Implementation of a Biologically Inspired Responsive Joint Attention System for a Social Robot

The concept of joint attention holds significant importance in human interaction and is pivotal in establishing rapport, understanding, and effective communication. Within social robotics, enhancing user perception and fostering a sense of natural interaction with robots becomes a central element. In this sense, emulating human-centric qualities in social robots, such as joint attention, defined as the ability of two or more individuals to simultaneously focus on a common event, can increase their acceptability. This work introduces a responsive joint attention system integrated into the social robot Mini. The system calculates the position of the user's head, body, and face orientations in real-time. With this information, the robot can perform natural movements based on the user's gaze and pointing directions. Moreover, the robot employs verbal expressions to alert the user when distractions are detected, enhancing the perception of the robot's responsiveness. This study also explores differences in user perception of the robot when the joint attention system is active. A user experiment involving an interactive gaming scenario is proposed. The results show significance in various social presence dimensions, validating the system and indicating that users discern when the joint attention system is active and perceive the robot's responsive behavior.