Human-Aware Robot Navigation Based on Learned Cost Values from User Studies

Kira Bungert, Lilli Bruckschen, Stefan Krumpen, Witali Rau, Michael Weinmann, and Maren Bennewitz
In proceedings of International Conference on Robot and Human Interactive Communication (RO-MAN), 2021
 

Abstract

In this paper, we present a new approach tohuman-aware robot navigation, which extends our previous proximity-based navigation framework [1] by introducing vis-ibility and predictability as new parameters. We derived these parameters from a user study and incorporated them into a cost function, which models the user’s discomfort with respect to a relative robot position based on proximity, visibility, predictability, and work efficiency. We use this cost function in combination with an A* planner to create a user-preferred robot navigation policy. In comparison to our previous framework, our new cost function results in a 6% increase in social distance compliance, a 6.3% decrease in visibility of the robot as preferred, and an average decrease of orientation changes of 12.6ͦ per meter resulting in better predictability, while maintaining a comparable average path length. We further performed a virtual reality experiment to evaluate the user comfort based on direct human feedback, finding that the participants on average felt comfortable to very comfortable with the resulting robot trajectories from our approach.

Bibtex

@INPROCEEDINGS{bungert-2021-RO-MAN,
     author = {Bungert, Kira and Bruckschen, Lilli and Krumpen, Stefan and Rau, Witali and Weinmann, Michael and
               Bennewitz, Maren},
      title = {Human-Aware Robot Navigation Based on Learned Cost Values from User Studies},
    journal = {International Conference on Robot and Human Interactive Communication},
  booktitle = {International Conference on Robot and Human Interactive Communication (RO-MAN)},
       year = {2021},
       note = {to appear},
   abstract = {In this paper, we present a new approach tohuman-aware robot navigation, which extends our previous
               proximity-based navigation framework [1] by introducing vis-ibility and predictability as new
               parameters. We derived these parameters from a user study and incorporated them into a cost
               function, which models the user’s discomfort with respect to a relative robot position based on
               proximity, visibility, predictability, and work efficiency. We use this cost function in combination
               with an A* planner to create a user-preferred robot navigation policy. In comparison to our previous
               framework, our new cost function results in a 6% increase in social distance compliance, a 6.3%
               decrease in visibility of the robot as preferred, and an average decrease of orientation changes of
               12.6ͦ per meter resulting in better predictability, while maintaining a comparable average path
               length. We further performed a virtual reality experiment to evaluate the user comfort based on
               direct human feedback, finding that the participants on average felt comfortable to very comfortable
               with the resulting robot trajectories from our approach.}
}