Humans Social Relationship Classification during Accompaniment

TL;DR

This study develops deep learning models to classify social relationships between walking pairs into four categories, demonstrating promising accuracy and potential for real-world robotic applications.

Contribution

It introduces neural network architectures for social relationship classification during accompaniment, improving upon previous results and showing potential for robot integration.

Findings

Achieved good classification accuracy

Enhanced previous study outcomes

Showed potential for real robot implementation

Abstract

This paper presents the design of deep learning architectures which allow to classify the social relationship existing between two people who are walking in a side-by-side formation into four possible categories --colleagues, couple, family or friendship. The models are developed using Neural Networks or Recurrent Neural Networks to achieve the classification and are trained and evaluated using a database of readings obtained from humans performing an accompaniment process in an urban environment. The best achieved model accomplishes a relatively good accuracy in the classification problem and its results enhance partially the outcomes from a previous study [1]. Furthermore, the model proposed shows its future potential to improve its efficiency and to be implemented in a real robot.