A Robot Hand with T-MPSOM Neural Networks in a Model of the Human Haptic System

Abstract

We have developed an 8 d.o.f. robot hand, which has been tested with two computational models of haptic perception. Each model uses a variant of the novel self-organizing neural network, the Tensor-Multiple Peak Self-Organizing Map (T-MPSOM). One of the models uses a variant of the T-MPSOM that multiplies the activity corresponding to each of the two input vectors, while the other uses a variant that sums them. The computational models were trained and tested with a set of objects consisting of hard spheres, blocks and cylinders. Both models were capable of shape categorization, and in addition, one of the models was able to discriminate individual objects. 1.