A New Approach to Task Segmentation in Mobile Robots by mnSOM

Proposed is a new task segmentation method in navigation of mobile robots by a modular network SOM (mnSOM). mnSOM is an extension of SOM in that a function module instead of a vector unit is used to increase its representation capability. It has the ability of both segmentation and interpolation. During learning, modules in mnSOM compete with each other to become an expert for a subset of data. To increase temporal continuity of winner modules, winner decision algorithms using an MSE based threshold are proposed to improve standard mnSOM. We also propose methods for labeling modules based on MSE. The resulting mnSOM demonstrates good segmentation performance of 89.3% for a novel dataset.

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

[2]  Stefano Nolfi,et al.  Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems , 1998, Neural Networks.

[3]  K. Tokunaga.  Modular network SOM : Extension of SOM to the realm of function space , 2003 .

[4]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[5]  Tetsuo Furukawa,et al.  Generalized Self-Organizing Maps (mnSOM) for Dealing with Dynamical Systems , 2004 .

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

[7]  T. Furukawa,et al.  Modular network SOM (mnSOM): from vector space to function space , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[8]  Jean-Arcady Meyer,et al.  Learning to Perceive the World as Articulated: An Approach for Hierarchical Learning in Sensory-Motor Systems , 1998 .

[9]  Klaus-Robert Müller,et al.  Annealed Competition of Experts for a Segmentation and Classification of Switching Dynamics , 1996, Neural Computation.

[10]  Jun Tani,et al.  Model-based learning for mobile robot navigation from the dynamical systems perspective , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[11]  Jun Tani,et al.  Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB , 2004, Neural Networks.

[12]  Stefano Nolfi,et al.  Extracting Regularities in Space and Time Through a Cascade of Prediction Networks: The Case of a Mobile Robot Navigating in a Structured Environment , 1999, Connect. Sci..