Transcript
A group of engineers at NUI Galway and the University of Ulster is developing integrated circuit technology that mimics the neuron structure and operation of the brain. One key goal of the research is the application of the electronic neural device, called a "hardware spiking neural network," to the control of autonomous robots which can operate independently in remote, unsupervised environments, such as remote search and rescue applications, and in space exploration.
According to Dr. Fearghal Morgan, Director of the Bio-Inspired Electronics and Reconfigurable Computing research group at NUI Galway, "Until now, the robotics arena has focused on electronic controllers which incorporate one or more microprocessors, which typically execute instructions in sequence and, while performing tasks quickly, are limited by the instruction processing speed."
The neural network that Morgan's team is developing will contain thousands of small electronic neuron-like devices that operate at the same time, as neurons do in a human brain. It interprets the robot's environment through signals received from sensing devices, such as cameras and ultrasonic sensors, which act as the eyes and ears of the robot. The neural network then changes the behavior of the robot accordingly, by sending signals to the robot's limbs to enable activities such as walking, grasping objects, and avoiding obstacles.
The network can be trained to perform a particular function, and can be retrained many times for various applications. The training process resembles the training of the brain, by making, strengthening, and weakening the links between neurons and defining the conditions which cause a neuron to fire, sending signals to all of the attached neurons. As in the brain, the collection of interconnected neurons makes decisions on incoming data to cause an action in the controlled system.
|
