A Motivational Architecture to Create more Human-Acceptable Assistive Robots for Robotics Competitions

Abstract

Non-research spectators of robotic competitions perceive robot behaviors as deterministic. This perception plays a significant role in the acceptation of robots as social entities. This paper presents a motivational based architecture to generate natural autonomous robot behaviors that will help to improve the users' perception of robot's abilities. This proposal is based on Alderfer's simplification of Maslow's hierarchy of needs. A customized version of the ability test Speech Recognition & Audio Detection Test from the RoboCup competition has been implemented to illustrate how this architecture works. We discuss and analyze how the motivational variables affect the robot behaviors generated during the human-robot interaction. The preliminary tests show less deterministic robot behaviors than traditional approaches for robotic competitions.