Explainable Representations of the Social State: A Model for Social Human-Robot Interactions

TL;DR

This paper introduces an explainable model for representing the social state in human-robot interactions, focusing on key concepts and signals to improve understanding and communication in complex multi-party social scenarios.

Contribution

It defines a minimal, explainable set of concepts and signals for tracking social states, organized into four cognitive domains to enhance interpretability and tractability.

Findings

Proposes a structured social state representation for HRI

Organizes social concepts into four cognitive domains

Facilitates explainability and communication in social interactions

Abstract

In this paper, we propose a minimum set of concepts and signals needed to track the social state during Human-Robot Interaction. We look into the problem of complex continuous interactions in a social context with multiple humans and robots, and discuss the creation of an explainable and tractable representation/model of their social interaction. We discuss these representations according to their representational and communicational properties, and organize them into four cognitive domains (scene-understanding, behaviour-profiling, mental-state, and dialogue-grounding).