Touch Perception with SOM, Growing Cell Structures and Growing Grids

摘要

We have implemented four bio-inspired self-organizing haptic systems based on proprioception on a 12 d.o.f. anthropomorphic robot hand. The four systems differ in the kind of self-organizing neural network used for clustering. For the mapping of the explored objects, one system uses a Self- Organizing Map (SOM), one uses a Growing Cell Structure (GCS), one uses a Growing Cell Structure with Deletion of Neurons (GCS-DN) and one uses a Growing Grid (GG). The systems were trained and tested with 10 different objects of different sizes from two different shape categories. The generalization abilities of the systems were tested with 6 new objects. The systems showed good performance with the objects from both the training set as well as in the generalization experiments, i.e. they mapped the objects according to shape and size and discriminated individual objects. The GCS-DN system managed to evolve disconnected networks representing different clusters in the input space (small cylinders, large cylinders, small blocks, large blocks), and the generalization samples activated neurons in a proper subnetwork in all but one case.