People's adaptive side-by-side model evolved to accompany groups of people by social robots

Journal Article (2020)


IEEE Robotics and Automation Letters







Doc link


Download the digital copy of the doc pdf document


The presented method implements a robot accompaniment in a side-by-side formation of a single person or a group of people. The method enhances our previous robot adaptive side-by-side behavior allowing the robot to accompany a group of people, not only one person, doing an adaptive side-by-side behavior. The adaptive means that the robot is capable of adjusting its motion to the behavior of the person (or people) being accompanied (in position and velocity), without bothering other pedestrians in the environment, as well as avoiding colliding with static and dynamic obstacles. Furthermore, the robot can deal with the random factor of human behavior in several situations: if other people interfere the path of the companions, the robot leaves space to one of the accompanied person by approaching the other person, but without invading any personal space; if the people of the group changes their physical position inside the group formation, the robot adapts to them dynamically by changing from the lateral position inside the formation to the central position in the formation or otherwise; the robot adapts to the velocity changes of the companions and other people that interfere in the path of the group, in magnitude and direction of the movement; the robot can deal with occlusions of one accompanied person by the other. Finally, the method has been validated using synthetic experiments and real-life experiments with our robot. Furthermore, we developed a user study comparing the method with a Wizard of Oz.



Author keywords

Mobile robotics, robot companion, social human-robot interaction, human-centered robotics

Scientific reference

E. Repiso, A. Garrell Zulueta and A. Sanfeliu. People's adaptive side-by-side model evolved to accompany groups of people by social robots. IEEE Robotics and Automation Letters, 5(2): 2387-2394, 2020.