Vehicle driving in a platoon is an efficient and ecological driving solution. Introducing the concept of digital twin (DT) into the platoon to establish platoon digital twin (PDT) can improve the management efficiency and driving safety of the platoon. However, the joint allocation of multiple types of resources in a platoon digital twin network (PDTN) is an important issue for the successful implementation and maintenance of the PDT. In this paper, we investigate the resource allocation problem in a PDTN. By comprehensively considering the effects of high mobility of platooning vehicles, real-time nature of the DTs, and multi-vehicle cooperation, we propose a PDT utility optimization model for bandwidth and computation resource allocation. We formulate the dynamic resource allocation problem as an M-th order Markov decision process (MDP) and design a deep reinforcement learning (DRL)-based dynamic resource allocation (DRLDRA) method to solve it. To optimize the actions of the agent, we reshape the state in a smaller time granularity to better reflect the temporal variations of the state. Correspondingly, we design temporal feature extraction neural networks (TFENNs) based on multi-head self-attention (MHSA) mechanism and long short-term memory (LSTM) to extract the temporal features of the state. To improve the learning efficiency, a decentralized multi-agent deep deterministic policy gradient (DDPG)-based learning framework is proposed. Numerical results show that the DRLDRA method performs excellently and outperforms other benchmark methods.
28 November 2023 in IEEE Internet of Things Journal
Real-time object detection is an essential part of various Internet of Things (IoT) applications. Unmanned aerial vehicles (UAVs) employ visual sensors to capture highdefinition images to detect objects of interest. However, current research on UAV detectors mainly focuses on developing more sophisticated network architectures, with little attention paid to the limitations of UAV computing resources. In this work, we present an end-to-end split-and-shuffle detector, named SCSDet. Unlike the mainstream detector designs that heavily rely on bottleneck structures, our method is based on inexpensive splitand- shuffle operations. It encourages the detector to avoid unnecessary transformation layers for channel down-sampling, thereby minimizing memory and computation cost. This is rarely studied in detector architecture design. Specifically, we first design a lightweight backbone structure (SCSNet) based on split-and-shuffle, which allows frequent interaction between different gradient information to capture more useful nonlinear features for small-scale objects at a low cost. Next, we construct an efficient receptive field module (ERFM) to generate richer multireceptive field expressions for the initial feature space. It significantly alleviates the adverse effects of single receptive field size on the capability of the detectors to detect small-scale objects. Finally, we propose a grouped local attention convolution (GLAConv), which utilizes local sliding windows with different coverage rates to adaptively learn channel and spatial attention. This makes the detector to focus on the foreground. Experimental results show that our method achieves high accuracy with low complexity in UAV object detection.
8 April 2025 in IEEE Transactions on Automation Science and Engineering
Traffic object detection based on computer vision (CV) can usually be deployed on the embedded computing platform of autonomous vehicles or unmanned aerial vehicles (UAVs), to provide critical information about traffic scenes for autonomous driving or traffic management. However, due to limited computing resources, there is a need for small, lightweight, and reliable object detectors. As an emerging technology, spatial pyramid pooling methods have great potential in improving the detection performance of real-time object detectors. Most of the existing works focus on the development of more complex spatial pyramid pooling methods for higher accuracy, but real-time performance is also important in the everchanging traffic scene. Thus, to balance the tradeoff between real-time detection and accuracy, we design a solution for real-time traffic object detection: a novel real-time object detector, named ESPPNet. Specifically, we propose an efficient plug-and-play spatial pyramid pooling method (ESPP). The method consists of a progressive spatial pyramid pool structure (PSPP) and a multi-scale feature enhancement module (MFEM). We first use PSPP to capture multi-scale feature maps with richer nonlinear features. Then, MFEM is used to establish effective long-range dependencies for multi-scale features. Experimental results on the VisDrone and SODA10M public datasets demonstrate that our method can achieve better real-time performance, less resource utilization, and higher accuracy, compared with other state-of-the-art methods.
Digital twin (DT)-empowered platoon can improve platoon management efficiency and driving safety. However, the resource allocation scheme of low-latency platoon digital twin (PDT) and the interactions with platoon control strategy are important issues in the study of PDTs. In this paper, we study the resource allocation in the PDT network and the interaction mechanism between PDT and platoon control for an unmanned aerial vehicle (UAV)-hosted PDT. We introduce the age of information (AoI) metrics to characterize the freshness of the DTs. To explore the impact of the PDT resource allocation scheme on the platoon control strategy, we propose a joint optimization model for power resource allocation and platoon control. Specifically, the allocation of power resources affects the PDT’s AoI, and the high-latency PDT in turn affects the platoon control strategy. Our objective is minimize the weighted sum of the system’s average energy consumption and the PDT’s average peak AoI. To solve the problem, we first reformulate the power resource allocation problem over a period of time as a Markov decision process (MDP) model, and then propose the Dirichlet deep deterministic policy gradient-based power allocation (D3PGPA) method based on Dirichlet distribution and DDPG algorithm. The method can not only effectively explores the state space while satisfying the constraints of limited resources but also improve the stability of the algorithm. Numerical results show that the D3PGPA method can host a PDT with low AoI and improve the stability of the platoon. Besides, our proposed method performs stably and outperforms other benchmark methods.
The object detection technology of optical remote sensing images has been widely applied in military investigation, traffic planning, and environmental monitoring, among others. In this paper, a method is proposed for solving the problem of small object detection in optical remote sensing images. In the proposed method, the hybrid domain attention units (HDAUs) of channel and spatial attention mechanisms are combined and employed to improve the feature extraction capability and suppress background noise. In addition, we designed a multiscale dynamic weighted feature fusion network (MDW-Net) to improve adaptive optimization and deep fusion of shallow and deep feature layers. The model is trained and tested on the DIOR dataset, and some ablation and comparative experiments are carried out. The experimental results show that the mAP of the proposed model surpasses that of YOLOv5 by a large margin of +2.3 and has obvious advantages regarding the detection performance for small object categories, such as airplane, ship, and vehicle, which support its application for small target detection in optical remote sensing images.
25 August 2025 in IEEE Transactions on Vehicular Technology
The rapid growth of compute-intensive and delay-sensitive applications in the Internet of Vehicles (IoV) has brought new challenges to traditional Vehicle Edge Computing (VEC). Especially during peak traffic periods, fixed base stations (BSs), due to their static deployment and limited coverage, struggle to elastically scale computing resources to meet the dynamically changing computational demands of vehicular users, which to some extent affects the overall quality of service and efficiency of system resource utilization. In this paper, we propose a hybrid edge computing framework that integrates Autonomous Aerial Vehicles (AAVs) as mobile computing nodes to complement fixed base stations. For this AAV-BS hybrid edge computing environment, we design and optimize a computation offloading model considering heterogeneous task types and AAV trajectory planning. The proposed model tackles the joint optimization of system revenue, service delay, and energy consumption, while considering practical constraints such as AAV energy limitations and base station capacity. To address this multi-objective optimization challenge, we construct a Markov Decision Process (MDP) model and develop a multi-head self-attention enhanced Multi-Agent Deep Dirichlet Deterministic Policy Gradient (MHSA-MAD3PG) algorithm. The multi-head self-attention mechanism enables agents to capture complex dependencies and interactions in the environment, leading to more effective collaborative decision-making. Comprehensive simulation results demonstrate that our proposed approach achieves superior performance in terms of system revenue, service delay, and energy efficiency compared to baseline methods.