| || Controlling a Mobile Robot with a Biological Brain
Author : Warwick, Kevin;Xydas, Dimitris;Nasuto, Slawomir J.;Becerra, Victor M.;Hammond, Mark W.;Downes, Julia H.;Marshall, Simon;Whalley, Benjamin J.
Source : Defence Science Journal ; Vol:60(1) ; 2010 ; pp 005-014
Subject : Computer Science;Computer Networks;Defence Science Journal
Keywords : Mobile Robot;Machine Learning;Neural Network;Biological Neuronal Networks;Intelligent Controlling Mechanism;Biological Neurons
Abstract : The intelligent controlling mechanism of a typical mobile robot is usually a computer system. Some recent research is ongoing in which biological neurons are being cultured and trained to act as the brain of an interactive real world robotthereby either completely replacing, or operating in a cooperative fashion with, a computer system. Studying such hybrid systems can provide distinct insights into the operation of biological neural structures, and therefore, such research has immediate medical implications as well as enormous potential in robotics. The main aim of the research is to assess the computational and learning capacity of dissociated cultured neuronal networks. A hybrid system incorporating closed-loop control of a mobile robot by a dissociated culture of neurons has been created. The system is flexible and allows for closed-loop operation, either with hardware robot or its software simulation. The paper provides an overview of the problem area, gives an idea of the breadth of present ongoing research, establises a new system architecture and, as an example, reports on the results of conducted experiments with real-life robots.