ORF-MOSAIC for adaptive control of a biomimetic arm
This study is an attempt to take advantage of a cerebellar model to control a biomimetic arm. The cerebellar controller is a modified MOSAIC model which adaptively controls the arm. We call this model ORF-MOSAIC (Organized by Receptive Fields MOdular Selection And Identification for Control). The arm features a musculoskeletal model which is controlled through muscle activations by means of optimization techniques. With as few as 16 modules, we were able to control the arm in a workspace of 30×30 cm. The system was able to adapt to an external field as well as handling new objects despite delays. The discussion section suggests that there are similarities between the microzones in the cerebellum and the modules of this new model.