Affecta-Context: The Context-Guided Behavior Adaptation Framework

TL;DR

Affecta-Context is a framework that enables social robots to adapt their behaviors based on physical context and user preferences, learned through interaction, to improve human-robot interaction quality.

Contribution

The paper introduces Affecta-Context, a novel framework that clusters physical contexts and learns behavior prioritization through human interactions, enhancing robot adaptability.

Findings

The framework successfully learned behavior prioritization over 72 interactions.

It demonstrated the ability to generalize to new, unseen physical contexts.

The approach improved the robot's behavior alignment with user preferences.

Abstract

This paper presents Affecta-context, a general framework to facilitate behavior adaptation for social robots. The framework uses information about the physical context to guide its behaviors in human-robot interactions. It consists of two parts: one that represents encountered contexts and one that learns to prioritize between behaviors through human-robot interactions. As physical contexts are encountered the framework clusters them by their measured physical properties. In each context, the framework learns to prioritize between behaviors to optimize the physical attributes of the robot's behavior in line with its current environment and the preferences of the users it interacts with. This paper illlustrates the abilities of the Affecta-context framework by enabling a robot to autonomously learn the prioritization of discrete behaviors. This was achieved by training across 72 interactions in two different physical contexts with 6 different human test participants. The paper demonstrates the trained Affecta-context framework by verifying the robot's ability to generalize over the input and to match its behaviors to a previously unvisited physical context.