Mind the Context: Continual Learning of Socially Appropriate Robot Actions via Environmental-Social Disentanglement

2026-08-13

AI Summary

This work addresses the challenge faced by social robots in domain-incremental settings, where conflating environmental and social cues impairs their ability to learn socially appropriate behaviors. To overcome this limitation, the paper proposes an Explicitly Decoupled Dual-branch (EDD) framework that explicitly separates environment-related and social knowledge during continual learning. By integrating a replay mechanism, EDD mitigates catastrophic forgetting while enabling effective knowledge retention. This approach represents the first effort to explicitly disentangle environmental and social factors in domain-incremental continual learning, significantly enhancing both learning efficiency and behavioral appropriateness across diverse indoor environments. Experimental results demonstrate that EDD consistently outperforms state-of-the-art methods across multiple indoor domains, and ablation studies confirm the efficacy of the decoupling strategy as well as its robustness to varying domain orders.

Abstract

Social robots are expected to operate across diverse environments, where similar arrangements can imply different socially appropriate actions, e.g., starting a conversation may be acceptable in a crowded home but disruptive in an office meeting. Because such norms and environments cannot all be anticipated in advance, robots require continual learning (CL) to adapt from sequential experience while retaining previously acquired knowledge. Prior work has studied CL for generating socially appropriate robot actions, but it has not addressed domain-incremental settings in which the robot incrementally encounters diverse contexts (e.g., living room, meeting room, office, hallway), where both environmental (e.g., whether the space is open or cluttered with furniture) and social cues (e.g., how people or other agents are positioned around the robot) jointly shape the appropriateness of robot actions. We address this gap with the Explicit Disentanglement Dual-Branch (EDD) framework. EDD explicitly separates environmental and social-agent related knowledge and uses replay-based rehearsal to mitigate forgetting while learning the appropriateness of robot actions (e.g., cleaning, serving, starting a conversation) across several indoor domains. Experiments show that EDD outperforms several state-of-the-art baselines, and ablation studies further evaluate different disentanglement strategies and the sensitivity to domain ordering. Our code is publicly available at https://github.com/Cambridge-AFAR/Mind-the-Context.git.

Problem

• continual learning
• socially appropriate actions
• environmental-social disentanglement
• domain-incremental learning
• social robots

Innovation

• Continual Learning
• Socially Appropriate Actions
• Environmental-Social Disentanglement
• Domain-Incremental Learning
• Replay-Based Rehearsal