Our work opens up several exciting avenues of research in related fields. For example, the software that we have developed has made possible interesting new approaches to computer vision and robotics.
Clearly the artificial fish is a situated virtual robot that offers a much broader range of perceptual and animate capabilities, lower cost, and higher reliability than can be expected from present-day physical robots like those described in [Maes1991b]. For at least these reasons, artificial fishes in their dynamic world can serve as a proving ground for theories that profess competence at effectively linking perception to action [Ballard1991]. To date, this thesis work has formed the basis for computer vision research--an approach termed animat vision that has been pioneered by Terzopoulos [Terzopoulos and Rabie1995, Terzopoulos1995].
The animat vision methodology employs artificial animals or animats as realistic, active observers of their dynamic world. This approach can potentially liberate a significant segment of the computer vision research community from their dependence on expensive robot hardware. It addresses the needs of scientists who are motivated to understand and ultimately reverse engineer the powerful vision systems found in higher animals. As is argued by Terzopoulos dt-ai95,
Readily available hardware systems are terrible models of biological animals. For lack of a better alternative, however, [vision scientists] have been struggling with inappropriate hardware in their ambition to understand the complex sensorimotor functions of real animals. Moreover, their mobile robots typically lack the compute power necessary to achieve real-time response within a fully dynamic world while permitting active vision research of much significance.
The artificial fishes and their habitats that we have developed are rich enough for grounding biologically inspired active vision systems as is shown by Terzopoulos and Rabie dt-rabie95. They have enabled active vision algorithms to be implemented entirely in software, thus circumventing the problems of hardware vision.
|Xiaoyuan Tu||January 1996|