Planning with a functional neural network architecture

Introduces the concept of planning in an interactive environment between two systems: the challenger and the responder. The responder´s task is to produce behavior that relates to the challenger´s behavior through some response function. In this setup, we concentrate planning on the responder´s actions and use the produced plan in order to control the responder. In general, the responder is assumed to be a nonlinear system whose input-output (I/O) map may be expressed by a Volterra series. The planner uses an estimate of the challenger´s future output sequence, the response function, and a model of the responder´s I/O relation implemented through a functional artificial neural network (FANN) architecture, in order to produce the input sequence that will be applied to the responder in the future, in parallel-time with the challenger´s corresponding output sequence. The responder accepts input from the planner, which may be combined with feedback information, in order to produce an output sequence that relates to the challenger´s output sequence according to the response function. The importance of planning for the generation of smooth behavior is discussed, and the effectiveness of the planner´s implementation using neural network technology is demonstrated with an example