temporal features of the input sequences, respectively. Three mechanisms allow the network to deal with repeated or shared states: local and global context units, neurons disabled to learn, and redundancy. The network produces the current and the next state of the learned sequences and is able to solve ambiguities. The model is simulated over various sets of robot trajectories in order to evaluate learning and recall, trajectory sampling effects and robustness.

[1]  John J. Craig,et al.  Introduction to Robotics Mechanics and Control , 1986 .

[2]  Francis L. Merat,et al.  Introduction to robotics: Mechanics and control , 1987, IEEE J. Robotics Autom..

[3]  M. Kuperstein,et al.  Implementation of an adaptive neural controller for sensory-motor coordination , 1989, International 1989 Joint Conference on Neural Networks.

[4]  Helge J. Ritter,et al.  Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[5]  Heikki Hyötyniemi.  Locally Controlled Optimization of Spray Painting Robot Trajectories , 1990 .

[6]  H. Hyotyniemi.  Locally Controlled Optimization of Spray Painting Robot Trajectories , 1990, Proceedings of the IEEE International Workshop on Intelligent Motion Control.

[7]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[8]  Klaus Schulten,et al.  Implementation of self-organizing neural networks for visuo-motor control of an industrial robot , 1993, IEEE Trans. Neural Networks.

[9]  T. Sejnowski,et al.  The predictive brain: temporal coincidence and temporal order in synaptic learning mechanisms. , 1994, Learning & memory.

[10]  Bernhard Schölkopf,et al.  View-Based Cognitive Mapping and Path Planning , 1995, Adapt. Behav..

[11]  Ulrich Nehmzow,et al.  Route learning in mobile robots through self-organisation , 1996, Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96).

[12]  Rajesh P. N. Rao,et al.  Learning Navigational Behaviors using a Predictive Sparse Distributed Memory , 1996 .

[13]  Peter I. Corke,et al.  A robotics toolbox for MATLAB , 1996, IEEE Robotics Autom. Mag..

[14]  Jukka Heikkonen,et al.  Self-Organization and Autonomous Robots , 1997 .

[15]  Guy Wallis,et al.  Temporal Order in Human Object Recognition Learning , 1998 .

[16]  Aluizio F. R. Araújo,et al.  Fast learning of robot trajectories via unsupervised neural networks , 1999 .

[17]  Aluizio F. R. Araújo,et al.  Unsupervised Learning and Recall of Temporal Sequences: An Application to Robotics , 1999, Int. J. Neural Syst..