A Hybrid Soft Asynchronous Actor–Critic Framework for UAV-Assisted IoV Task Offloading With Vehicle Trajectory Prediction
IEEE Internet of Things Journal · 15.06.2026 · 13 (12) · 27688-27701
DOI: 10.1109/jiot.2026.3680146 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.06.2026. Verfasst von Ying Yuan und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Major Science and Technology Support Program of Hebei Province.
Abstract (Originalsprache)
With the rapid increase in computing demand for the Internet of Vehicles (IoV), the limited on-board computing resources have gradually become a bottleneck restricting the efficient processing of tasks. Unmanned aerial vehicles (UAVs), with their high mobility and flexible deployment capabilities, have become an ideal platform for assisting IoV task offloading. However, the dynamic environment and the mobility of vehicles pose significant challenges for task offloading and resource allocation in UAV-assisted IoV networks. This article proposes a soft asynchronous actor–critic (SAAC) framework with vehicle trajectory prediction based on deep reinforcement learning (DRL) for UAV-assisted IoV task offloading. First, to solve the problem of poor stability of traditional multiagent DRL algorithms in dynamic environments, this article combines the asynchronous training of multiagent systems with the soft update and target network mechanism to improve the anti-interference and stability of the algorithm. Second, a module based on a recurrent neural network (RNN) integrated with a sliding window mechanism is proposed to address the uncertainty arising from vehicle mobility. This module enables precise prediction of vehicle trajectories, thereby facilitating forward-looking flight strategy planning for UAVs and reducing task transmission delays. Simulation results show that the proposed algorithm is effective, and therefore, this article provides a new framework for the UAV-assisted IoV task offloading.
Förderung
- Major Science and Technology Support Program of Hebei Province
Zitieren
APA
Yuan, Y., Zhu, P., Wang, C., Li, G., & Yao, Z. (2026). A Hybrid Soft Asynchronous Actor–Critic Framework for UAV-Assisted IoV Task Offloading With Vehicle Trajectory Prediction. IEEE Internet of Things Journal, 13(12), 27688-27701. https://doi.org/10.1109/jiot.2026.3680146
Vancouver
Yuan Y, Zhu P, Wang C, Li G, Yao Z. A Hybrid Soft Asynchronous Actor–Critic Framework for UAV-Assisted IoV Task Offloading With Vehicle Trajectory Prediction. IEEE Internet of Things Journal. 2026;13(12):27688-27701. doi:10.1109/jiot.2026.3680146
BibTeX
@article{Yuan2026,
author = {Yuan, Ying and Zhu, Pai and Wang, Cong and Li, Guorui and Yao, Zhengmao},
title = {A Hybrid Soft Asynchronous Actor–Critic Framework for UAV-Assisted IoV Task Offloading With Vehicle Trajectory Prediction},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {12},
pages = {27688--27701},
doi = {10.1109/jiot.2026.3680146}
}
EUVIMED