부산대학교 도서관

Keywords Person-following control; Human--robot social interaction; Socially acceptable robot motion; Motion human-aware robot navigation; Human--robot interactive communication Highlights * The kinematic controller, derived from a new concept of 'extended kinematic model'. * The variable gains which, depending on the relative velocities, automatically adjusts the controller behavior. * The use of proxemics to give a comfort sensation to the user. * The stability proof with the reporting of real robot's experimental results. * Subjective and objective metric assessments from the users to conclude that our social robot navigation in the person-following task is accepted. Abstract This work presents a novel stable controller for the person-following task that includes social considerations for a differential drive mobile robot equipped with an RGB-D camera and a laser range finder as main sensors. The proposed controller adapts its behavior based on the knowledge of both: a modified personal space distribution and human user velocity. Control objectives are focused hence on keeping the human user within the camera's field-of-view while the mobile robot follows it, with a socially acceptable motion through arbitrary paths. To show the good behavior of this proposal, simulation and real experimental results are included and discussed. The asymptotic stability of the overall system is proved through the Lyapunov theory. Also, in our proposal, three state-of-the-art algorithms were integrated with the controller. In particular, a new real-time multi-person skeletal tracking system is used to obtain the relative human--robot position, a text to speech algorithm is used to confirm the commands given by the human, and also, a SLAM algorithm is used to obtain the map of the environment while the main task is being performed. Additionally, a hand gesture recognition module is included to interact with the mobile robot. This way, the robot is allowed to navigate with a socially-aware behavior in environments shared with humans. Finally, subjective and objective metrics are used as a validation method for human perception about the achieved robot motion. Author Affiliation: (a) Universidad Politecnica Salesiana, Cuenca, Ecuador (b) Institute of Automatics, National University of San Juan, Argentina (c) Department of Computer Science, University of Tuebingen, 72076 Tuebingen, Germany * Corresponding author. Article History: Received 30 May 2020; Revised 10 October 2021; Accepted 28 February 2022 Byline: Julio Montesdeoca [jmontesdeoca@ups.edu.ec] (a,*), J. Marcos Toibero (b), Julian Jordan (c), Andreas Zell (c), Ricardo Carelli (b)