Bioinspired Adaptive Spiking Neural Network to Control NAO Robot in a Pavlovian Conditioning Task

The cerebellum has a central role in fine motor control and in various neural processes, as in associative paradigms. In this work, a bioinspired adaptive model, developed by means of a spiking neural network made of thousands of artificial neurons, has been leveraged to control a humanoid NAO robot in real-time. The learning properties of the system have been challenged in a classic cerebellum-driven paradigm, the Pavlovian timing association between two provided stimuli, here implemented as a laser-avoidance task. The neurophysiological principles used to develop the model, succeeded in driving an adaptive motor control protocol with acquisition and extinction phases. The spiking neural network model showed learning behaviors similar to the ones experimentally measured with human subjects in the same conditioning task. The model processed in real-time external inputs, encoded as spikes, and the generated spiking activity of its output neurons was decoded, in order to trigger the proper response with a correct timing. Three long-term plasticity rules have been embedded for different connections and with different time-scales. The plasticities shaped the firing activity of the output layer neurons of the network. In the Pavlovian protocol, the neurorobot successfully learned the correct timing association, generating appropriate responses. Therefore, the spiking cerebellar model was able to reproduce in the robotic platform how biological systems acquire and extinguish associative responses, dealing with noise and uncertainties of a real-world environment.