Robot Companion: A Social-Force based approach with Human Awareness-Navigation in Crowded Environments

Gonzalo Ferrer, Anaís Garrell and Alberto Sanfeliu

Abstract—Robots accompanying humans is one of the core capacities every service robot deployed in urban settings should have. We present a novel robot companion approach based on the so-called Social Force Model (SFM). A new model of robot-person interaction is obtained using the SFM which is suited for our robots Tibi and Dabo. Additionally, we propose an interactive scheme for robot's human-awareness navigation using the SFM and prediction information. Moreover, we present a new metric to evaluate the robot companion performance based on vital spaces and comfortableness criteria. Also, a multimodal human feedback is proposed to enhance the behavior of the system. The validation of the model is accomplished throughout an extensive set of simulations and real-life experiments.


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.

Interaction with obstacles while accompanying a person: In the video below is depicted a series of examples while accompanying a person, and simultaniouly avioding static obstacles in the Barcelona Robot Lab (BRL).


Interaction with people while accompanying a person: Same setting as the one depicted on the left, but in this scenario the interaction is mainly due to walking persons near the robot.



Real experiments in the BRL using prediction information: The experiment setting is as follow, we explain each volunteer to naturally walk towards its chosen destination, each one corresponds to a crossing in the Barcelona Robot Lab (BRL).


Real experiments in the BRL without using prediction information: Same setting as the one depicted on the left, but in this scenario no prediction information is used.



Real experiments in the FME using prediction information: The environment corresponds to the Statistics Faculty (FME). The volunteers chose a destination, among two options represented as the red pylons. Prediction information is used.



Real experiments in the FME without using prediction information: The environment corresponds to the Statistics Faculty (FME). In this video, no prediction information is used and the volunteers were told to walk around without aiming to any destination, just to test the robot physical approach.


_