Generation of autonomous behavior for robots is a general unsolved problem. Users perceive robot as repetitive tools that do not respond to dynamic situations. This research faces the generation of natural behaviors in assistive service robots for dynamic domestic environments, particularly, a motivational-oriented cognitive architecture to generate more natural behaviors in autonomous robots.
The proposed architecture, called HiMoP, is based on three elements: Hierarchy of needs to define robot drives; Set of Motivational variables connected to robot needs; and Pool of finite state machines to run robot behaviors. First element is inspired in Alderfer's hierarchy of needs, it defines the variables defined in the motivational component. The pool of finite-state machine (FSM) implements the available robot actions, and those actions are selected dynamically attending the motivational variables and the external stimuli. Thus, the robot is able to perform different behaviors even under similar conditions.
A customized version of the Speech Recognition \& Audio Detection Test, proposed by the RoboCup Federation has been used to illustrate how the architecture works and how it dynamically adapts and triggers robots behaviors attending internal variables and external stimuli
Quiz Game and Context Awareness
Trivia game between user and robot. The conversation is interrupted by a ringbell.