Human-Centered Digital Twins: A Bidirectional WebXR-Based Architecture for Immersive Interaction

Digital twin technology has emerged as a profound paradigm for bridging physical systems and their virtual counterparts through real-time data synchronization and interactive three-dimensional visualization. However, existing digital twin platforms are predominantly domain-specific, proprietary, and reliant on dedicated software infrastructure, severely limiting accessibility, interoperability, and cross-domain applicability. This paper presents a Universal Digital Twin (UDT) framework based on open web standards that incorporates AI as an architectural component alongside immersive XR interaction through a human-centered, bidirectional architecture. The proposed five-layer framework ensures real-time synchronization between physical and virtual systems while providing a foundation for AI-assisted decision-making and enabling users to influence system behavior through AR/VR interfaces. Implemented using Three.js and WebXR, the platform supports domain-agnostic applications, optimized 3D visualization, real-time telemetry monitoring, and intelligent analytics powered by large language models, physics-informed neural networks, and reinforcement learning, all accessible through standard web browsers without specialized software. The performance of the proposed framework was evaluated using browser-based performance metrics, including Largest Contentful Paint (LCP), Interaction to Next Paint (INP), Cumulative Layout Shift (CLS), and execution profiling under different network and processing conditions. Experimental results indicate that the framework achieves fast loading times, stable rendering performance, and efficient visualization across constrained and unconstrained environments.