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

Xiaohuan Li; Junchuan Fan; Bingqi Zhang; Rong Yu; Xumin Huang; Qian Chen

cs.LGApr 9, 2026

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

Authors: Xiaohuan Li, Junchuan Fan, Bingqi Zhang, Rong Yu, Xumin Huang, Qian Chen

Organizations: Guangxi University Key Laboratory of Intelligent Networking and Scenario System (School of Information and Communication, Guilin University of Electronic Technology), Guilin 541004, China · Research Institute of Highway Ministry of Transport, Beijing 100000, China · School of Automation, Guangdong University of Technology, Guangzhou 510006, China · School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541004, China

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.

Figures & tables

Fig. 2: The diagram of the proposed SU-HATD3 algorithm.

Panel of Figure 3 — Fig. 3: Convergence analysis under different algorithms, learning rates, and scenario scales.

Panel of Figure 4 — Fig. 4: System utility of various algorithms under different settings.

Symbol	Definition	Value (Unit)
$N$	Number of UAVs	[5,10]
$R$	Number of roadside sensors	[20,50]
$U$	Computation frequency of UAVs	[100,400] step/s
$T_{n}$	Computing resources of UAVs	$10^{6}$ step
$v_{n,t}$	Speed of UAVs	[70, 150] m/s
$s_{r}$	The amount of sensing data	[0, 24] KB

TABLE I: SIMULATION PARAMETERS

Fig. 5: Comparison of the average fidelity and average delay for 5 UAVs and 40 roadside sensors under different algorithms.

Fig. 6: UAV movement trajectory with

N

= 2,

R

= 40 (The start and end points are marked with text and red stars, respectively).

Intelligent Transportation Systems

Intelligent Transportation Systems apply sensing, communication, AI, and optimization to make transport networks safer and more efficient.

See all 297 papers

Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV
May 6, 2026Maoxin Ji, Qiong Wu, Pingyi Fan +4Trajectory Optimization Intelligent Transportation Systems
School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China · School of Information Engineering, Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications, Nanchang University, Nanchang 330031, China · Department of Electronic Engineering, State Key laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China +4
A Digital Twin Framework for Traffic-Aware UAV Pavement Monitoring in Open-Traffic Conditions
Jun 17, 2026Yamil Uchani, Grace Luna, Edwin Salcedo +1UAV Navigation Digital Twins
Department of Mechatronics Engineering, Universidad Cat´olica Boliviana “San Pablo”, Bolivia · School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom
TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs
Jul 26, 2026Muhammad Umar Farooq Qaisar, Lin Zhang, Zhen Chen +3UAV Navigation Decentralized MARL
Hangzhou International Innovation Institute of Beihang University, Hangzhou 311115, China · Hangzhou International Innovation Institute of Beihang University, Hangzhou 311115, China, the School of Automation Science and Electrical Engineering at Beihang University, Beijing 100191, China, and the State Key Laboratory of Intelligent Manufacturing Systems Technology, Beijing 100854, China · School of Intelligent Science and Engineering and the School of Transportation, Southeast University, Nanjing 211189, China +3

May 6, 2026J/K move · Enter open · S save

Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV

Maoxin Ji, Qiong Wu, Pingyi Fan, Cui Zhang+3

School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China · School of Information Engineering, Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications, Nanchang University, Nanchang 330031, China · Department of Electronic Engineering, State Key laboratory of Space Network and Communications, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China+4

Trajectory Optimization Intelligent Transportation Systems UAV Trajectory Optimization Wireless Resource Allocation LLM Request Scheduling

Open paper AskPDF arXiv

This paper investigates a multi-Unmanned Aerial Vehicle (UAV) joint base station-assisted Internet of Vehicles (IoV) task offloading system in dense urban environments. To minimize system delay and energy consumption under strict coupling constraints, the complex non-convex optimization problem is decoupled into a hierarchical execution framework. First, a sequential distributed optimization algorithm based on Second-Order Cone Programming (SOCP) is proposed to optimize the 3D flight trajectory of each UAV, ensuring adaptive network coverage. Second, a novel hybrid resource scheduling paradigm synergizing Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) is developed. Within this framework, the DRL agent dictates the initial resource allocation, while the LLM acts as a semantic macro-scheduler to rectify long-tail allocation imbalances for failed and surplus tasks. Crucially, a reward decoupling mechanism is introduced to isolate DRL training from external LLM interventions, thereby ensuring policy convergence. Finally, the task offloading ratios are precisely determined via Linear Programming (LP) within an alternating optimization loop. Simulation results demonstrate that the proposed method significantly outperforms traditional multi-agent reinforcement learning baselines in terms of task success rate and system efficiency.

Abstract

Intelligent Transportation Systems

Explore similar work

Joint Optimization of Trajectory Control, Resource Allocation, and Task Offloading for Multi-UAV-Assisted IoV

A Digital Twin Framework for Traffic-Aware UAV Pavement Monitoring in Open-Traffic Conditions

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs