Efficient Twin Migration in Vehicular Metaverses: Multi-Agent Split Deep Reinforcement Learning with Spatio-Temporal Trajectory Generation

2025-03-30

AI Summary

In vehicular metaverses, high vehicle mobility, dynamic RSU load fluctuations, and heterogeneous resource constraints cause excessive digital twin (VT) migration latency and service discontinuity. To address this, we propose a multi-agent hierarchical deep reinforcement learning (DRL) framework. Our approach introduces a lightweight, modular DRL architecture enabling low-overhead, real-time VT migration decisions; integrates road-network topology and historical trajectory data into a spatiotemporal trajectory generation model to enhance generalization under dynamic conditions; and jointly optimizes VT migration policies with RSU resource coordination. Experimental results demonstrate a 29% improvement in quality of experience (QoE), a 25% reduction in model parameters, and significant latency reduction—thereby ensuring continuous, immersive VT services.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Multiagent Learning
• Application Domains: Mobility, Driving & Flight

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Vehicle Twins (VTs) as digital representations of vehicles can provide users with immersive experiences in vehicular metaverse applications, e.g., Augmented Reality (AR) navigation and embodied intelligence. VT migration is an effective way that migrates the VT when the locations of physical entities keep changing to maintain seamless immersive VT services. However, an efficient VT migration is challenging due to the rapid movement of vehicles, dynamic workloads of Roadside Units (RSUs), and heterogeneous resources of the RSUs. To achieve efficient migration decisions and a minimum latency for the VT migration, we propose a multi-agent split Deep Reinforcement Learning (DRL) framework combined with spatio-temporal trajectory generation. In this framework, multiple split DRL agents utilize split architecture to efficiently determine VT migration decisions. Furthermore, we propose a spatio-temporal trajectory generation algorithm based on trajectory datasets and road network data to simulate vehicle trajectories, enhancing the generalization of the proposed scheme for managing VT migration in dynamic network environments. Finally, experimental results demonstrate that the proposed scheme not only enhances the Quality of Experience (QoE) by 29% but also reduces the computational parameter count by approximately 25% while maintaining similar performances, enhancing users' immersive experiences in vehicular metaverses.

Problem

• Optimizing Vehicle Twin migration for seamless immersive services
• Managing dynamic RSU workloads and heterogeneous resources efficiently
• Reducing latency and enhancing QoE in vehicular metaverses

Innovation

• Multi-agent split DRL for VT migration decisions
• Spatio-temporal trajectory generation algorithm
• Enhanced QoE with reduced computational parameters