Digital Twin Synchronization Over Mobile Embodied AI Network With Agentic Intelligence

2026-05-14

AI Summary

Existing digital twin synchronization frameworks struggle to maintain high-fidelity virtual representations under information-age constraints, as they fail to fully exploit the collaborative sensing and autonomous mobility capabilities of intelligent agents. This work proposes a mobile AI networking framework grounded in embodied intelligence, featuring a five-stage closed-loop workflow—mobile sensing, collaborative perception, onboard semantic processing, channel-aware mobility, and uplink transmission—and introduces a two-layer optimization algorithm. The upper layer employs dynamic matching games for efficient agent-task assignment, while the lower layer jointly optimizes bandwidth, power, and velocity through continuous resource allocation. Semantic compression is innovatively leveraged as a key mechanism to reduce latency under bandwidth limitations, complemented by a velocity-adaptive strategy that balances energy and time costs. Simulations demonstrate that the proposed approach significantly reduces synchronization error and outperforms multiple baselines, validating the efficacy of semantic communication and autonomous mobility control.

Abstract

Efficient digital twin (DT) synchronization relies on maintaining high-fidelity virtual representations with minimal age of information (AoI). However, the synergistic potential of cooperative sensing and autonomous mobility of the sensing agent remains underexplored in existing DT synchronization frameworks. In this paper, we propose an agentic AI-empowered mobile embodied AI network (MEAN) framework for DT synchronization. In the proposed hybrid architecture, the base station (BS) conducts global orchestration, while the agents autonomously execute a five-stage closed-loop workflow: move-to-sense, cooperative sensing, onboard semantic processing, channel-aware mobility, and uplink transmission. To optimize synchronization performance, we formulate a joint topology dispatching and multidimensional resource allocation problem aimed at minimizing the maximum twin deviation across regions, subject to heterogeneous sensing fidelity and energy budget constraints. To tackle this, we develop a hierarchical two-layer optimization algorithm, where the outer-layer refines multi-agent assignment via a dynamic matching game, and the inner-layer iteratively optimizes the continuous resources. Extensive simulation results verify the convergence of the proposed algorithm and demonstrate its substantial superiority over multiple baseline schemes in reducing synchronization deviation. Furthermore, the results reveal that semantic compression serves as a vital substitute for channel resources in latency reduction under constrained bandwidth, while autonomous velocity adaptation provides an essential degree of freedom for the system to navigate the fundamental energy-time trade-off.

Problem

• Digital Twin Synchronization
• Age of Information
• Mobile Embodied AI
• Cooperative Sensing
• Autonomous Mobility

Innovation

• Digital Twin Synchronization
• Mobile Embodied AI Network
• Agentic Intelligence
• Semantic Compression
• Hierarchical Optimization