Joint Task Offloading, Inference Optimization and UAV Trajectory Planning for Generative AI Empowered Intelligent Transportation Digital Twin

2026-04-08

AI Summary

This study addresses the fidelity–latency trade-off encountered when unmanned aerial vehicles (UAVs) perform diffusion model inference in generative AI–driven digital twins for intelligent transportation systems. To tackle this challenge, the authors formulate, for the first time, a unified framework that jointly models task offloading, generative AI inference parameter optimization, and UAV trajectory planning as a heterogeneous-agent Markov decision process. They propose a Sequentially Updated Heterogeneous-Agent Twin-Delayed Deep Deterministic Policy Gradient (SU-HATD3) algorithm, which efficiently coordinates multidimensional decisions under dynamic network conditions. The approach significantly enhances system utility and convergence speed, achieving a superior balance between the fidelity and timeliness of digital twin updates.

Abstract

To implement the intelligent transportation digital twin (ITDT), unmanned aerial vehicles (UAVs) are scheduled to process the sensing data from the roadside sensors. At this time, generative artificial intelligence (GAI) technologies such as diffusion models are deployed on the UAVs to transform the raw sensing data into the high-quality and valuable. Therefore, we propose the GAI-empowered ITDT. The dynamic processing of a set of diffusion model inference (DMI) tasks on the UAVs with dynamic mobility simultaneously influences the DT updating fidelity and delay. In this paper, we investigate a joint optimization problem of DMI task offloading, inference optimization and UAV trajectory planning as the system utility maximization (SUM) problem to address the fidelity-delay tradeoff for the GAI-empowered ITDT. To seek a solution to the problem under the network dynamics, we model the SUM problem as the heterogeneous-agent Markov decision process, and propose the sequential update-based heterogeneous-agent twin delayed deep deterministic policy gradient (SU-HATD3) algorithm, which can quickly learn a near-optimal solution. Numerical results demonstrate that compared with several baseline algorithms, the proposed algorithm has great advantages in improving the system utility and convergence rate.

Problem

• Task Offloading
• Inference Optimization
• UAV Trajectory Planning
• Digital Twin
• Generative AI

Innovation

• Generative AI
• Diffusion Model Inference
• UAV Trajectory Planning
• Task Offloading
• Heterogeneous-Agent Reinforcement Learning