Robot Social-Aware Navigation Framework to Accompany People

Gonzalo Ferrer, Anaís Garrell, Fernando Herrero and Alberto Sanfeliu

Abstract—We present a novel robot social-aware navigation framework to accompany people in crowded urban areas. This system includes people tracking, human motion prediction, social-aware navigation and interactive learning to compute their parameters. Our contributions include: first, we introduce the ``Extended Social-Force Model'' (ESFM), based on the Social Force Model, to consider the person-accompanied and robot interactions. Second, a human motion predictor is used to estimate the destination of the person being accompanied.} Third, a robot social-aware navigation model is designed, which relies on the ESFM and the people motion predictor. Fourth, an interactive learning method using multimodal human feedback is developed to compute the parameters of the social-aware navigation model. Finally, a quantitative metric based on people's personal spaces and comfortableness criteria, is designed to evaluate the performance of the robot companion task. The validation of the model is accomplished throughout an extensive set of simulations and real-life experiments. In addition, a volunteers' survey is used to measure the acceptability of our robot companion's behavior.


Videos—The following videos show the performance of our robot companion approach:

Simulation: In order to evaluate mathematically the correctness of the reactive navigation model, we have tested it in a simulated environment.


Simulation: the environment corresponds to the BRL, using two destinations.


New Robot companion while avoiding a person: In the video below is depicted a example while Dabo accompanies a person, and simultaniouly avoids a person in the scene (FME).


New Robot companion while avoiding a group of crossing people: Same setting as the one depicted on the left, but in this scenario there is a group of people in the scene.


New Robot companion while avoiding a static obstacle: The Dabo robot accompanies a person while avoids an static obstacle in the scene.


New Robot companion in a behavioral case of study: In this example, Dabo accompanies a person near a corner.


_