Neural computation and self-organizing maps: an introduction
Neural computation and self-organizing maps: an introduction
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
Revised Papers from the International Workshop on Sensor Based Intelligent Robots
Hi-index | 0.00 |
In this article we show how an active stereo camera head canbe made to autonomously learn to fixate objects in space. Duringfixation, the system performs an initial and a correction saccade. Inthe learning phase the correction saccade is controlled by a crudepre-wired algorithm, in analogy to a mechanism surmised toexist in the brainstem. A vector-based neural network serves as theadaptive component in our system. A self-organizing fovea improvesdramatically the convergence of the learning algorithm and theaccuracy of the fixation. As a possible application we describe thevisuo-motor coordination of the camera head with an anthropomorphicrobot arm.