Human-Robot Interaction in Museum Exhibition Assembly: A Framework for Adaptive Collaboration

Abstract

Exhibition assembly in museums represents a critical phase in translating abstract curatorial concepts into tangible physical forms. Unlike structured industrial settings, museum environments are often unstructured and unpredictable, posing considerable challenges for human-robot interaction (HRI). This study proposes an adaptive collaboration framework for HRI, specifically tailored to meet the unique demands of museum exhibition assembly. The framework is structured around three core interaction mechanisms: behavioral coordination, intention sharing, and role collaboration. It addresses key challenges such as the sensitivity of cultural artifacts, environmental complexity, and the necessity of establishing trust between humans and robots. To improve collaborative accuracy, the framework incorporates hierarchical task modeling, adaptive behavior adjustment, and multimodal information exchange. For intention sharing, it introduces multidimensional situational modeling, context-aware intention inference algorithms, and perceivable feedback systems. To optimize role allocation, it employs a flexible role assignment strategy, adaptive interaction patterns, and clear role status indicators. By extending HRI research beyond industrial applications, the framework offers novel insights into collaborative systems within complex cultural contexts. Nevertheless, further empirical validation and context-specific analysis are required to fully bridge the gap between theoretical development and practical implementation.