Browse Topic: Electrical, Electronics, and Avionics

Items (60,704)
Find
Research on Intelligent Switching and Control Strategy of Air-Sea Amphibious WIG Craft Based on Multi-Sensor Fusion2026-99-0619To be published on 11/06/2026
Aiming at the core problems of abrupt changes in dynamic characteristics and poor smoothness in mode switching during the cross-medium operation of amphibious wing-in-ground (WIG) craft, this paper develops an intelligent switching and control system based on multi-sensor fusion. The system integrates measurement data from the Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), and Light Detection and Ranging (LiDAR) to construct a state observation module for mode switching decision-making. On this basis, a fuzzy switching logic centered on flight altitude and sea state characteristics is proposed, and a hybrid control strategy combining Linear Quadratic Regulator (LQR) and Proportional-Integral-Derivative (PID) is designed to realize the smooth transition between water surface and flight modes. Numerical simulations conducted in Python demonstrate that the proposed control scheme can accurately determine the mode switching timing, stabilize the pitch angle fluctuation within ±3° during the transition process, and effectively enhance the ability of WIG craft to operate autonomously and stably of the WIG craft in complex sea conditions.
Zhang, Qihao, Yan, Yifei, Cao, Fengshuo, Xiong, Yueling, Liu, Qing, Deng, Yanpeng, Wu, Peng
Air Target Trajectory Prediction Method Based on MSD-Transformer2026-99-0604To be published on 11/06/2026
The prediction of air target trajectories is important. It is necessary to integrate time-series data in the motion of air targets, such as timestamps, spatial coordinates, kinematic parameters, etc. To cope with the challenges of air target trajectory prediction in complex electromagnetic environments, this paper proposes the MSDTransformer model. The SMSAE and DDE modules are introduced, and this method improves the performance of air-target trajectory prediction. The sensitivity analysis of system hyperparameters verifies the rationality of model parameter configuration. The experimental results show that, among the simulated air target data, MSD-Transformer achieves lower prediction errors and demonstrates strong overall performance, compared with 5 main methods (iTransformer, Informer, PatchTST). It can support the understanding and prediction of target situations, provide an accurate basis for the analysis of the intentions of air targets and the prediction of the evolution of situation evolution, and then improve the situation awareness ability. It has important application value for trajectory prediction in modern aerospace surveillance and situation awareness.
Zhang, Yongzhuang, Sun, Peng, Zhang, Jieyong, Yang, Guangwei, Jiang, Jianxiong, Li, Tianxin, Zhong, Yun
Reproducing Capture Control in a Novel Hardware-in-the-Loop Simulation System2026-99-0601To be published on 11/06/2026
In space gravitational wave detection, the verification of the mass release capture phase determines subsequent mission advancement. Existing control algorithms are primarily validated through simulation, though ground-based experimental verification remains indispensable. This paper develops a two-stage torsion pendulumbased ground hardware-in-the-loop (HIL) simulation system to simulate and verify the position and attitude degrees of freedom of the test mass. An Expansive State Observer and State Feedback Control (ESO-SFC) disturbance rejection and capture controller based on an ESO and SFC was designed and compared with a PID controller. Numerical simulation results demonstrate that the ESOSFC controller outperforms the PID controller. Experimental validation was conducted on a HIL simulation system. Results confirmed the system's capability to achieve capture functionality while validating the effectiveness of both the ESO-SFC and PID control algorithms. The ESO-SFC demonstrated superior control performance to PID, with experimental outcomes consistent with simulation results. This provides a reference for test mass release capture control algorithms.
Ping, Shanyan, Ren, Yuqi, Cui, Bing, Zhang, Chu, Xia, Yuanqing, Duan, Li, Kang, Qi
2026 International Conference on Artificial Intelligence, Autonomous Systems, and Aerospace (AIAS 2026)2026-99-0600To be published on 11/06/2026
TOC
Tobolski, Sue
Autonomous Obstacle Detection and Landing Site Selection Method for Complex Lunar Approach Phases2026-99-0635To be published on 11/06/2026
In response to the challenges of autonomous obstacle detection and landing site selection during the soft-landing approach phase of the Chang'e probes, this paper proposes a method based on Fractal Brownian Motion (FBM) for local lunar terrain reconstruction and obstacle identification. Using passive optical imagery and incorporating statistical models of crater morphology and distribution, the method approximates the 3D structure of candidate landing areas and estimates local slopes. Combined with texture analysis (TA) via K-means clustering evaluated by silhouette coefficients, and by integrating slope and roughness metrics, feasible landing zones are autonomously identified. Simulation results demonstrate that the proposed approach can rapidly reconstruct terrain and select suitable landing areas, showing good mission adaptability.
Zhu, Hanxi, Wu, Peng, Wu, He, Li, Yixiu, Tang, Weipeng, Deng, Yanpeng
An Enhanced Mamba Integrating Dynamic Compression Ratio Channel Attention and Progressive Projection for Multivariate Time Series Forecasting2026-99-0640To be published on 11/06/2026
Time series forecasting is a practical cornerstone for decision-making in diverse fields including finance, energy management and meteorology, yet conventional Transformer-based models are plagued by high computational complexity inherent in their attention mechanism, as well as poor efficiency in capturing long-range dependencies when processing long-sequence time series data. Meanwhile, the recently proposed Mamba model built on a linear-complexity state space model has achieved strong performance in long-sequence modeling tasks, but the vanilla Mamba model still has obvious limitations in time series forecasting scenarios, including insufficient discriminability of channel features, unsatisfactory prediction accuracy, and information loss during feature transmission in the encoder layer. To address these issues, this paper proposes An Enhanced Mamba Integrating Dynamic Compression Ratio Channel Attention and Progressive Projection for Multivariate Time Series Forecasting, which incorporates three core improvement strategies: a lightweight dynamic compression ratio channel attention, a residual-optimized encoder, and a progressive prediction head. These strategies realize adaptive weighting of channel features, lossless information transmission in the encoder and gradual refinement of forecasting results respectively. Extensive experiments on multiple public time series datasets show that compared with the vanilla Mamba model and mainstream Transformer-based forecasting methods, the proposed model achieves significant improvements in prediction accuracy, along with stronger robustness and higher practical application value.
Zhu, Yongdong, Zou, Lei, Li, Na, Wang, Chenxi
Vehicle Detection from UAV Perspective Based on GBC-YOLOv5s in the Low-Altitude Economy2026-99-0643To be published on 11/06/2026
This paper presents GBC-YOLOv5s, a lightweight vehicle detection model designed for unmanned aerial vehicle (UAV) applications in the growing low-altitude economy sector. By utilizing the baseline YOLOv5s architecture, we integrated three structural enhancements to achieve an optimal trade-off between algorithmic precision and processing expenses. First, ghost convolution is used to exploit feature map redundancy, substantially cutting both parameter count and computational overhead. Second, a Bi-Level routing attention (BRA) mechanism is integrated. This allows the model to capture global context along with fine-grained local features of vehicle targets effectively. Third, standard upsampling is replaced with content-aware reassembly of features (CARAFE). This better preserves feature details, which proves particularly important for detecting small objects. Testing was conducted on a custom UAV-based vehicle dataset. GBC-YOLOv5s achieves 86.6% average precision (AP) with only 4.7 M parameters. This represents a 34.7% reduction from the original YOLOv5s with 7.2 M parameters. The accuracy drop is merely 0.2%. Ablation experiments validate both the individual impact and synergistic nature of each proposed module. Results show that GBC-YOLOv5s reaches a practical balance between performance and efficiency. It offers a workable solution for real-time vehicle detection on resource-limited UAV platforms and intelligent traffic monitoring applications.
Zhang, Qingpei, Yu, Tianhao, Zhao, Zheming
Compensation Strategy-Based Gaussian Approximation Fusion Filtering for Multi-Sensor Nonlinear Systems Subject to Markov DoS Attacks2026-99-0614To be published on 11/06/2026
The research concentrates on the Gaussian approximation fusion filtering (GAFF) issue for multi-sensor nonlinear systems under Markov denial of service (DoS) attacks. This paper aims to propose a fusion filtering algorithm for the addressed systems to cope with DoS attacks within the Gaussian approximation filtering framework, where the attacks follow the Markov property. In particular, a prediction compensation strategy is adopted to reduce the impact caused by the attacks as much as possible. In light of the available measurements, the Gaussian approximation local filtering unified framework is given, where the Gaussian weighted integrals are addressed by means of the cubature Kalman method. By using the sequential inverse covariance intersection fusion criterion, the GAFF algorithm is obtained to improve estimation accuracy. Finally, a simulation experiment with comparison tests is introduced to validate the effectiveness of the proposed GAFF method.
Luo, Ruonan, Hu, Jun, Jia, Chaoqing, Dao, Wen
Coupling Effect Analysis of Disturbance from Rotating Components in Flexible Satellites2026-99-0610To be published on 11/06/2026
This study investigates the coupling effect between rotating components of a satellite equipped with flexible appendages and the satellite’s unconstrained modes. A modal synthesis method based on mixed coordinates is adopted to establish the dynamic model of a satellite with multiple flexible appendages. The vibration equations under the excitation of disturbance torques induced by rotating components are derived for the flexible appendages in an unconstrained state. The on-orbit unconstrained modal frequencies and their mode shape vectors are calculated. Based on this, the analytical expressions for the satellite’s unconstrained modal responses and attitude angular velocity under the influence of driving disturbances from rotating components are obtained. Furthermore, the coefficient matrix that characterizes the amplification of attitude angular velocity induced by flexible vibration is analyzed when the drive frequency of rotating components is coupled with the satellite’s unconstrained modal frequencies. Taking a sun-synchronous orbit satellite with a single solar array as an example, the on-orbit unconstrained modal frequencies as a function of solar array angles are calculated. By applying harmonic disturbance torque generated by a rotating component, the attitude angular velocity and constrained modal coordinates are obtained through simulation. When the drive frequency of the rotating component matches the satellite’s unconstrained modal frequency, the corresponding mode shape (eigenvector) is analyzed. Based on the eigenvector values, the constrained mode of the solar array exhibiting the maximum coupling vibration is identified. The amplification coefficient matrix of attitude angular velocity resulting from coupling with the drive disturbance of the rotating component is validated. The damping coefficient associated with the unconstrained mode is estimated using the simulation data.
Sun, Shang, Niu, Wenting, Zhang, Kaicheng, Yang, Yulong, Zhang, Yanzhao
Knowledge-Driven Aerial Swarm Target Intent Recognition Method for Few-Shot Scenarios2026-99-0623To be published on 11/06/2026
With the continuous advancement of collaborative unmanned aerial vehicle (UAV) swarm applications, the importance of intent recognition for aerial swarms in UAV management and control has become increasingly evident. To address the shortcomings of existing intent recognition methods, this paper proposes a knowledge-driven aerial swarm target intent recognition method designed for few-shot scenarios. First, a target trajectory clustering algorithm is designed by combining trajectory similarity measurement (which considers directional features) with density peaks clustering. This algorithm groups targets exhibiting the same or similar motion trends, thereby transforming the swarm target intent recognition problem into a swarm member intent recognition problem, which reduces the complexity of intent recognition. Second, considering the behavioral dynamics inherent in aerial swarm collaborative applications, a target intent inference model is constructed based on a Dynamic Bayesian Network (DBN). Utilizing the characteristic information of swarm targets at different time points, this model achieves intent inference and recognition through a hierarchical process: “sub-intent inference → accumulation of historical sub-intent sequences → intent inference.” Finally, simulation experiments are conducted to verify the feasibility and effectiveness of the proposed method.
Jiang, Jianxiong, Gui, Yang, Sun, Peng, Yang, Xinyu, Yang, Guangwei, Zhong, Yun
Onboard AI-Driven Autonomous Tasking for Rapid Wildfire Response with a LEO Wide-Swath Observation Satellite2026-99-0609To be published on 11/06/2026
Low Earth Orbit (LEO) remote sensing satellites exhibit significant limitations in emergency response operations, primarily due to the constraints of orbital mechanics and a traditional reliance on ground-involved, open-loop operational models. Current response latencies often span several hours, rendering acquired data less effective for disasters with rapid temporal dynamics. We propose a new intra-pass autonomous reaction application mode to solve this key problem in emergency response. We build the mode on an agile satellite platform operating in an 800 km sun-synchronous orbit. We equip the platform with two core sensors through an innovative design. The two sensors are an optical camera with 0.5-meter resolution and a forward-looking infrared camera. The infrared camera has a 600-kilometer swath and a 10-meter nadir resolution. We take onboard artificial intelligence technologies as the research core. The technologies support real-time and autonomous analysis of forward-looking infrared image data. This analytical capability facilitates the real-time detection and autonomous confirmation of stochastic events, such as wildfires, by leveraging onboard artificial intelligence (AI) to perform real-time analysis of IR imagery. This subsequently triggers immediate autonomous re-tasking for high-resolution follow-up observation within the same orbital pass. We establish an optimization model for the satellite system. The model is used to solve the key balance problem between the sensor forward-looking angle, achievable reaction time, and actual detection resolution. We conduct a detailed engineering time budget analysis for the whole satellite operation system. Analysis results show that a specific forward-looking angle must be set for the infrared camera to obtain a 70-second autonomous response window of the satellite. The 70second window contains 30 seconds for AI cognitive analysis, a maximum of 33.6 seconds for platform attitude maneuvering, and 10 seconds for platform stability adjustment. The minimum forward-looking angle required for the infrared camera is about 33.6 degrees. The ground sampling distance of the infrared camera will decrease to 12.2 meters at this angle. The resulting 12.2-meter ground sampling distance (GSD) remains sufficient to meet the practical requirements of early-stage detection. The proposed Intra-Pass Autonomous Reaction (IPAR) mode reduces emergency response times from hours to seconds, significantly enhancing the proactive observation capabilities of LEO platforms.
Qiu, Hu, Zhao, Xinwei, Liu, Dongfusheng, Wang, Honghai
Energy Management for Series Hybrid Aircraft Based on a Dual Adaptive Equivalent Fuel Minimization Strategy2026-99-0603To be published on 11/06/2026
Series hybrid tiltrotor aircraft operate under highly dynamic and multi-phase flight missions. This paper addresses the resulting energy management challenge. Moving beyond the direct application of existing optimization algorithms, this study proposes a novel codesign framework that synergizes offline global optimization with online fuzzy adaptive control. The key theoretical innovation lies in transforming the online, real-time optimization problem of determining the optimal equivalent factor into an offline global optimization problem for the parameters of a fuzzy-PI controller. This is achieved through a hybrid particle swarm optimization and genetic algorithm (PSOGA), which optimizes the controller's scaling factors and gains. The optimized controller embeds mission-level economic information into the online generation of the equivalent factor, so that the power-split decision is determined not only by the instantaneous operating conditions, but also by the overall economic objective of the mission. Simulation results under typical and stochastic flight conditions validate the framework's effectiveness. Compared to benchmark strategies, the proposed PSOGA-Fuzzy-A-ECMS achieves a 6.7% improvement in fuel economy while robustly maintaining the battery state of charge within a safe and stable range. This study provides a systematic and theoretically-grounded design paradigm for real-time energy management in complex, time-varying systems.
Wang, Zhihao, Wang, Xiangyang
Research on Quantification Methods for Nonlinear Forming Length of Ultra-Thin Flat Wires in Flat Wire Motors2026-99-1913To be published on 11/06/2026
Because of the imprecision of length quantification in the manufacturing of flat wire windings for flat wire motors, empirical allowances have long been a common practice in production, which in turn leads to considerable material waste and elevated production costs. This paper presents an integrated solution that fuses material experiments, reverse engineering, simulation iteration and parametric design, realizing accurate prediction and quantitative calculation of winding forming length. First, high-precision elastic-plastic constitutive relationships of flat wires are acquired through room-temperature uniaxial tensile tests. On this basis, reverse engineering is applied to derive the initial geometric characteristics and process motion paths of flat wire windings from the 3D model of finished products. Next, an innovative closed-loop iterative compensation algorithm is constructed, with the forming height of the innermost flat wire layer serving as an absolute reference; finite element simulation is then utilized to dynamically optimize the forming length of each flat wire layer. Finally, a parametric design system with a visual interactive interface is developed, which enables an intelligent workflow where precise cutting lengths and equipment motion curves are automatically generated upon input of key design parameters. Production validation results show that this method drastically reduces the length allowances of flat wires, markedly lowers the production scrap rate, and shortens the process debugging cycle of new motor models by more than 80%.
Li, Wenbin, Zhu, Ye
Aeroseek: Exploring LLM-Enhanced Monte-Carlo Path Planning for UAV Navigation2026-99-0613To be published on 11/06/2026
While Unmanned Aerial Vehicles (UAVs) hold immense potential for transforming the low-altitude economy, developing an agent that combines both intelligence and flexibility remains a significant challenge. To this end, we propose a novel aerial navigation system, Aeroseek, to search for executable paths that coherently transition from cognitive understanding to physical movement, enabling more autonomous and flexible navigation with instruction guidance. Specifically, given a navigation instruction, we follow a fast-andslow thinking procedure inspired by human pilots by breaking down complex decisions into manageable sub-tasks and initiating motion planning immediately upon the completion of each sub-task for realtime movement. By integrating a multi-branch Chain-of-Thought, Aeroseek is capable of combining reasoning with spatial recognition and self-verification to search for robust sub-goals under expected constraints. For sub-goal navigation, we introduce Online Kinodynamic Monte-Carlo Path Planning (OnKi-MCPP), a novel motion planning approach handling both kinodynamic constraints and path search, while ensuring obstacle avoidance for UAVs. Benefiting from the proposed two-tier searching protocol, Aeroseek demonstrates comprehensive capabilities in processing complicated instructions and adapts to dynamic aerial conditions. Extensive experiments demonstrate the advantages of Aeroseek across tasks of varying complexity.
Luo, Guoan, Xu, Tian, Zhou, Jiacong, Wang, Xianyun
Study on the Severity of Aircraft Ice Protection System Performance in the Icing Envelope2026-99-0611To be published on 11/06/2026
In the process of design and verification of the aircraft ice protection system, a prediction model of ice protection system performance based on Severity Index(IPSI) is proposed, which quantifies the relationship between input and output energy of the ice protection system. In this research, a theoretical calculation method is developed, and the water total collection coefficient and convective heat transfer coefficient on the skin surface were obtained using CFD calculations and rapid neural network prediction methods. The consistency between IPSI and ice protection system performance is verified through an aircraft wing ice protection wind tunnel test. The results show that the lower the slat skin temperature in the ice protection area, the higher the IPSI value, which means the more severe the ice protection system performance. The ice protection performance severity analysis method is carried out for the cases in the CCAR/FAR/CS-25 continuous maximum(CM) envelope of an aircraft, and the IPSI values of each case at some altitudes are calculated, as well as the distribution of the ice protection system performance severity cases in the CM altitude-temperature envelope. The ice protection system performance severity cases are not the highest or lowest atmospheric static temperature in the CM envelope, in which atmospheric static temperature ranges from -8°C to -23°C from low altitude (1500 ft) to high altitude (22000 ft). When the flight speed is constant, and the atmospheric static temperature is gradually reduced, the IPSI value decreases. When the atmospheric static temperature is constant, and the flight speed increases gradually, the IPSI value increases. The influence of water evaporation heat transfer on ice protection performance severity is greater than that of convection heat transfer. The total air temperature for the most severe condition is always 0°C at every altitude. The IPSI calculation model can be used to quickly predict the severity of ice protection system performance in other ice protection areas of aircraft, even wind blades.
Hu, Weixue
Design of a Gantry-Type Intelligent Grasping Device for Logistics Warehousing Based on MaixCam2026-99-1925To be published on 11/06/2026
Traditional warehousing suffers from low efficiency, high manual error rates, substantial labor costs, and complex deployment, while existing sorting devices remain poorly adaptable for small- and medium-sized operations. To address these issues, this paper presents an intelligent gantry-type grasping device for logistics warehousing based on the MaixCam. The device integrates mechanical design, computer vision, and electronic control. An Arduino Mega2560 serves as the main control board, with 57-series and 42-series stepper motors and servo motors driving the gantry and gripper. The mechanical structure adopts a miniaturized gantry architecture constructed from alloy steel, enabling operation in confined workspaces. A YOLOv5s model with transfer learning was trained for cargo box recognition using a dataset of 654 images collected under various lighting conditions and backgrounds. The model achieves a recognition accuracy of 93%–96% with inference times of 10–14 ms at 25–28 FPS. The proposed device provides a viable solution for automated sorting in small-to medium-sized warehouses, balancing recognition performance, power consumption, and cost.
Xiang, Chang’an, Zhou, Dan, Fan, Zhiwei
A Method for Disordered Circlip Recognition Based on Improved YOLOv11 and Association Strategy2026-99-0622To be published on 11/06/2026
To realize automated grasping of randomly placed C-type circlips in automotive and mechanical assembly processes, this paper proposes an identification method based on the improved YOLOv11 algorithm and an exclusive association strategy. First, a detail enhancement convolution (DEConv) module is introduced into the C3k2 module of the YOLOv11 network to enhance the ability to capture the edges and high-frequency details of the circlips; Second, the parallel patch-aware attention (PPA) module is adopted in the detection head instead of the traditional convolution, and through multi-branch fusion and channel-spatial attention mechanism, it adaptively focuses on the key areas of small targets; Finally, the normalized Wasserstein distance (NWD) loss function is used instead of the IoU loss to alleviate the gradient disappearance problem in the positioning of small targets and improve the model’s detection accuracy. Based on precise detection, this paper innovatively proposes a circlip-hole association strategy based on multi-level spatial constraints, achieving accurate pairing of randomly placed circlips through bounding box-inclusive attribution judgment, distance screening, and selection of the best circlip-pair. Experimental results show that compared with the original YOLOv11 model, our model improves the mAP50 and mAP50-95 significantly by 5.7% and 3.3%, respectively; its association accuracy reaches above 95%, and the average processing time is 142 ms. Both in terms of accuracy and speed, our model meets the requirements of industrial real-time grasping and provides reliable prior information for the subsequent precise clamping of the robotic arm.
Wang, Chuang, Li, Jiyan, Wang, Yongming, Tan, Libin
Anchoring Mechanics Analysis and Structural Optimization of Slip for Pipeline Plugging Robot2026-99-1915To be published on 11/06/2026
Reliable anchoring of slip is essential for preventing axial slippage of pipeline plugging robots under high-pressure plugging conditions. However, excessive tooth penetration may induce furrow formation, local plastic deformation, and hard-contact damage on the inner wall of the pipeline. To balance anchoring capacity and pipe-wall protection, this study establishes a mechanical model for the slip–pipe interaction and analyzes the effects of key structural parameters on slip anchoring performance. The self-locking condition between the slip and slip bowl is first derived, and the minimum equivalent friction coefficient required for stable anchoring is determined. Subsequently, an explicit finite element model of the slip anchoring process is developed to evaluate the influence of bevel angle, tooth profile angle, and curvature radius on the von Mises stress and equivalent plastic strain of both the slip and the pipe wall. Based on the simulation results, an orthogonal parameter optimization scheme is conducted to identify the optimal structural combination. The results show that the optimized slip structure, consisting of a 20° bevel angle, a 90° tooth profile angle, and a 150 mm curvature radius, can effectively reduce pipe-wall damage while maintaining reliable anchoring performance. This study provides a theoretical and numerical basis for the structural design and optimization of anchoring slip in pipeline plugging robots.
Wang, Mingkuan, Zhang, Enchao, Gao, Ang, Shao, Hongyuan, Zhang, Shimin, Zhu, Xiaoxiao
UAV Positioning and Tracking Measurement Method Based on Laser-Vision Dual-Mode Fusion2026-99-1929To be published on 11/06/2026
Flight positioning accuracy is a key technical indicator of unmanned aerial vehicle (UAV) systems. To quantitatively and accurately evaluate the positioning accuracy of UAV flight trajectories, this paper proposes a theoretical model for motion trajectory measurement and positioning, as well as a systematic solution for tracking measurement, based on a 2D tracking turntable carrying a dual-mode optoelectronic fusion integration system consisting of a laser ranging sensor and a vision camera. It analyzes the main influencing factors of measurement errors and establishes a measurement error model for flight trajectory positioning. Finally, flight trajectory tracking, positioning, and measurement experiments are carried out based on the principle prototype, which verifies the correctness of the method model and the feasibility of the system scheme. This study provides a theoretical basis and technical support for the testing of UAV flight control positioning accuracy indicators.
Qi, Weijie, Qiao, Yongming
2026 International Conference on Intelligent Vehicles and Mechanical Engineering (IVME 2026)2026-99-1900To be published on 11/06/2026
TOC
Tobolski, Sue
Intelligent Unmanned Aerial Vehicle System for Automated Red Pine Cone Harvesting in Dense Forests2026-99-0630To be published on 11/06/2026
This paper describes an intelligent unmanned aerial vehicle (UAV) system that automates red pine cone harvesting in dense forests to mitigate the safety and inefficiency of traditional manual harvesting. The suggested system combines multi-sensor fusion perception, variable-stiffness rigid-flexible composite manipulator, and smart path planning into a single aerial harvesting system. To create a three-dimensional model of the environment and robust cone detection under complicated lighting conditions and extreme canopy occlusion, a heterogeneous sensor suite such as LiDAR, depth cameras, and inertial sensors is used. According to the results of fused perception, collision-free approach paths are created to lead the UAV safely to target cones in limited three-dimensional spaces. One of the significant contributions of this work is the iterative design and optimization of a dedicated harvesting manipulator to be used in aerial forestry operations. A comparative analysis of various structural designs leads to the creation of a rigid flexible composite manipulator with an effective workspace diameter of 1.8 m and adequate stiffness to reduce the effects of the downwash of the UAV rotor. The disturbance-assisted harvesting strategy is adopted by the system, which enables efficient dislodgement of cones without requiring accurate grasping. The proposed technical route is proven to be feasible based on laboratory experiments and initial field tests carried out in real forest settings. It has been experimentally proven that the combined system can effectively perform autonomous harvesting cycles, including target recognition, navigation, and cone dislodgement, thus offering a practical technical paradigm of intelligent and safe forestry harvesting applications.
Shi, Shuaiqi, Du, Yisheng, Li, Xiang, Wang, Weidong
Optimization of Vehicle Windshield Cleaning: A Novel Horizontal Wiper System Based on Ball Screw Drive2026-99-1909To be published on 11/06/2026
Conventional types of wipers are characterized by some consistent disadvantages, such as huge uncleared blind spots (up to 40 percent of the target area), limited wiping functionality, and great dynamic visual interference. Due to the intensive full-field visibility demands of autonomous driving, this paper will introduce a new linear reciprocating wiper that will be driven by a ball screw. In particular, one of the prototypes of such a system is designed based on a Dongfeng heavy-duty truck, according to which the traditional oscillatory movement is converted into a horizontal directional movement by a ball screw. This is powered by a motor of 24 V drive with a worm gear reducer to give the force needed to achieve the horizontal reciprocating motion of the wiper blade assembly over the windshield. For the intelligent control module of the proposed lateral linear wiper system, a special intelligent control system is developed based on the principle of CAN bus communication and multi-sensor fusion. Both a rain sensor and a proportional-integral-derivative (PID) algorithm allow the system to achieve adaptive control of wiper speed and apply to various modes, including intermittent wiping, low-speed wiping, and high-speed wiping.
Dong, Xingzhuang, Hu, Yanxingyu, Li, Jincheng, Xu, Tongqiang, Wu, Liying
Failure Mechanism Analysis of Traction Battery Caused By Bottom Collision2026-99-1914To be published on 11/06/2026
As green development has become a global unified strategy, major developed countries in the world have successively announced their ambition to achieve carbon neutrality in this century. The new energy vehicle and traction battery industry has ushered in a high-quality development moment, and the safety of traction batteries has also been widely valued worldwide. As the traction battery is mainly arranged at the bottom of the vehicle, enhancing the operational safety of new energy vehicles necessitates a breakthrough in performance testing for bottom-impact protection. It is essential to develop a robust evaluation methodology that can accurately and efficiently evaluate the extent of damage inflicted on the battery system following a bottom impact or collision. Based on the bottom impact experiment of a typical traction battery pack, this paper studies the damage morphology and damage mechanism of the bottom impact. By integrating finite element mechanical simulations, it provides a detailed analysis of the evolving mechanical states across different zones of the battery pack during the impact event. The findings contribute to enhancing safety protection strategies for traction batteries in bottom impact scenarios and offer crucial support for evaluating the post-impact safety performance of new energy vehicles.
Yan, Pengfei, Han, Liqiong, Chen, Liduo, Wang, Fang, Ma, Tianyi, He, Gaiyun, Liu, Lei
Category-Aware Transformer for Automotive Spare Parts Demand Forecasting2026-99-1917To be published on 11/06/2026
In the modeling process, existing auto parts demand forecasting methods often fail to clearly distinguish structural differences at the demand-frequency level, which results in limited adaptability in real scenarios characterized by sparse demand and a complex category structure. In response to the above problems, this paper proposes a category-aware Transformer framework for auto parts demand forecasting. To explicitly represent demand differences across frequency-based accessory groups and to reduce training bias caused by long-tail sample imbalance, the framework first constructs frequency categories based on statistical demand characteristics and incorporates them into the model as embedding-based structural priors. It then designs a category-perception attention mechanism within the Transformer to guide differentiated modeling of category-related temporal dependencies. At the same time, in order to improve the expression ability of sparse and nonlinear disturbances, this paper introduces a nonlinear mapping module at the prediction end and uses a weighted loss function based on sample distribution to constrain the training target. Experimental results on three real auto-parts demand datasets from Dongfeng Automobile Co., Ltd. show that the proposed method outperforms five benchmark models in terms of RMSE and MAE, with especially strong performance in predicting intermediate-frequency and long-tail parts.
Yi, Yuxuan, Wang, Xiaodong, Yang, Wei, Cai, Yonghua
Design and Optimization of an LQR-Based Multivariable Control System for an RBCC Engine2026-99-0632To be published on 11/06/2026
To achieve the key control objectives of thrust regulation and inlet protection for a rocket-based combined cycle (RBCC) engine under wide flight envelope, high-speed operating conditions, this study is based on a nonlinear component-level RBCC engine model developed in MATLAB/Simulink. A state space model is established using a least squares system identification method. By incorporating actuator dynamics, an augmented system model is formulated, and a Differential Evolution (DE) optimized Linear Quadratic Regulator (LQR) multivariable closed-loop control strategy is proposed. Simulation results show that the proposed strategy significantly improves both response speed and disturbance-rejection capability. Compared with the conventional LQR controller, the maximum oscillation of the inlet stability margin is reduced from 11% to 4.4%, and the thrust settling time is shortened by 83%. These results verify the feasibility of the proposed control method under complex operating conditions.
Zheng, Runtong, Han, Chongpeng, Xie, Zhenwei
A Rapid Determination Method for Key Node Parameters in the Full-Process Launch Vehicle Mission Design2026-99-0641To be published on 11/06/2026
-7
Dong, Chenyu, Liu, Lingyu, Han, Hongwei, Zhang, Longxi, An, Yang, You, Zhipeng
Regenerative Braking Control Strategy for Electric Vehicle Based on Improved Ant Colony Algorithm2026-99-1919To be published on 11/06/2026
To address low energy recovery efficiency and inaccurate torque distribution of regenerative braking in electric vehicles, this paper proposes an optimized fuzzy control strategy for regenerative braking based on an improved ant colony algorithm. The design focuses on using the battery state of charge, real-time vehicle speed, and braking intensity as fuzzy control inputs, with the regenerative braking ratio as the output. By employing the improved ant colony algorithm to dynamically optimize the parameters of the fuzzy controller, the accuracy of electric motor braking force distribution is effectively improved; Building on this foundation, the introduction of the Elite Ant Guidance Algorithm enhances the speed of adaptive pheromone updates and dynamic path selection, thereby improving regenerative braking energy recovery efficiency. A MATLAB/Simulink simulation model was developed, and comparisons under the NEDC and UDDS test cycles demonstrated that, compared to traditional fuzzy control strategies, the optimized algorithm increases energy recovery efficiency by 12.8% and 8.1%, respectively, confirming the effectiveness and validity of the improved control strategy.
Yang, Zijiang, Zhang, Wei, Zhang, Jihong, Qi, Ye, Zhang, Zilei
The Dynamic Analysis of the Passenger Car Steering and Braking Stability2026-99-1912To be published on 11/06/2026
During cornering-braking maneuvers, an excessively high braking torque can consume a substantial portion of the available tire-road friction and cause insufficient frictional capacity to satisfy the lateral force demand generated by cornering. As a result, the vehicle may experience stability degradation and, in severe cases, lose control, potentially causing accidents. In this study, an AMESim-based vehicle dynamics model is developed, and yaw rate and sideslip angle are adopted as the primary evaluation indices to characterize steering-braking behavior. Under conditions of a fixed turning radius and initial braking speed, the critical braking force was simulated and analyzed. Additionally, the critical steering wheel angle was examined under conditions of a fixed braking torque and steering speed. The results indicate that if either the braking force or the steering wheel angle exceeds its critical value, the vehicle will lose stability during combined steering and braking.
Ma, Lianglin, Yi, Bingjun, Hu, Yang
Covariance-based Filtering and Smoothing Estimation under a Round-Robin Protocol2026-99-0627To be published on 11/06/2026
This paper focuses on recursive estimation for stochastic systems under the round-robin (RR) protocol. In recursive estimation, it is assumed that the state evolution process of the signal is unknown, and the relevant estimation research is only carried out relying on the mean and covariance functions of the process. To effectively avoid the occurrence of transmission channel conflicts and ensure the fairness of data allocation during transmission, this paper chooses to adopt the RR protocol to schedule and manage data communication. Specifically, this scheduling rule stipulates that only one sensor is allowed to acquire the network communication opportunity within a fixed time period, and the entire scheduling process is executed cyclically in a preset fixed order. Based on the observable information available in the system, this paper further designs and proposes a recursive estimation algorithm by means of the innovation method. Finally, a numerical simulation experiment is given to verify the effectiveness and feasibility of the proposed estimation algorithm.
Lin, Xiao, Li, Jiaxing, Du, Junhua, Wu, Meiyun
Cooperative Adaptive Cruise Control for Connected Vehicle Platoons with Unknown Control Directions Under Output Constraints2026-99-0624To be published on 11/06/2026
In this paper, a distributed cooperative adaptive cruise control (CACC) strategy is designed for connected vehicle platoons under unknown control directions and time-varying speed constraints. To address vehicle control directions unknown problem arising from uncertain actuator and vehicle parameters, a Nussbaum-type gain is incorporated into the controller design processes, enabling stable operation without prior knowledge of the vehicle direction. Furthermore, the barrier Lyapunov function is employed to enforce speed constraints, ensuring all vehicles remain within safe and admissible velocity bounds. The designed leaderless scheme allows all vehicles to participate equally in coordination, enhancing robustness and scalability under a bidirectional communication topology. Finally, a simulation result is proposed to validate the effectiveness of the CACC strategy.
Li, Xin, Wei, Xiaozong, Chen, Si, Yang, Shaopeng, Liu, Mingyang, Zhu, Liangkuan
Investigation on Interface Analysis and Process Simulation of Electromagnetic Pulse Welding for Automotive Copper Terminal/Aluminum Conductor Joints2026-99-1922To be published on 11/06/2026
To suppress the formation of brittle intermetallic compounds typically generated during conventional joining of Cu/Al dissimilar materials in the automotive lightweighting sector, this study examines the interface properties and process simulation of electromagnetic pulse welding technology for connecting copper terminals to aluminum conductors. High-quality welds exhibit a wavy interface composed of interpenetrating metallic phases, according to microstructural research. To represent workpiece dynamics, magnetic field distribution, and impact behavior under discharge voltages ranging from 4 to 5.5 kV, a linked electromagnetic-structural finite element model was developed. According to simulation data, increasing the discharge voltage significantly enhances impact pressure, strain rate, and magnetic flux density, all of which support strong contact bonding. The study offers a reference for the lightweight production of automobile electrical connectors by demonstrating the impact of process factors on weld quality.
Li, Liang, Lei, Xiaokun, Fang, Cheng, Li, Yaxiong, Tang, Ming, Wang, Hu, Xie, Chong, Du, Changqing
Adaptive Multi-Agent Path Planning for UAV Formation Missions Based on MAPPO with Curriculum Learning and Graph Attention Networks2026-99-0615To be published on 11/06/2026
In high-end aerospace mission scenarios such as distributed sensing and tactical reconnaissance, path planning for multi-UAV cooperative formation flight has become an indispensable core component of mission systems. However, a key unresolved technical bottleneck remains: how to achieve an optimal balance between strictly maintaining the UAV formation’s preset geometric configuration and realizing collision-free, flexible flight in dynamically changing complex environments. Multi-Agent Reinforcement Learning (MARL) can theoretically solve this coupled optimization problem, but the control instructions generated by the existing mainstream MARL methods often have high-frequency fluctuation issues. Direct deployment of these fluctuating commands on physical UAV hardware will increase alternating stress on mechanical structures, raise the risk of motor overheating, and significantly boost battery energy consumption. These problems directly restrict the engineering application of such methods. To address the above challenges, this paper proposes a robust control framework that accounts for UAV physical characteristics to solve the model mismatch between simulation environments and real flight scenarios during carrier-based UAV deployment. Firstly, to improve the learning efficiency of the algorithm and avoid the cold start problem in the initial training stage, this paper introduces the Adaptive Curriculum Learning (ACL) method. Unlike the fixed-difficulty training mode, ACL can dynamically adjust the environmental complexity based on the real-time task performance of the UAVs. It first allows agents to master basic formation maintenance skills, before training is gradually transitioned to more complex tasks such as navigation in intricate environments. Additionally, considering the computational limitations of the onboard embedded processors of UAVs, this paper only integrates the Graph Attention Network (GAT) into the centralized Critic network of the centralized training and decentralized execution (CTDE) framework. The core advantage of this design is that the system no longer solely relies on distance as the judgment basis but assesses the influence of adjacent UAVs based on the collision risk level. This not only improves the accuracy of value estimation, but also does not compromise the response speed of local control instructions- a feature that is crucial for the real-time requirements of UAV flight control. The proposed method was tested and validated in a high-fidelity simulation environment built in strict compliance with UAV kinematic constraints. The experimental results fully demonstrate its superiority: in dense obstacle areas, the success rate of the task reached 80.4%; compared with the aggressive baseline method, the jerk was reduced by 10.9%. Most importantly, the flight trajectories generated by this framework are smooth and adaptable to actual flight conditions, and the corresponding control commands can be directly deployed on real flight controllers without additional parameter adjustments. This result demonstrates that the proposed framework achieves substantial technical progress in enhancing the autonomous response capabilities of UAV clusters to complex scenarios.
Huang, Xingyu, Zhang, Jiyu, Jiang, Yanshu, Fan, Yuhang
A Tail-Aware Enhanced YOLOv8 Framework for Robust Welding Defect Detection2026-99-0608To be published on 11/06/2026
In high-end manufacturing and aerospace equipment, reliable identification of welding defects is the key premise for intelligent fault diagnosis and structural health management because undetected or misclassified defects may lead to serious safety risks. However, the actual welding inspection scene is usually subject to some problems, such as limited training data, serious imbalance of categories, and low contrast of defect patterns, which significantly reduce the robustness of traditional vision-based inspection methods. In order to meet these challenges, this paper proposes a tail-sensing-enhanced welding defect detection framework based on YOLOv8, which is specifically aimed at the distribution of common long tail defects in industrial inspection tasks. On the premise of not changing the original network architecture, this method systematically enhances the learning ability of underrepresented defect categories through collaborative optimization in data, training, and loss levels. The specific measures include tailperceived data enhancement, convergence-oriented training strategy, and loss re-weighting of classification priority. The experimental results on multi-class welding defect datasets show that the proposed framework significantly reduces the false alarm rate and inter-class confusion of small samples and low contrast defects, and improves the reliability and robustness of the overall diagnosis. These results show that the proposed method provides an effective and practical solution for intelligent welding fault diagnosis and has great potential to be integrated into aerospace manufacturing quality inspection and health monitoring systems.
Fan, Yuhang, Zhang, Jiyu, Huang, Xingyu
A Hierarchical Optimization Strategy for On-Orbit Energy Management and Attitude Control of Spacecraft2026-99-0605To be published on 11/06/2026
This paper addresses an energy-optimal attitude control strategy for space solar power satellites (SSPSs) during on-orbit energy transmission missions. The study focuses on a space solar power generation and energy transmission experimental satellite as the research object. First, the attitude dynamics of the satellite are modeled using the Lagrange method, and the satellite’s attitude control actuators, namely the single-gimbal control moment gyroscopes (SGCMGs), are also modeled to capture their dynamic behavior and constraints. Second, a PD controller based on quaternion and angular velocity error feedback is designed to achieve the desired attitude necessary for the energy transmission task. Subsequently, a hierarchical optimization approach is developed to obtain the energy-optimal attitude control strategy over one orbital period, considering multiple factors such as the satellite’s on-orbit energy consumption, the energy collection efficiency of the solar array in non-shadow regions, and the energy transmission efficiency between the satellite and the ground station. The optimization process is divided into two levels. In the first level, within the ground station’s visibility window, an energy balance analysis at different potential transmission moments is performed to determine the optimal transmission timing that maximizes the energy received by the ground station. In the second level, during the energy transmission phase, a cost function is formulated that incorporates pointing accuracy, pointing stability, and actuator energy consumption, and the controller parameters are globally optimized using the Adaptive Particle Swarm Optimization (APSO) algorithm. The simulation results demonstrate that the proposed hierarchical optimization method can significantly enhance the operational efficiency of on-orbit energy transmission, providing a practical engineering approach for the efficient on-orbit operation of future space solar power stations.
Wang, Ke, Zhang, Ning, Ma, Wenlai, Zhao, Yang
Run Time Assurance Filter Framework for Collision Avoidance of Unmanned Aerial Vehicles Using Reinforcement Learning2026-99-0620To be published on 11/06/2026
In recent years, Reinforcement Learning (RL) has been increasingly applied to the collision avoidance systems of Unmanned Aerial Vehicles (UAVs) due to its high performance in complex tasks and relatively low online computational cost. Despite these advantages, the lack of interpretability in RL and decision-making processes poses significant challenges to safety verification, which severely limits the practical deployment of RL-based autonomous flight systems in safety-critical scenarios. Ensuring safety during both training and testing remains the key for real-world applications. To address this issue, a Run Time Assurance (RTA) filter framework for a UAV collision avoidance system based on RL is proposed. The framework continuously monitors the avoidance actions generated by RL and ensures that unsafe actions can be identified and corrected in real time. The framework provides security while retaining the performance advantages of RL. First, a discrete kinematics model of the UAV and a collision avoidance environment for a three-dimensional multi-intruder UAV are established. The Proximal Policy Optimization (PPO) algorithm is used to train the UAV avoidance policy. Secondly, the RTA filter with safe constraints is designed based on this model. To reduce the position error between the discrete kinematics model and the continuous dynamics model of the UAV, optimization is performed using the Sequential Least Squares Programming Method (SLSQP). The RTA is applied to the training and testing phases of UAV collision avoidance systems to monitor and correct unsafe actions online. Finally, three training and testing methods are set: no RTA, RTA without punishment, and RTA with punishment. Comparing different relaxation coefficients allows for analyzing their impact on filter performance. Simulation results demonstrate that the RTA effectively enhances safety throughout training and testing. Compared with the no RTA method, the collision rate is reduced by 7.04%, and the success rate is increased by 2.68%. In extreme collision avoidance scenarios, the average collision rate obtained by different reinforcement learning algorithms is reduced by 21.46%, and the average success rate is increased by 15.54%.
Ma, Zan, Yan, Liqin, Bai, Jie, Liu, Yubin, Sun, Shuguang
Model Predictive Formation of Multi-AAVs in Underground Utility Tunnels2026-99-0607To be published on 11/06/2026
As a core carrier of urban underground infrastructure, underground utility tunnels have an increasingly urgent demand for AAV swarm technology in operation and maintenance tasks such as internal pipeline inspection and fault diagnosis. However, the special environment of utility tunnels, characterized by GPS signal loss, narrow and enclosed space, and complex types of obstacles (including fixed pipeline supports and temporary construction components), poses severe challenges to AAV swarm operations. In this scenario, while maintaining the predetermined formation configuration, AAV swarms are required to complete three tasks simultaneously: accurately avoiding complex static obstacles in the tunnels, real-time evading other AAVs within the swarm to prevent intra-formation collisions, and strictly maintaining a safe distance from the tunnel walls. The superposition of these three constraints and the narrow operating space greatly increases the difficulty of swarm control. Traditional control methods often suffer from problems such as formation collapse, jerky obstacle avoidance, or wall scraping. To address the above pain points, this paper proposes an AAV swarm Model Predictive Control (MPC) method integrated with the Adaptive Perceptual Cauchy Mutation Pigeon-Inspired Optimization (APCMPIO) algorithm. This method optimizes the receding horizon parameters and constraint weights of model predictive control through the APCMPIO algorithm to achieve rapid response to complex dynamic scenarios, and embeds a dynamic safe distance threshold mechanism to balance formation integrity and individual safety. A simulation experiment was built for a utility tunnel inspection scenario with 6 AAVs. It significantly improves the operational adaptability and robustness of AAV swarms in constrained utility tunnel environments, providing reliable technical support for the swarm-based operation and maintenance of underground infrastructure.
Li, Tian-Qi, Ma, Lei, Liu, Yan-Jun, Li, Shu, Li, Dapeng, Liu, Lei
Rapid Thrust Evaluation of Solid Rocket Motor Nozzles Using Neural Network with Geometric Variations2026-99-0618To be published on 11/06/2026
To address the complexity of the influence of expansion-section geometry on the thrust performance of solid rocket motor nozzles and the low efficiency of numerical-simulation-based optimization, this study proposes a deep-learning-based method for rapid nozzle thrust prediction. With a representative 70-lb BATES nozzle as the research object, the expansion-section contour is parameterized using cubic spline functions. Combined with Latin hypercube sampling and two-dimensional inviscid numerical simulations, a nozzle geometry– thrust dataset covering a wide range of contour characteristics is constructed. On this basis, surrogate models based on a fully connected neural network, a one-dimensional convolutional neural network, and a two-dimensional convolutional neural network are developed, and the applicability of different network architectures to the nozzle thrust prediction task is systematically compared. The results demonstrate that convolutional neural networks outperform fully connected networks in terms of geometric feature representation capability and prediction stability. In particular, by explicitly modeling the spatial structural features of the nozzle contour, the two-dimensional convolutional model achieves a coefficient of determination close to unity on the test set, with an average relative error of 0.03%. Further hyperparameter sensitivity analysis clarifies the effects of batch size, number of training epochs, and learning rate on model convergence behavior and generalization performance. This work provides a feasible technical support for rapid thrust evaluation and efficient optimization-oriented nozzle design.
Yuan, Yuan, Wu, Wei-tao, Hua, Yue
A Flight Test Anomaly Detection Framework Based on Adaptive Weight Fusion2026-99-0606To be published on 11/06/2026
Flight anomaly detection plays a critical role in ensuring aviation safety. However, conventional anomaly detection methods often suffer from limited accuracy due to their reliance on single-sensor observations or fixed-weight multi-sensor fusion strategies. To address these limitations, this paper proposes an adaptive weight fusion framework for flight-test anomaly detection. The proposed framework integrates a signal-to-noise-ratio-based adaptive weighting strategy, an improved Kalman filtering algorithm, and an ensemble anomaly detection model within a hierarchical fusion architecture to achieve robust multi-sensor data fusion and anomaly identification. Experiments were conducted using the NASA DASHlink Tail_666_9 flight dataset. Compared with conventional methods, the proposed framework achieved improvements in overall accuracy, precision, recall, and F1-score. Specifically, the proposed method achieved an F1-score of 0.486 while reducing the average anomaly detection delay by more than 2 s. These results indicate that the proposed framework can improve the effectiveness and timeliness of flight anomaly detection, demonstrating its potential for real-time flight safety monitoring.
Wang, Yixin
GeoPR: Label-free LiDAR Place Recognition with Hybrid Geometric Graphs2026-99-1926To be published on 11/06/2026
LiDAR place recognition plays a crucial role in SLAM systems and robot localization. To address the drawback of existing hand-crafted descriptors—namely, their limited topological representation capability in complex scenes—and the high training cost and strong dependence of semantic-assisted methods, our study proposes a label-free hybrid geometric graph-based LiDAR place recognition algorithm, termed Geometric Place Recognition (GeoPR). GeoPR exploits the intrinsic geometric structural information of point clouds. Our algorithm adopts a preprocessing module to directly extract stable geometric primitives from raw point clouds as geometric nodes. On this basis, we design a hybrid geometric graph descriptor by introducing logarithmic distance weighting and Gaussian soft binning to enhance robustness against discretization errors and dynamic disturbances. During the matching process, our research adopts a two-stage “global search - geometric verification” framework: using a KD-tree for rapid candidate screening, followed by a geometric consistency verification module based on correspondences to eliminate false positive loop closures. Experiments on public datasets show that, without any training data or GPU acceleration, GeoPR achieves significantly higher precision and recall than mainstream hand-crafted methods, while its scene adaptability is comparable to advanced deep learning methods. Therefore, this work provides an efficient and reliable place-recognition solution for automatic driving and lightweight mobile robot platforms.
Cao, Bingyin, Zhang, Xudong
An Interactive Click-Based UAV Path Planning Method for Anti-Corrosion Spraying Using BIM-SLAM Fused 3D Models2026-99-0637To be published on 11/06/2026
To solve the critical challenges of uncoordinated operational node selection and premature mission termination caused by dynamic energy or coating depletion during anti-corrosion spraying on largescale steel structures, this paper proposes an advanced path planning methodology for UAVs. The proposed approach is built upon a BIMSLAM fusion model. Specifically, a high-fidelity three-dimensional (3D) environmental model is reconstructed by integrating offline BIM structural priors with real-time SLAM data. Furthermore, the framework implements the ICP algorithm and Kalman filtering simultaneously to eliminate point cloud noise and compensate for perceptual occlusions, thereby achieving a 5 cm localization accuracy in cluttered industrial environments. A dual-stage pipeline is established for pre-screening and dynamic evaluation. In the offline phase, geometrically inaccessible task points are identified and pruned via spatial accessibility analysis. During real-time operations, the onboard system continuously calculates the battery State of Charge (SoC), operational power, and remaining paint volume to eliminate inefficient flights. For the path generation stage, a hybrid search strategy is developed, which implements a Genetic Algorithm for task sequencing alongside a multi-objective cost function parameterized by four metrics: energy consumption, paint requirements, obstacle proximity, and task density. Additionally, Softmax is used to dynamically regulate the weight coefficients, enabling the system to balance operational safety and efficiency based on the instantaneous state vector. Finally, a fifth-order B-spline parameterization is used to maintain flight stability under complex wind disturbances and heavy time-varying payloads. Consequently, the results show that the proposed method significantly outperforms conventional baselines. The recorded 96.7% mission completion rate demonstrates its operational reliability for the maintenance of bridges and towers.
Qian, Lei, Huang, Chen, Tan, Libin, Huang, Tao
Design Strategy for Cislunar Space Navigation Constellations Based on Navigation and Autonomous Navigation Performance2026-99-0625To be published on 11/06/2026
This paper proposes a bi-objective design strategy for cislunar navigation constellations, simultaneously optimizing navigation performance for target users and the autonomous navigation performance of constellation itself. The design variables include orbital characteristic parameters and inter-satellite phases, while the objectives are defined as the worst-case Geometric/Position Dilution of Precision (GDOP/PDOP) for users and the constellation's aggregated Dynamic and Geometric Dilution of Precision (DAGDOP). To address phase jump issues, the optimization is formulated on a product manifold and solved using the Riemannian steepest descent algorithm via the Pymanopt toolbox. Three constellations are designed by this strategy, which are six-satellite constellation for the Lunar South Pole station, a twenty-satellite constellation for lunar surface and lunar orbit users, and an eight-satellite constellation for a LEO-to-DRO transfer trajectory. Simulation results demonstrate that the optimized designs achieve the required geometric visibility, maintain GDOP/PDOP below specified usable thresholds (e.g., max PDOP of 5.96 for the South Pole, max GDOP of 2.28 for the transfer), and exhibit stable autonomous navigation performance. The study confirms the feasibility of the proposed strategy for designing practical, high-performance navigation constellation deployments across diverse cislunar mission scenarios.
Chan, Meichen, Qiu, Haipeng, Hu, Jiaxin, Yang, Leping, Zhu, Yanwei, Chen, Yujie
Multi-Constraint Optimization-Based Perception and Trajectory Planning for Robotic Strand Cutting and Roughening in Box Girder Anchor Recesses2026-99-0634To be published on 11/06/2026
A robotic system that integrates prestressing-steel strand cutting with automated surface roughening was developed to address the high labor cost, harsh working conditions, and poor quality consistency encountered in anchor-hole operations for prefabricated box girders. To overcome perception bottlenecks in high-dust and strong-glare casting-yard environments, a coarse-to-fine, two-stage pose estimation method was proposed based on point-cloud semantic segmentation and geometric-feature constraints. A deep-learning network was employed to decouple and isolate regions of interest (ROIs), and a weighted ICP algorithm was applied to achieve submillimeter-level positioning. To mitigate mobile-chassis docking deviations and constrained workspace limitations, a multi-constraint trajectory-optimization model and an online re-planning strategy were implemented. Field experiments show that, under extreme conditions with point-cloud incompleteness up to 20%, the system yields a positioning error below 1.65 mm and a trajectory-tracking root-mean-square error (RMSE) consistently within 2.8 mm. While the automated process increases the operational speed by approximately 1.5 to 1.8 times compared to manual work, its primary value lies in eliminating occupational hazards and ensuring consistent processing quality, demonstrating significant engineering value.
Yi, Dongbo, Wang, Yong, Ma, Tengyue, Li, Yang, Liu, Daochang
An Intelligent Scheduling Optimization Method for High-Speed Railway Beam Yards Integrating Dijkstra Algorithm and Linear Programming2026-99-0636To be published on 11/06/2026
As the core facilities for prefabricated box girder production, highspeed railway beam yards are confronted with multiple practical challenges, including large-scale operation, intricate production processes, and frequent dynamic interferences in construction. Traditional manual scheduling methods are unable to achieve optimal allocation of production resources and efficient coordination of the entire production chain. In view of this problem, this paper proposes an intelligent scheduling optimization method that combines the Dijkstra algorithm with linear programming, and constructs a coordinated scheduling system that covers the whole process of “girder erection-girder fabrication-girder storage”. Supported by BIM+GIS digital twin technology, this system integrates multisource data from the Internet of Things (IoT) and production management platforms. In the system, the Dijkstra algorithm is used to dynamically plan the optimal path for girder erection, while a linear programming model is adopted to realize precise scheduling of production resources. Taking the production task of 1,672 box girders at the Baohui Beam Yard as an engineering application case, the results show that this method can improve the girder erection efficiency by 20%, raise the utilization rate of production resources by 15%, and reduce the process waiting time by 30%. It effectively solves the prominent problems of traditional scheduling, such as resource idleness and construction schedule delays, and thus provides theoretical support and practical reference for the development of intelligent construction 2.0 in high-speed railway beam yards.
Yi, Dongbo, Ma, Tengyue, Li, Yang, Yu, Ziqi, Li, Linsen
A Multimodal Perception Unmanned System Based on GNN and SLAM2026-99-0633To be published on 11/06/2026
The complex environments encountered in emergency rescue scenarios pose severe challenges to the perception and navigation capabilities of unmanned ground systems. This paper designs and implements a ground unmanned rescue system named "SkyEye" based on multimodal perception fusion. The system adopts a four-wheel independent steering and four-wheel drive (4WIS-4WID) omnidirectional ground chassis and integrates a 4D-FMCW LiDAR, structured-light binocular cameras, a high-precision IMU, and Beidou RTK. Through a tightly coupled graph-optimization SLAM framework and GNN-based dynamic obstacle prediction, it achieves robust perception and autonomous navigation in complex rescue scenarios. Experiments show that under clear open-field conditions, the system achieves centimeterlevel positioning accuracy and obstacle recognition accuracy ≥95%. In extreme dense smoke, recognition accuracy remains at 82.6% with stable navigation. The obstacle avoidance response latency is ≤0.5 s in narrow spaces and GNSS-denied tunnels. This paper elaborates the platform kinematic model, multi-sensor spatio-temporal calibration, detailed SLAM implementation, and complete GNN trajectory prediction pipeline, providing a theoretical basis and engineering reference for ground emergency rescue unmanned systems.
Li, Yizhen, Wei, Yuxiao, Wen, Yuanhao, Xun, Xuhang, Wang, Chengjun, Wu, Peng
Multi-Step Time Series Forecasting for Intermittent Demand Based on Transformer2026-99-0616To be published on 11/06/2026
Consumable spare parts for civil aircraft are characterized by intermittent demand patterns. Constrained by long order replenishment cycles, traditional single-step demand forecasting struggles to effectively support inventory decisions. Moreover, research on intermittent demand forecasting primarily focuses on single-step, short-term cycle predictions, while multi-step forecasting using advanced deep learning methods remains in its early stages. To address this issue, this study introduces a multi-step forecasting approach based on the Transformer architecture, employing a MIMO strategy to achieve long time series forecasting for intermittent demand. The model is validated using a dataset from an airline maintenance base consisting of 360 intermittent demand items. A comparative analysis is conducted against three traditional time series models (SES, Croston, and SBA) and several neural network architectures (FNN, GRU, and LSTM). The performance of different methods was compared using six evaluation metrics. Results demonstrate that the Transformer consistently delivers outstanding performance across various forecast horizons. Notably, in long-horizon forecasting tasks, the model’s advantage in prediction accuracy becomes increasingly significant as the forecast step increases.
Zhang, Zhaomin, Zhao, Xin, Zhang, Jian, Fu, Weifang
Comparative Analysis of BDS PPP-B2b on Shore-Based and Ship-Borne Platforms2026-99-0642To be published on 11/06/2026
The integration technology of autonomous navigation and positioning provides critical technical support for high-precision positioning in the marine environment. As an indispensable core technology in modern marine navigation, satellite navigation plays a vital role in marine navigation safety and precision operations, such as marine surveying, ship navigation, and offshore engineering. The BDS PPPB2b service is commonly used in the marine high-precision application. However, compared to the landing application, the BDS PPP in the marine environment performs poorly due to the complex environmental factors on the ship-borne platform, such as hull occlusion and sea surface signal reflection. To compare and analyze the positioning performance differences of BDS PPP-B2b between shore-based and ship-borne platforms, an experiment has been conducted by using real data of the BDS receiver on both shore-based and ship-borne platforms. The results have shown that the BDS PPPB2b positioning performance on a ship-borne platform achieves poor satellite visibility and stable positioning performance. The BDS PPPB2b positioning accuracy after convergence can reach centimeter and decimeter levels on shore-based and ship-borne platforms, respectively.
Wang, Xilong, Li, Menghao, Shi, Huiwen, Sun, Min, Lu, Yin
Research on the Construction of a Multi-Dimensional Fusion Vehicle Software Performance Testing System2026-99-1905To be published on 11/06/2026
1
Xu, Yaozong, Ju, Weinan, Zhao, Qiujun, Su, Yu, Liu, Yangyang
Research on UAV RF Signal Recognition Method Based on Deep Learning2026-99-2214To be published on 11/06/2026
In the field of unmanned aerial vehicle (UAV) signal recognition based on deep learning, complex electromagnetic environments pose severe challenges. Among them, interference suppression and recognition robustness under low signal-to-noise ratio (SNR) conditions are major research focuses. To tackle these issues, this paper proposes a robust radio frequency (RF) signal recognition method for UAVs. The method is built on an improved ResNet18 network. It separates the video transmission signals and control signals of UAVs, and adopts mixed-SNR training. These designs greatly strengthen the model’s ability to perform reliable recognition. First, the short-time Fourier transform (STFT) is used to convert UAV I/Q signals into time-frequency images. A refined time-frequency masking strategy is then adopted. This strategy separates and suppresses interference from control signals according to their bandwidth differences from video transmission signals, thus improving signal quality. Second, a squeeze-and-excitation (SE) channel attention module is embedded into each residual block of ResNet18. This structure enables the model to concentrate on critical features. The classification head is also rebuilt into a three-layer fully connected network to strengthen nonlinear transformation and complex feature interaction. Given the performance variation of the model across different SNR levels, a mixed-SNR training strategy is adopted. Fine grid search experiments are conducted to identify the optimal data distribution for maximizing recognition performance. Experimental results on the public DroneRFb-DIR dataset show that the improved ResNet18 model achieves a 3.07% increase in classification accuracy. The time-frequency masking method brings an extra performance gain of 1.08%. Although the mixed-SNR strategy causes a slight accuracy drop at the high SNR of 20 dB, it improves recognition accuracy by 8% to 53.01% within the low-SNR range of −10 dB to 10 dB. It also effectively reduces misclassification between different UAV types and enhances the model’s robustness. The proposed method provides a feasible solution for accurate and stable UAV signal recognition in complex electromagnetic scenarios.
Yu, Jiankun, Chen, Yongyou
Design of Lightweight Chaotic SM4 System for Low-Altitude Communication Networks2026-99-2207To be published on 11/06/2026
The deep integration of edge computing, blockchain, and UAV technology with the low-altitude economy has rapidly expanded the scale and scope of low-altitude communication networks. To support the rapid development of the low-altitude economy, the number of heterogeneous terminal devices is growing exponentially, posing new challenges to data transmission security within low-altitude data networks. Most UAVs and terminal devices adopt lightweight designs to maintain flight weight, resulting in limited computational and storage resources that cannot support mature cryptographic schemes. This vulnerability makes data collected by such devices susceptible to eavesdropping and tampering. Furthermore, standard symmetric encryption algorithms fail to decouple the spatio-temporal correlation of data within low-altitude networks, creating security risks of interception or modification in open low-altitude network environments. This paper designs and implements a highly secure, lightweight, low-altitude data encryption protection scheme based on the SM4 cryptographic algorithm and chaos theory. A hardware-software co-processing encryption system was developed on the ZYNQ platform. This solution introduces chaotic mappings into the SM4 key expansion phase in the software layer to enhance network security, while a cyclic reuse architecture and dual-buffer structure achieve low resource overhead algorithm acceleration on the programmable hardware layer, ensuring data throughput. Verification results from the FPGA-based test platform demonstrate that the proposed system exhibits effectiveness and efficiency under low resource overhead conditions. It can be deployed as an endpoint or additional module within low-altitude networks to safeguard data security.
Qin, Zhikang, Yu, Chengxiao, Chen, Xin, Liu, Ying
Dynamic SFC Deployment in Low-Altitude Communication Network with A3C and GAT2026-99-2206To be published on 11/06/2026
Low-altitude Communication Network (LCN) refers to network systems that employ drones and other low-altitude aerial platforms as carriers. Leveraging advanced communication technologies and data processing methodologies, these networks enable high-efficiency data transmission in low-altitude airspace, thus emerging as a pivotal driver for the advancement of the low-altitude economy. With the continuous advancement of Unmanned Aerial Vehicle (UAV), artificial intelligence, and communication technologies, LCN have been increasingly integrated into smart city construction, Internet of Things expansion, emergency management, and other fields. As a core component of these sectors, LCN have effectively driven the robust development of the low-altitude economy. Within the context of LCN, the efficient deployment of Service Function Chain (SFC) emerges as a critical factor in optimizing network service capabilities and enhancing resource utilization efficiency. In the dynamic and complex operating environment of LCN, reasonable and efficient SFC deployment can effectively coordinate the allocation of communication, computing, and storage resources, laying a solid foundation for the stable and high-quality operation of various network services. However, existing deployment algorithms either fail to fully consider the dynamic changes in the LCN or lack sufficient exploratory strategies, making them difficult to adapt to the diverse business scenarios within the LCN. To address the issue, our study proposes a dynamic SFC deployment method based on the Asynchronous Advantage Actor-Critic (A3C) and Graph Attention Network (GAT) algorithms. The experimental findings indicate that our proposed algorithm achieves a notable reduction in orchestration expenses, while simultaneously enhancing resource utilization, thus exhibiting excellent performance and robust adaptability in dynamic LCN environments.
Yang, Zihan, Yin, Jianhui, Yu, Chengxiao, Hu, Jinju, Liu, Ying
Items per page:
1 – 50 of 60704