Architecture and Representations

The study of architectures to support intelligent behaviour is certainly the broadest, and arguably one of the most ill-defined enterprises in AI and Cognitive Science. The basic scientific question we seek to answer is: “What are the trade-offs between the different ways that intelligent systems might be structured?” These trade-offs depend in large part on what kinds of tasks and environment a system operates under (

niche space

), and also what aspects of the

design space

we deem to be architectural. In CoSy we have tried to answer that question in several ways. First, by thinking about the requirements on architectures that arise from our particular scenarios (parts of niche space). Second, by building systems that follow well-defined architectural rules, and using these systems to carry out experiments on variations of those rules. Third, by using the insights from system building to improve our understanding of the trade-offs between different architectural choices, i.e. between different partial designs. Our objective in CoSy has not been to come up with just another robot architecture, but instead to try to make some small steps forward in a new science of architectures.