Advanced Image Understanding and Autonomous Systems 1 Current Approaches to Image Understanding

The ultimate goal of most image understanding systems is to produce an unambigu-ous 3-D representation of the local visual environment. This representation can then be employed by robotic systems to eeect some meaningful action. A great deal of research eeort is concerned with the development of visual and`manipulative' representations, and their generative processes, which allow for the eeective linking of such visual perception and robotic action. Part of the motivation for this eeort 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 speciied 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 reeects the requirements of its designer. This remains an open question. Image understanding systems, in general, and robot vision systems, in particular, are concerned with the automatic interaction between computer-based machines and their environment. This interaction is facilitated by ongoing intelligent interplay between perception, on the one hand, and action, be it navigation or manipulation, on the other. This is perhaps best characterized by the currently-popular paradigm of active vision where the sensor is actively moved through the local environment to validate and reene the interpretation the system has formed of the scene before it. Current approaches to image understanding are based, for the most part, on the assumption that, if the image understanding system is concerned with its environment, it must somehow abstract relevant information about the environment so that it can`reason' with it. These two aspects of vision, the representation of information and the processes which facilitate the abstraction of that information, form the kernel of current