Adaptive selection of intelligent processing modules and its applications

In this paper we study the problem of application-based Human-Robot Interaction (ITRI). We introduce a problem called The Human State Problem (HSP) and we propose a robotic architecture that partially solves this problem. In the The Human State Problem, a robot performs a set of tasks. A user, interacts with the robot using indirect feedback. The goal of the robot is to keep a user in a desired state; in most cases this state is happy or satisfied. The indirect human feedback is used to reconfigure the robot's behavior. The behavior is generated by a selection mechanism that adaptively selects computational resources. The computational resources are then used for the processing of the current input-to-output mapping. The computational resources are selected from a pool of available intelligent processing resources that represents all available computational capacity of the robotic application. The problem defined by the HSP lays in the fact that the robotic application receives only indirect and partial human feedback. Such feedback is not sufficient for the robot to easily predict or decide what actions are the most appropriate.