Distance-Based Computational Models for Facilitating Robot Interaction with Children

David Feil-Seifer, Maja Mataric'

Abstract


Among core challenges involved in using robots as social tools in interaction scenarios are sensing and interpreting the user's activities and social behavior, monitoring the dynamics of the social context, and selecting and producing appropriate robot action. When employing social human-robot interaction, modalities of communication such as speech or gesture are commonly considered. However, interpersonal distance between people can contain significant social and communicative information. If human-robot interaction reflects this human-human interaction property, then human-robot distances also convey social information. If a robot is to be an effective social agent, its actions, including those relating to interpersonal distance, must be appropriate for the given social situation. This becomes a greater challenge in playful and unstructured interactions, such as those involving children.


This paper demonstrates the use of a model over distance-based features for the recognition and expression of spatial social behavior. This model was designed to classify averse social behavior of a child engaged in playful interaction with a robot. This model used distance-based features to autonomously identify interaction/play, avoidance, wall-hugging, and parent-proximity behavior with 94% accuracy. The same methodology was then used to model the spatial aspects of a person following a robot. This model was then used as part of a modified navigation planner to enable the robot to exhibit socially-aware goal-oriented navigation behavior. The model-based planner resulted in robot navigation behavior that was more effective at allowing a partner to follow the robot. This effect was demonstrated using quantitative measures of navigation performance and observer rating of the robot's behavior. These two uses for spatial models were implemented on complete robot systems and validated in evaluation studies with children with autism spectrum disorders and with neurotypical adults.


Keywords


Socially Assistive Robotics, Autism Spectrum Disorders, Machine Learning

Full Text:

PDF


DOI: http://dx.doi.org/10.5898/jhri.v1i1.15

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.