Pre-locate net for object detection in high-resolution images

Small-object detection has long been a challenge. High-megapixel cameras are used to solve this problem in industries. However, current detectors are inefficient for high-resolution images. In this work, we propose a new module called Pre-Locate Net, which is a plug-and-play structure that can be combined with most popular detectors. We inspire the use of classification ideas to obtain candidate regions in images, greatly reducing the amount of calculation, and thus achieving rapid detection in high-resolution images. Pre-Locate Net mainly includes two parts, candidate region classification and behavior classification. Candidate region classification is used to obtain a candidate region, and behavior classification is used to estimate the scale of an object. Different follow-up processing is adopted according to different scales to balance the variance of the network input. Different from the popular candidate region generation method, we abandon the idea of regression of a bounding box and adopt the concept of classification, so as to realize the prediction of a candidate region in the shallow network. We build a high-resolution dataset of aircraft and landing gears covering complex scenes to verify the effectiveness of our method. Compared to state-of-the-art detectors (e.g., Guided Anchoring, Libra-RCNN, and FASF), our method achieves the best mAP of 94.5 on 1920 × 1080 images at 16.7 FPS.     

全自动主着陆/着舰引导数据解算与融合算法

针对舰载机全自动自主着陆/着舰对飞机定位精确要求高的需求,提出了一种利用卫星导航和雷达联合进行信息融合精确定位算法。文章采用载波相位差分定位、野值剔除和序贯异类数据融合技术,有效提高了对飞机的定位引导精度和可靠性。     

基于VR-Forces的舰载机起飞与降落仿真

VR-Forces是当前较为成熟的计算机生成兵力仿真平台,使用该平台可实现舰载机在航空母舰上起飞和降落仿真。在该仿真平台中舰载机起飞和降落的主要原理的基础上,阐述了舰载机搭载(卸载)组件和航空母舰占用引导控制组件的功能、类继承关系和配置方法,分析了舰载机起飞降落过程中的仿真流程。通过测试想定实现了F/A-18舰载机滑行、起飞、降落、停靠整个流程。研究成果对基于VR-Forces的作战仿真和开发类似系统有一定的技术参考价值。     

某高速着陆无人机方向舵纠偏控制设计及性能分析

无人机高速着陆过程中,由于侧风或初始干扰导致的滑跑侧偏极其危险。基于高速状态下方向舵纠偏效率高的特点,建立某无人机高速着陆动力学模型,设计方向舵纠偏控制策略,并基于Matlab/Simulink平台建立无人机滑跑非线性动力学模型及方向舵纠偏控制模型;对具有初始1°偏航角和1m/s持续垂直侧风情况下的无人机着陆工况进行仿真分析,并通过控制着陆速度、着陆初始姿态角和侧风强度,分析纠偏控制系统的性能。结果表明:所设计的纠偏控制系统具有一定的航向纠偏和抗持续侧风能力,最大侧偏距小于3 m,偏航角小于5°,较好地实现了高速滑跑阶段的侧向纠偏性能。     

动力增升对翼身融合飞机沉降特性的改善

翼身融合体飞机起降阶段的“沉降问题”是影响该类布局飞行安全的典型问题，为此提出了一种将动力风扇竖直嵌入机翼中的动力增升方案。分析了动力增升系统对飞行的气动影响，提出了动力增升系统的匹配设计和评价方法，探讨了动力增升系统布局的主要约束。在综合考虑动力增升系统推质比、俯仰力矩配平以及操稳特性等限制因素基础上，基于示例翼身融合体无人机，匹配设计了动力增升系统及其布局方案，针对过渡飞行状态设计了姿态稳定控制律。飞行试验表明:使用动力增升能缓解进近阶段升降舵操纵所引起的下沉率突增与高度沉降现象，同时可将验证机的起、降速度降低20%以上，且该方案易于在小型翼身融合体飞机上实现。      

基于局部应力-应变法的飞机起落架车架寿命分析

起落架是飞机结构中的重要组成部分,是飞机的主要承力构件,其工作性能直接影响飞机的起飞性能、着陆性能和安全。首次翻修寿命是一个非常重要的安全参数,而飞机起落架车架是决定起落架翻修寿命的关键构件。本文应用局部应力-应变法的原理,研究在循环载荷条件下某起落架的疲劳(裂纹形成)寿命,并对其裂纹形成寿命和出现裂纹后的剩余强度进行了估算,进而从疲劳断裂方面提出了延长该主起落架首次翻修寿命的理论依据。     

The effect of a rocky terrain for CubeSat landing on asteroid surfaces

The paper describes a general modelling procedure to build a simulation tool to investigate contact motion of a CubeSat on an asteroid surface. We investigate landing performance and landing success for the case of elastic rocky terrain and flat surfaces. As a case study, we focus on the disposal of ESA’s Hera Milani CubeSat by landing on the moon of Didymos binary asteroid system. The simulation environment includes the modelling of real shape and 6-DOF motion of the lander, the shape-based gravity models of Didymos and Dimorphos and rocks on surface, that are generated as physical obstacles. Trends and estimates on the performance of the landing phase and the most relevant effects on the outcome of the soil interaction process, are inferred. The statistical results on settling time, dispersion area and motion characteristics, such as number of bounces, show and quantify the effect of rocks on a successful passive and permanent landing.     

Optimal crater landmark selection based on optical navigation performance factors for planetary landing

Planetary craters are natural navigation landmarks that widely exist and are easily observed. Optical navigation based on crater landmarks has become an important autonomous navigation method for planetary landing. Due to the increase in observed crater landmarks and the limitation of onboard computation, the selection of good crater landmarks has gradually become a research hotspot in the field of landmark-based optical navigation. This paper designs a fast crater landmark selection method, which not only considers the configuration observability of crater subsets but also focuses on the influence on navigation performance arising from the measurement uncertainty and the matching confidence of craters, which is different from other landmark selection methods. The factor of measurement uncertainty, which is anisotropic, correlated and nonidentically distributed, is quantified and integrated into selection based on crater pairing detection and localization error evaluation. In addition, the concept of the crater matching confidence factor is introduced, which reflects the possibility of 2D projection measurements corresponding to 3D positions. Combined with the configuration observability factor, the crater landmark selection indicator is formed. Finally, the effectiveness of the proposed method is verified by Monte Carlo simulations.     

月表陨坑检测轻量化深度学习方法

针对目前基于深度学习的陨坑检测方法存在的模型参数量大和检测速度慢的问题，提出了一种轻量化的深度学习陨坑检测方法。首先，采用通道剪枝方法删减卷积神经网络中冗余的卷积核，得到结构紧凑高效的陨坑检测模型。然后，使用轻量化的深度可分离卷积操作替换基础陨坑检测模型中的标准卷积操作，进一步降低了模型的复杂度。仿真实验结果表明，所提出的轻量化陨坑检测模型能够保证较高的像素预测精度，并且能够适应亮度、图像噪声等干扰因素的影响。同时，与轻量化处理前的模型相比，参数量减少了99.2%，检测速度提升了94%。     

基于自适应预测校正的月球软着陆制导控制方法

应用自适应预测制导方法，研究月球软着陆过程中的制导控制问题。作为一种具有逻辑结构的构造性方法，本文概述了自适应预测制导方法的实现步骤。针对月球软着陆过程中制导控制量少于被控制量这一“欠驱动”问题，在已有的基于一阶特征模型的全系数自适应预测校正方法的基础上，将输入输出相等的系统拓展为输入少于输出的“欠驱动”系统，以满足对位置、速度矢量同时进行制导控制的需要。本文针对初始状态误差、推力偏差、质量偏差以及比冲偏差下的软着陆过程，进行了Monte Carlo仿真分析，结果表明，自适应预测制导方法可有效用于月球软着陆过程的制导控制，且具有较高的精度和较强的鲁棒性。