Advanced Image Understanding and Autonomous Systems

Abstract

The ultimate goal of most image understanding systems is to produce an unambiguous 3-D representation of the local visual environment. This representation can then be employed by robotic systems to effect some meaningful action. A great deal of research effort is concerned with the development of visual and 'manipulative' representations, and their generative processes, which allow for the effective linking of such visual perception and robotic action. Part of the motivation for this effort is the desire to develop autonomous systems. It is argued in this paper that the requirements for the development of autonomous systems are not fully compatible with the current representation-based A.I. paradigm. While this approach is ideal for the construction of goal-oriented systems which function in environments that can be speci ed a priori, it does not, and cannot, address the problems encountered when adaptive, self-determining, autonomous systems are required. It is argued that such autonomous systems must be self-organizing. The problem which then arises is how such autonomous systems can be imbued with a goal-oriented behaviour which reflects the requirements of its designer. This remains an open question.