YFYanfang Fu

Yanfang Fu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yanfang Fu has a total of 103 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Research on a Digital Twin-Based Local Penetration Algorithm for UAV Swarms

    by Shaochun Qu, Yuhuan Cai, Shiyan Wan, Yanfang Fu

    To address the challenges faced by UAV swarms in local narrow-space penetration missions, including constrained passages, dense obstacles, and the difficulty of balancing formation stability and traversability, this paper proposes a local penetration method that integrates virtual–center consensus-based formation control with a V-shaped formation self-reconfiguration strategy. First, a virtual geometric center is introduced as the consensus reference to replace the traditional physical leader node, thereby reducing the risk of single-point failure and improving swarm coordination consistency. Second, geometric constraints, including the effective channel width, lateral formation width, and safety margin, are incorporated to construct a channel-constraint-driven formation self-reconfiguration mechanism, enabling the swarm to contract its formation, avoid obstacles during traversal, and recover the formation after passing through the constrained region. Finally, a digital twin-based virtual–real interactive validation platform is constructed to verify the formation maintenance, formation reconfiguration, and virtual–real trajectory consistency of the proposed method. Experimental results show that the proposed method can maintain favorable formation consistency and safe inter-UAV distances in constrained channel environments while demonstrating good stability and scenario adaptability during formation adjustment and recovery.

  • Open Access

    ORBIT: Robust Offline Reinforcement Learning via Integrated Observation Recovery with Belief-Based Decision-Making Under Observation Corruption and Delay

    by Yibo Zhao, Zijian Cao, Zhihao Zhang, Yanfang Fu

    Offline reinforcement learning (offline RL) learns policies from pre-collected trajectories without online interaction with the environment, making it suitable for high-cost and safety-critical control applications. However, offline training datasets may suffer from observation corruption, while deployed agents may experience observation delay, resulting in distorted trajectory contexts and mismatches between available observations and current actions. To address this compound degradation, this paper proposes the Observation Recovery and Belief-Integrated Transformer (ORBIT), a robust offline RL algorithm that integrates diffusion-model-based observation recovery with delay-aware belief-based decision-making. ORBIT first employs an Observation Recovery Module (ORM) to detect and selectively recover suspicious observations by exploiting local temporal consistency. It then uses a Delay-Aware Belief Decision Transformer (DBDT) to infer decision-relevant information from delayed observations, historical actions, previously observed rewards, and delay-step information. The inferred belief representation is fused with delayed-observation features and fed into a Decision Transformer backbone for action prediction. Experiments on D4RL MuJoCo tasks show that ORBIT achieves an average normalized score of 32.1 in corrupted no-delay settings, outperforming Decision Transformer (DT) and Robust Decision Transformer (RDT) by 52.9% and 43.9%, respectively. Under adversarial corruption with fixed observation delays, ORBIT achieves 15.8, outperforming Delay-Transformer Belief Policy Constrained Offline Reinforcement Learning (DT-CORL) and RDT.

  • Open Access

    An Improved Particle Swarm Optimization Method for Multi-Unmanned Ground Vehicle Task Allocation Under Symmetric and Asymmetric Task Distributions with Time Windows

    by Ying Lu, Peiyi Li, Yanfang Fu

    Collaborative task allocation for multiple unmanned ground vehicles (UGVs) is a constrained combinatorial optimization problem in which symmetric vehicle resources must be coordinated with asymmetric task requirements. In delivery and inspection scenarios, homogeneous vehicles operate under identical rules, whereas task points differ in spatial distribution, demand, service time, and time window requirements. These asymmetries make compact, temporally feasible, and workload-balanced routing difficult. SACWDO-PSO is developed as a discrete particle swarm optimization framework that integrates Clarke–Wright savings initialization, adaptive parameter control, and simulated annealing local search. The savings strategy improves initial swarm quality, adaptive control adjusts exploration and exploitation during the search, and simulated annealing refines local route structures. The method is evaluated on Solomon VRPTW benchmark data under a soft time window penalty objective and insimulation scenarios developed using Unreal Engine 4.27 integrated with Microsoft AirSim 1.8.1. SACWDO-PSO obtains lower objective values and fewer time window violations than the compared swarm-intelligence baselines on most benchmark instances, while Wilcoxon signed-rank tests indicate statistically significant improvements over PSO, DPSO, and GA.

  • Open Access

    Research on Multi-UAV Cooperative Formation Control Method Considering Coupling and Communication Delay

    by Zequn Liu, Zhuxin Guo, Jianing Wei, Yunfei Zhang, Wanlin Fan, Yanfang Fu

    Coupling effects and communication delays present major challenges for distributed formation control of multi-UAV formations. This work characterizes coupling effects and integrates them into cooperative control synthesis under delay conditions. A leader state observer is introduced to reconstruct the leader’s state via neighboring information, reducing reliance on direct links and improving communication robustness. A delay aware cooperative control law with coupling effects is then developed, and Lyapunov–Krasovskii analysis establishes matrix inequality conditions to ensure stability. The key innovation lies in actively exploiting communication coupling to accelerate the error convergence rate and ensure formation tracking under communication delays. Theoretical analysis, grounded in the Lyapunov stability theorem, elucidates the mechanism by which coupling effects accelerate the error convergence rate. The effectiveness of the proposed method is validated through simulations of leader–follower formations.

  • Open Access

    SwinMR: A Mutual Refinement Enhanced SwinTrack Framework

    by Shifeng Zhao, Chuanyuan Yang, Yanfang Fu

    The task of tracking weak targets in low-altitude UAV scenarios requires high robustness and generalization ability of the model. Against this backdrop, this paper proposes a novel annotation and training mechanism based on SwinTrack. To improve the model’s tracking ability for weak targets, this paper proposes a pseudo-label consistency screening and background enhancement annotation strategy. This strategy enlarges the target box proportionally before training to obtain more effective background information. Furthermore, pseudo-labels are screened using a hybrid gating system of geometric overlap and confidence consistency to reduce the negative transfer interference of noise generated in different domains on the model. Since the data feature distribution varies significantly in tracking tasks, this paper introduces a mutual-teaching pseudo-label iterative training method into the field of weak target tracking. This aims to continuously transfer the model from the source domain to the target domain during iteration, thereby improving the model’s generalization ability. Experiments have shown that, when faced with a completely new dataset of weak target tracking, the proposed method improves upon recent strong baselines in single-target tracking by 0.05 in both P@20 and NP-AUC, and by 0.04 in SUS, demonstrating the enhanced tracking performance and generalization ability of the proposed method in the field of weak target tracking.

  • Open Access

    Multi-Fault Prediction of Electromechanical Actuators Based on SCI-BiGRU

    by Xiaojun Bai, Hanlin Liang, Haiyang Jia, Yanfang Fu, Zhaofeng Pan

    This paper presents a fault prediction model for electromechanical actuators (EMA) based on the SCI-BiGRU architecture, with the aim of achieving precise prediction of multiple fault modes. Upon analyzing the monitoring signals of the electromechanical actuators, target signal with good distinguishability across various fault modes was selected. Based on the target signal, this study implements multi-fault prediction through a predict-then-classify approach. Firstly, an improved SCI temporal prediction module was introduced to forecast the future waveform of the target signal. Subsequently, effective fault features were extracted from the predicted signal and fed into an enhanced BiGRU model for accurate fault category diagnosis. This integrated process achieves precise prediction of multiple fault modes within a unified framework. Experimental validation was conducted on the FLEA dataset from NASA, where the proposed model demonstrated robust performance in both temporal prediction and fault classification stages, thereby achieving high-precision early prediction of multiple fault modes.

  • BCUA: A UAV Group Authentication Protocol Based on the CVMerkle Tree Structure

    by Wenlong Jiang, Zhiqiang Du, Xiaofeng Rong, Yanfang Fu, Siqi Zheng, Yuanbo Chen

    With the rapid development of 5 G communication technology, small military UAV swarms are increasingly used in reconnaissance, surveillance, and remote sensing fields. Authentication has become a critical factor in ensuring the safe and efficient operation of UAV swarms. Due to their complexity and limitations, traditional methods cannot meet the dynamic deployment and command authority switching requirements of UAV swarms in special wartime environments. Therefore, this study proposes a secure and efficient authentication scheme for UAV swarms based on the CVMerkle tree structure. The scheme integrates distributed digital ledger technology to optimize the authentication process between UAVs and the Airborne Command Center(ACC). This significantly reduces the communication and computational load while improving the security and reliability of authentication. Additionally, the scheme introduces the innovative concept of dynamic authorization in the ACC, which effectively eliminates security threats arising from internal corruption within the core organization. The results of the simulation experiment demonstrate that the scheme offers significant advantages in terms of security, efficiency, and storage requirements. Future research will focus on developing more efficient key management mechanisms and swarm-switching strategies to adapt to the complex and dynamic combat environment, further enhancing the combat effectiveness of UAV swarms.


  • Open Access

    Dual-Chain-Based Dynamic Authentication and Handover Mechanism for Air Command Aircraft in Multi-UAV Clusters

    by Jing Ma, Yuanbo Chen, Yanfang Fu, Zhiqiang Du, Xiaoge Yan, Guochuang Yan

    Cooperative multi-UAV clusters have been widely applied in complex mission scenarios due to their flexible task allocation and efficient real-time coordination capabilities. The Air Command Aircraft (ACA), as the core node within the UAV cluster, is responsible for coordinating and managing various tasks within the cluster. When the ACA undergoes fault recovery, a handover operation is required, during which the ACA must re-authenticate its identity with the UAV cluster and re-establish secure communication. However, traditional, centralized identity authentication and ACA handover mechanisms face security risks such as single points of failure and man-in-the-middle attacks. In highly dynamic network environments, single-chain blockchain architectures also suffer from throughput bottlenecks, leading to reduced handover efficiency and increased authentication latency. To address these challenges, this paper proposes a mathematically structured dual-chain framework that utilizes a distributed ledger to decouple the management of identity and authentication information. We formalize the ACA handover process using cryptographic primitives and accumulator functions and validate its security through BAN logic. Furthermore, we conduct quantitative analyses of key performance metrics, including time complexity and communication overhead. The experimental results demonstrate that the proposed approach ensures secure handover while significantly reducing computational burden. The framework also exhibits strong scalability, making it well-suited for large-scale UAV cluster networks.


  • Open Access

    A Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization

    by Bo Yang, Linghang Gao, Fangzheng Zhou, Hongge Yao, Yanfang Fu, Zelong Sun, Feng Tian, Haipeng Ren

    Cooperative multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for addressing complex real-world challenges, including autonomous robot control, strategic decision-making, and decentralized coordination in unmanned swarm systems. However, it still faces challenges in learning proper coordination among multiple agents. The lack of effective knowledge sharing and experience interaction mechanisms among agents has led to substantial performance decline, especially in terms of low sampling efficiency and slow convergence rates, ultimately constraining the practical applicability of MARL. To address these challenges, this paper proposes a novel framework termed Reward redistribution and Experience reutilization based Coordination Optimization (RECO). This innovative approach employs a hierarchical experience pool mechanism that enhances exploration through strategic reward redistribution and experience reutilization. The RECO framework incorporates a sophisticated evaluation mechanism that assesses the quality of historical sampling data from individual agents and optimizes reward distribution by maximizing mutual information across hierarchical experience trajectories. Extensive comparative analyses of computational efficiency and performance metrics across diverse environments reveal that the proposed method not only enhances training efficiency in multi-agent gaming scenarios but also significantly strengthens algorithmic robustness and stability in dynamic environments.