Real-time tracking control using modular neural chips with on-chip learning

We employ a modular analog chip of a neural architecture with continuous-time learning in a real-time control of a prototype physical system. The novel control structure and the experiments demonstrate the capability of the modular chips in applications that enhance system performance and which achieve calibration in real-time. The chips represent a new class of reconfigurable real-time controllers which can self-adapt to regulate, steer, or track a given profile without explicit mathematical modeling.