Joint mission and route planning of unmanned air vehicles via a learning-based heuristic

Unmanned air vehicles(UAVs) have been regularly employed in modern wars to conduct different missions. Instead of addressing mission planning and route planning separately,this study investigates the issue of joint mission and route planning for a fleet of UAVs. The mission planning determines the configuration of weapons in UAVs and the weapons to attack targets, while the route planning determines the UAV’s visiting sequence for the targets. The problem is formulated as an integer linear programming model. Due to the inefficiency of CPLEX on large scale optimization problems, an effective learningbased heuristic, namely, population based adaptive large neighborhood search(P-ALNS), is proposed to solve the model. In P-ALNS, seven neighborhood structures are designed and adaptively utilized in terms of their historical performance. The effectiveness and superiority of the proposed model and algorithm are demonstrated on test instances of small, medium and large sizes. In particular, P-ALNS achieves comparable solutions or as good as those of CPLEX on small-size(20 targets)instances in much shorter time.

An Air Route Planning Model of Unmanned Aerial Vehicles Under Constraints of Ground Safety

With the rapid growth of the number and flight time of unmanned aerial vehicles(UAVs),safety accidents caused by UAVs flight risk is increasing gradually.Safe air route planning is an effective means to reduce the operational risk of UAVs at the strategic level.The optimal air route planning model based on ground risk assessment is presented by considering the safety cost of UAV air route.Through the rasterization of the ground surface under the air route,the safety factor of each grid is defined with the probability of fatality on the ground per flight hour as the quantitative index.The air route safety cost function is constructed based on the safety factor of each grid.Then,the total cost function considering both air route safety and flight distance is established.The expected function of the ant colony algorithm is rebuilt and used as the algorithm to plan the air routes.The effectiveness of the new air route planning model is verified through the logistical distribution scenario on urban airspace.The results indicate that the new air route planning model considering safety factor can greatly improve the overall safety of air route under small increase of the total flight time.

Optimal confrontation position selecting games model and its application to one-on-one air combat

In the air combat process,confrontation position is the critical factor to determine the confrontation situation,attack effect and escape probability of UAVs.Therefore,selecting the optimal confrontation position becomes the primary goal of maneuver decision-making.By taking the position as the UAV’s maneuver strategy,this paper constructs the optimal confrontation position selecting games(OCPSGs)model.In the OCPSGs model,the payoff function of each UAV is defined by the difference between the comprehensive advantages of both sides,and the strategy space of each UAV at every step is defined by its accessible space determined by the maneuverability.Then we design the limit approximation of mixed strategy Nash equilibrium(LAMSNQ)algorithm,which provides a method to determine the optimal probability distribution of positions in the strategy space.In the simulation phase,we assume the motions on three directions are independent and the strategy space is a cuboid to simplify the model.Several simulations are performed to verify the feasibility,effectiveness and stability of the algorithm.

Online Multi-Object Tracking Under Moving Unmanned Aerial Vehicle Platform Based on Object Detection and Feature Extraction Network

In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion module is studied.Furthermore,a joint network of object detection and feature extraction is studied to construct a real-time multi-object tracking algorithm.For the problem of object association failure caused by UAV movement,image registration is applied to multi-object tracking and a camera motion discrimination model is proposed to improve the speed of the multi-object tracking algorithm.The simulation results show that the algorithm proposed in this study can improve the accuracy of multi-object tracking under the UAV platform,and effectively solve the problem of association failure caused by UAV movement.

Improved Weighted Local Contrast Method for Infrared Small Target Detection

In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).

Small objects detection in UAV aerial images based on improved Faster R-CNN

In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.

Adaptive cropping shallow attention network for defect detection of bridge girder steel using unmanned aerial vehicle images

Bridges are an important part of railway infrastructure and need regular inspection and maintenance.Using unmanned aerial vehicle(UAV)technology to inspect railway infrastructure is an active research issue.However,due to the large size of UAV images,flight distance,and height changes,the object scale changes dramatically.At the same time,the elements of interest in railway bridges,such as bolts and corrosion,are small and dense objects,and the sample data set is seriously unbalanced,posing great challenges to the accurate detection of defects.In this paper,an adaptive cropping shallow attention network(ACSANet)is proposed,which includes an adaptive cropping strategy for large UAV images and a shallow attention network for small object detection in limited samples.To enhance the accuracy and generalization of the model,the shallow attention network model integrates a coordinate attention(CA)mechanism module and an alpha intersection over union(α-IOU)loss function,and then carries out defect detection on the bolts,steel surfaces,and railings of railway bridges.The test results show that the ACSANet model outperforms the YOLOv5s model using adaptive cropping strategy in terms of the total mAP(an evaluation index)and missing bolt mAP by 5%and 30%,respectively.Also,compared with the YOLOv5s model that adopts the common cropping strategy,the total mAP and missing bolt mAP are improved by 10%and 60%,respectively.Compared with the YOLOv5s model without any cropping strategy,the total mAP and missing bolt mAP are improved by 40%and 67%,respectively.

基于UAV-RS虚拟仿真系统的教学模式探究

针对无人机和遥感测绘(unmanned air vehicle for remote sensing,UAV-RS)相关专业在实际教学中存在的问题,如设备资源和实验时间无法满足学生需求,野外作业中无人机的安全难以管控,天气和环境条件要求苛刻等,以无人机遥感测绘外业为仿真对象,设计开发了虚拟仿真系统,改革实训教学模式。仿真系统确立了无人机飞行操控、地面场景模拟和遥感图像获取3个模块,引导学生自主完成无人机遥感测绘外业过程。评估实验中经过仿真系统学习的学生(实验组)的项目完成率为:初级90%、中级80%、高级75%,均明显高于对照组。表明基于仿真系统的教学模式可提升UAV-RS的外业教学效果,提高复杂项目完成率,并能够激发学生自主学习的积极性。

Gradient Descent Algorithm for Small UAV Parameter Estimation System

A gradient descent algorithm with adjustable parameter for attitude estimation is developed,aiming at the attitude measurement for small unmanned aerial vehicle(UAV)in real-time flight conditions.The accelerometer and magnetometer are introduced to construct an error equation with the gyros,thus the drifting characteristics of gyroscope can be compensated by solving the error equation utilized by the gradient descent algorithm.Performance of the presented algorithm is evaluated using a self-proposed micro-electro-mechanical system(MEMS)based attitude heading reference system which is mounted on a tri-axis turntable.The on-ground,turntable and flight experiments indicate that the estimation attitude has a good accuracy.Also,the presented system is compared with an open-source flight control system which runs extended Kalman filter(EKF),and the results show that the attitude control system using the gradient descent method can estimate the attitudes for UAV effectively.

基于上下文信息与特征细化的无人机小目标检测算法

无人机航拍图像中的目标检测是近年来研究的热点,针对无人机视角下目标小而密集、背景复杂导致检测精度低的问题,提出一种基于上下文信息与特征细化的无人机小目标检测算法。通过上下文特征增强模块,利用多尺度扩张卷积捕获与周围区域像素点的潜在关系,为网络补充上下文信息,并根据不同尺度的特征层自适应生成各层级特征图的输出权重,动态优化特征图表达能力;由于不同特征图细粒度不同,使用特征细化模块来抑制特征融合中冲突信息的干扰,防止小目标特征淹没在冲突信息中;设计了一种带权重的损失函数,加快模型收敛速度,进一步提高小目标检测精度。在VisDrone2021数据集进行大量实验表明,改进后的模型较基准模型mAP50提高8.4个百分点,mAP50:95提高5.9个百分点,FPS为42,有效提高了无人机航拍图像中小目标的检测精度。

高阶深度可分离无人机图像小目标检测算法

当前无人机图像中存在小目标数量众多、背景复杂的特点,目标检测中易造成漏检误检率较高的问题,针对这些问题,提出一种高阶深度可分离无人机图像小目标检测算法.首先,结合CSPNet结构与ConvMixer网络,深度可分离卷积核,获取梯度结合信息,并引入递归门控卷积C3模块,提升模型的高阶空间交互能力,增强网络对小目标的敏感度;其次,检测头采用两个头部进行解耦,分别输出特征图分类和位置信息,加快模型收敛速度;最后,使用边框损失函数EIoU,提高检测框精准度.在VisDrone2019数据集上的实验结果表明,该模型检测精度达到了35.1%,模型漏检率和误检率有明显下降,能够有效地应用于无人机图像小目标检测任务.在DOTA 1.0数据集和HRSID数据集上进行模型泛化能力测试,实验结果表明,该模型具有良好的鲁棒性.

Unmanned air/ground vehicles heterogeneous cooperative techniques:Current status and prospects

Multiple unmanned air/ground vehicles heterogeneous cooperation is a novel and challenging filed.Heterogeneous cooperative techniques can widen the application fields of unmanned air or ground vehicles,and enhance the effectiveness of implementing detection,search and rescue tasks.This paper mainly focused on the key issues in multiple unmanned air/ground vehicles heterogeneous cooperation,including heterogeneous flocking,formation control,formation stability,network control,and actual applications.The main problems and future directions in this field were also analyzed in detail.These innovative technologies can significantly enhance the effectiveness of implementing complicated tasks,which definitely provide a series of novel breakthroughs for the intelligence,integration and advancement of future robot systems.

基于无人机巡检与深度学习的河道整治施工进度图像识别

长线性小流域治理工程中的河道衬砌、生态护岸等距离长、范围广、布置分散,且工区交通不便,人工巡检费时费力,难以及时掌握工程的整体施工进度形象面貌。提出了基于无人机巡检与深度学习的河道整治施工进度智能图像识别方法,通过定位施工节点(施工区域起点和终点)的位置计算施工进度。首先,建立了施工区域目标检测模型,针对无人机航拍影像进行河道衬砌护岸施工区域的识别以及施工节点的定位;然后,利用尺度不变特征变换(scale-invariant feature transform,SIFT)算法对不同视频帧中的施工节点进行匹配,并基于单目视觉的运动视差法,计算施工节点的实际工区坐标;最后,计算当前衬砌护岸施工进度,并分析进度偏差。结果表明:该方法得到的施工节点定位平均误差为1.026 m,平均相对误差为0.74%,该方法能够较为准确地从航拍图像中识别得到当前衬砌护岸的施工进程,从而实现长线性工区快速巡检,及时掌控现场施工进度,提高工程管理的智能化水平。

基于通信信号管制的城市空中交叉口设计研究

为确保城市低空空域内无人机规模化运行安全,缓解低空交通运行瓶颈,本文借鉴地面交通较为成熟的研究成果,结合城市低空及无人机运行特色,提出一种基于通信信号管制的城市空中交叉口设计模型。首先,考虑航路构型设计与航路运行主体,构建无人机运行所需的城市低空航路。其次,从进出口道、冲突响应距离2方面对空中交叉口几何结构进行设计,再从进口航道划分、通信信号管制、无人机高度调整3方面对交通组织进行设计,实现对空中交叉口的基本模型设计。最后,设置仿真实验验证该模型的可行性,并分析不同参数组合下的交叉口综合通行效率。实验结果表明:当飞行速度为18 m/s,纵向间隔为50 m,管制信号周期时长为226 s时,综合通行效率达到最佳。本研究可为未来城市空中交通航路网络精细划设与管理提供支撑,增强低空无人机交通的实践性。

基于需求的城市低空无人机航路网络构建方法

针对城市低空无人机运行需求不断增加的问题,综合考虑城市区域交通需求、空域环境以及无人机性能等限制条件,以最小化网络节点、最大化覆盖需求点和需求量为目标,提出了一种城市低空无人机航路网络构建方法.建立网络节点生成模型和航路网络构建模型;通过改进的greedy算法生成网络节点;结合使用k近邻(k-Nearest Neighbor,K-NN)和Prims算法构建无人机航路网络;选取上海地区物流业务需求量数据进行仿真验证,并运用复杂网络相关指标分析所构建的航路网络性能.结果表明:本文提出的城市低空无人机航路网络构建方法可以同时实现干线和支线航路网络的构建,且干线航路网络实现了网络全连通,还可以结合无人机任务需求设置网络节点实现航路网络灵活规划.

Bearing-only Visual SLAM for Small Unmanned Aerial Vehicles in GPS-denied Environments

This paper presents a hierarchical simultaneous localization and mapping（SLAM） system for a small unmanned aerial vehicle（UAV） using the output of an inertial measurement unit（IMU） and the bearing-only observations from an onboard monocular camera.A homography based approach is used to calculate the motion of the vehicle in 6 degrees of freedom by image feature match.This visual measurement is fused with the inertial outputs by an indirect extended Kalman filter（EKF） for attitude and velocity estimation.Then,another EKF is employed to estimate the position of the vehicle and the locations of the features in the map.Both simulations and experiments are carried out to test the performance of the proposed system.The result of the comparison with the referential global positioning system/inertial navigation system（GPS/INS） navigation indicates that the proposed SLAM can provide reliable and stable state estimation for small UAVs in GPS-denied environments.

基于改进YOLOX的无人机航拍图像小目标检测算法

在无人机上运用目标检测技术具有广泛的应用前景,但和自然拍摄的图像不同,无人机航拍的图像更加复杂,且大多数为小目标。而现有的检测算法缺乏对小目标的特征提取能力,从而导致严重的误检和漏检问题。针对上述问题,提出一种基于YOLOX框架的高效的无人机小目标检测算法。首先,在特征融合网络中增加一层检测微小目标的特征融合结构,通过利用浅层特征图中丰富的位置信息和轮廓信息来加强网络对小目标的识别能力;同时,为了防止额外参数的增加,将减少头网络中的一层卷积层并缩减其通道数。其次,提出一种通道-空间注意力机制模块(Channel Spatial Attention Module,CSAM),利用最优的权重分配使网络聚焦于特征图中小目标密集的区域。最后,提出一种带位置引导的标签分配策略(LB-SimOTA),根据每个预测框和真实框的交并比(IOU)的大小,分别配以不同的权重,以改善网络中整体预测框的质量。在小目标居多的数据集VisDrone2019上的实验结果表明,文中提出的算法和YOLOX-S相比,针对车和人的检测精度提升了8.63%,检测速度FPS也可达到86,因此更适合在无人机对地面小目标检测的场景下部署。

无人机辅助智能边缘网络技术综述

简要介绍了无人机作为空基信息平台的主要应用场景,结合6G多接入网络和用户为中心网络架构,讨论了无人机在构建智能边缘网络中的重要作用。结合无人机平台在不同场景下的通、感、算能力特点,介绍无人机自组网、无人机通感一体化、无人机边缘计算等无人机辅助智能边缘网络关键技术。最后,围绕无人机在构建智能边缘网络过程中与无线接入网新技术结合时产生的新问题,探讨无人机通信信道建模、三维立体部署与路径规划、携能有限与续航问题、无人机网络安全、无人机集群异构网络融合等关键技术挑战和未来研究方向。

面向无人机视角下小目标检测的YOLOv8s改进模型

从无人机视角进行目标检测,面临图像目标小、分布密集、类别不均衡等难点,且由于无人机的硬件条件限制了模型的规模,导致模型的准确率偏低。提出一种融合多种注意力机制的YOLOv8s改进模型,在骨干网络中引入感受野注意力卷积和CBAM(concentration-based attention module)注意力机制改进卷积模块,解决注意力权重参数在感受野特征中共享问题的同时,在通道和空间维度加上注意力权重,增强特征提取能力;通过引入大型可分离卷积注意力思想,改造空间金字塔池化层,增加不同层级特征间的信息交融;优化颈部结构,增加具有丰富小目标语义信息的特征层;使用inner-IoU损失函数的思想改进MPDIoU(minimum point distance based IoU)函数,以innerMPDIoU代替原损失函数,提升对困难样本的学习能力。实验结果表明,改进后的YOLOv8s模型在VisDrone数据集上mAP、P、R分别提升了16.1%、9.3%、14.9%,性能超过YOLOv8m,可以有效应用于无人机平台上的目标检测任务。

高分辨率特征增强的无人机航拍小目标检测

针对无人机航拍图像背景复杂、小尺寸目标分布密集等造成的检测精度低等问题,提出一种高分辨率特征增强的无人机航拍小目标检测算法。首先,提出了高分辨率特征增强网络,通过减少主干网络的下采样倍数来扩大输出特征图的尺度,同时引入双线性插值法来减少采样后特征信息的丢失,从而保留更多语义特征与细节特征。其次,在主干网络嵌入一种结合局部跨阶段结构的快速空间金字塔池化(Spatial pyramid pooling fast cross stage partial construction,SPPFCSPC)模块,增强局部与全局特征的信息融合,从而获得更大的感受野。最后,通过马赛克混合数据增强方法来增强图像背景的复杂度,提高模型的泛化能力。在公开数据集VisDrone 2019上的实验结果表明,与“你只需看一次”(You only look once,YOLO)系列等其他主流算法相比,本文算法的平均精度均值有显著的提高,在不同场景下均验证了本文算法的优越性,表明本文算法对无人机航拍图像的密集小目标检测任务有较强的实用性。