Integrated Techniques for Self-Organisation, Sampling, Habituation, and Motion-Tracking in Visual Robotics Applications.

Abstract

We summarise several techniques in use in our visual robotics research. Our aim is to develop robots that are thoroughly autonomous and adaptable. We describe a system that is independent of typical image derivation standards, sampling algorithms, a priori space, object, or motion models, yet is able to intelligently direct its attention to novel activity in a complex and changing environment. 1 Introduction We have developed a visual robotic system known as WRAITH, whose ultimate purpose is to follow (in the sense of both `track' and `understand') human movement, and to do so under the most unfavourable conditions, both external and internal. This is a long-term project, and this paper represents a report on the principles of design and the progress of the system so far. Our main interest lies in the improvement of performance autonomy and robustness. In addressing this challenge we have often tried to emulate the important characteristics of biological systems, but this has not pr...