Neural-based control of a mobile robot: A test model for merging biological intelligence into mechanical system

Abstract

The neuronal networks are considered as the origin of intelligence in organisms. In this paper, a new hybrid neurorobot system merging the biological intelligence to the artificial intelligence was created. It was based on a neuronal controller bi-directionally connected to an actual mobile robot implementing a novel vehicle which was aimed at searching objects. The modified software architecture and home-made stimulation generator were employed to support a bi-directional exchange of information between the biological and the artificial part by means of simple binomial coding/decoding schemes. Eventually, the dissociated neuronal network could be successfully employed to control an artificial agent to find the objects. And the robot performed better and better along with the times of trials in one experiment because of the short-term plasticity. A new framework was provided to investigate the biological-artificial bi-directional interfaces for the development of innovative strategies for brain-machine interaction in these simplified model systems.