Apraxia of speech is a motor speech disorder in which messages from the brain to the mouth are disrupted, resulting in an inability for moving lips or tongue to the right place to pronounce sounds correctly. Current therapies for this condition involve a therapist that in one-on-one sessions conducts the exercises. Our aim is to work in the line of robotic therapies in which a robot is able to perform partially or autonomously a therapy session, endowing a social robot with the ability of assisting therapists in apraxia of speech rehabilitation exercises. Therefore, we integrate computer vision and machine learning techniques to detect the mouth pose of the user and, on top of that, our social robot performs autonomously the different steps of the therapy using multimodal interaction.

A robust perception system is crucial for natural human–robot interaction. An essential capability of these systems is to provide a rich representation of the robot’s environment, typically using multiple sensory sources. Moreover, this information allows the robot to react to both external stimuli and user responses. The novel contribution of this paper is the development of a perception architecture, which was based on the bio-inspired concept of endogenous attention being integrated into a real social robot. In this paper, the architecture is defined at a theoretical level to provide insights into the underlying bio-inspired mechanisms and at a practical level to integrate and test the architecture within the complete architecture of a robot. We also defined mechanisms to establish the most salient stimulus for the detection or task in question. Furthermore, the attention-based architecture uses information from the robot’s decision-making system to produce user responses and robot decisions. Finally, this paper also presents the preliminary test results from the integration of this architecture into a real social robot.