Hardware implementation of a controller based on neurobiological adaptive models of the human motor-control system

Abstract

In this work, a neural structure has been implemented into a device based on the new trends in hardware integration, for motor-control In multisensorial anthropomorphic robotic systems. This implementation gives a solution to the problem of physic integration of biologically Inspired control hierarchies in a robotic head-arm installation for robotic reaching tasks. The complete architecture has been implemented on an electronic board connected to a PC computer through a PCI interface. The hardware structure consists of two blocks: one for the working phase of the system, and the other for the learning and supervision phase of the system. These two blocks have been implemented with different technologies based on DSP processors and FPGAs. The algorithms implemented on DSPs have the function of updating the neural network on the FPGA, supervising the working of the algorithm implemented on FPGA and introducing corrections when the neural network produces results with little errors. The neural network has been implemented on FPGA and implements spatial-motor transformations of the robotic platform. It is programmed and updated by the supervisor implemented on a DSP processor