Autonomy is an extended paradigm that subsumes both control and artificial intelligence (AI) paradigms, each of which is limited by its own abstractions. Control theory has run up against the limitations of its rigorous, but sparcely applicable, mathematical framework.AIresearch has lived under the illusion that intelligence can be demonstrated in abstract symbol spaces bereft of a rich, continuous coupling to the real world. Autonomy, as a design goal, offers an arena where both control and Al paradigms must be applied—and a challenge to the viability of both as independent entities. We discuss model-based architectures in which such paradigms can be integrated. Modeling principles for development of such architectures are proposed and illustrated. Endomorphic modeling plays a fundamental role since high autonomy requires models at different levels of abstraction that are homomorphically interrelated. Benchmarks are given for levels of autonomy that arise out of the model-based architecture.