How does context allow control of the visual process to make it tractable, while at the same time allowing for enough richness to detect unexpected events? Traditional formal models in AI have not had enough richness, but recent progress on reasoning under uncertainty shows promise in terms of contours, appearance, components etc. What is the best possible model to interact with the environment, which subsequently can be observed by the perception system. In addition the system has facilities for communication with the environment through which it also can articulate its knowledge.

The relation between reasoning, interpretation, recognition and processing of basic information cues is another fundamental problem studied. One important part of generation of models is the ability not only to REcognize objects, but also to perform recognition by means of categorisation. The system is embedded in the world and interacts with its environment to gather knowledge and perform its mission. The sheer amount of information available in the external environment calls for methods to generate abstract models. basic quality of memory is also forgetting or intelligent garbage collection methods.

Cognition is not passive process, where an observer merely is monitoring an external environment. For instance, is chair stable enough to allow sitting down? Some of these qualities can only be determined by interaction. Categorical perception is, however, major challenge as is seen on in the adjacent image. Finally Piaget inspired model of skill and task acquisition is being implemented as basis for teaching robot like creatures to interact with the environment to determine if an object qualifies for particular task.

This is nontrivial task. Inherently memory is limited and there is need to consider how memory can be utilized for different purposes context information, spatial layout, abstraction, etc. Can such models be directly applied can we endow the system with curiosity or can be rephrase these methods so as to make them operational and applicable for artificial cognitive systems. The concepts outlined above are fundamental questions addressed in the EU project cognitive vision systems in which issues related to categorisation, recognition, learning, interpretation and integration in relation to vision systems for intelligent embodied systems.