There is often seen in the literature a disconnect between higher-level artificial intelligence and lower-level controls research. Too often, path planners do not account for the physical capabilities of the agents that will be following their paths. Similarly, the best controllers available need to be given trajectories from somewhere. This work presents a combined architecture that links a high-level cognitive model, which can handle symbolic information and make rational decisions using it, with a lower-level optimal controller for planning detailed robotic vehicle trajectories. The priorities of the cognitive model are passed to the controller in the form of a set of weights that vary the importance of terms in a cost functional. Using the calculus of variations, this cost functional is combined with the physical system dynamics and globally optimized, resulting in a full-state trajectory that is optimal with respect to the agent’s strategic goals and physical capabilities.