Affecta-Context: The Context-Guided Behavior Adaptation Framework

2025-08-07

AI Summary

This study addresses the challenge of enabling social robots to autonomously adapt their interactive behaviors in dynamic physical environments based on real-time environmental states and user preferences. To this end, we propose Affecta-Context—a novel framework integrating context-aware clustering with reinforcement learning–based behavioral priority modeling. It enables environment-feature-driven adaptive behavior selection and cross-scenario generalization. By constructing an environment–behavior associative representation, the robot dynamically parses physical context—including illumination, spatial layout, and user pose—and optimizes interaction policies in real time. We conducted 72 human–robot interaction trials across two heterogeneous physical environments. Six participants validated the system’s generalization to unseen environments and its accuracy in behavior adaptation, demonstrating significant improvements in situational consistency and user acceptance.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Facilitates behavior adaptation for social robots using context
• Learns behavior prioritization through human-robot interactions
• Enables robots to generalize behaviors to new physical contexts

Innovation

• Context-guided behavior adaptation framework
• Clusters contexts by physical properties
• Learns behavior prioritization via interactions