Gerard Canal, Carme Torras, and Guillem Alenyà
Abstract: Assistive Robots have an inherent need for adapting to the user they are assisting. This is crucial for the correct development of the task, user safety, and comfort. However, adaptation can be performed in several manners. We believe user preferences are key to this adaptation. In this paper, we evaluate the use of preferences for Physically Assistive Robotics tasks in a Human-Robot Interaction user evaluation. Three assistive tasks have been implemented consisting of assisted feeding, shoe-fitting and jacket dressing, where the robot performs each task in a different manner based on the user preferences. We evaluate the ability of the users to determine which execution of the task used their chosen preferences (if any). The obtained results show that most of the users are able to successfully guess the cases where their preferences are used even when they had not observed the task before. We also observe that their satisfaction with the task improves when the chosen preferences are employed. Finally, we also analyze the user's opinions regarding assistive tasks and preferences, showing promising benefits of adapting the robot behavior to the user through preferences.
The following video shows some of the users performing the experiments, as well as the different behaviors of the robot in each task:
The following video shows how do different user preferences modify the behavior of the robot. Notice the video shows preferences which were not used in the paper. This video is supplementary and it has been added here for clarification on the different behaviors of the robot.