数字人感系统的研究

随着飞机模拟器技术的发展,电机伺服系统在人感系统中也得到了广泛的应用。本文着重讨论 了以DSP芯片为核心的数字人感系统组成和工作原理,并分析了系统的特点及功能。     

面向飞机装配精准定位的状态感知技术

状态感知、实时分析、自主决策、精准执行是航空智能制造的特征。总结影响飞机部件装配单元定位精度的多种因素,并结合感知技术发展,深入分析部件装配单元的可感知因素及其获取方式,确定了部件装配单元可感知的关键要素:装配现场温度、定位器所受载荷、定位器位移、产品位姿。结合飞机机翼装配单元,设计感知信息获取方式。通过模糊优选方法,构建传感器型号优选模型,完成部件装配单元传感器选型。通过传感器测量偏差平均化的方法,构建多种类、多数量的传感器布局模型,确定部件装配单元传感器的数目与位置,完成了传感器布局设计。基于多传感器信息融合方法,设计多传感器信息融合模型,对感知的多源异构信息进行融合处理,并通过构建状态感知模型,实现对部件装配单元定位状态的直观表达。     

The benefits brought by space—General public versus space agencies perspectives

Space agencies and governments have been long striving to find justification for the budgets allocated to non-commercial space missions. The most frequent justifications were scientific discoveries, technological development as well as national prestige. The current study aims to have a different look at the question “Which are the benefits brought by space?” by investigating/sampling/interrogating the public opinion and identifying the perception and view of the generation that form the bulk of the taxpaying citizens for the immediate future and will be actively financing any future missions. The study focuses on the answers provided to an online survey by an international sample of population. The target individuals are in the age range of 25–44 and are users of social networks. They are either employed or students, but they are not directly involved with the space sector. The survey aims to establish whether the promotional activities of ESA, NASA and other space agencies are aligned with the perceived benefits of this sample population. Is space contributing to what the target people consider important? What could be done to improve/change this perception? How did the public perception evolve? Which are the biggest problems humanity is confronted with today according to the sample population? Could space help addressing these major problems? The paper will firstly present the statistical analysis of the sample answers and the conclusions that can be drawn from them. In a second step it will compare the perceptions and expectations of the public in regards to space with the current space agencies strategies and identify the gaps and discontinuities.     

由感知到动作决策一体化的类脑导航技术研究现状与未来发展

随着脑与神经科学以及人工智能技术的持续发展，昆虫和哺乳动物大脑导航机理启发下的感知/认知/路径规划/动作决策一体化类脑导航技术得到了较大发展，可以实现由原始感知信息输入到导航动作决策的直接输出，呈现出接近动物端到端面向目标导航的智能行为，具有提高密集型无人机集群导航鲁棒性、准确性、实时响应动作、自主智能性以及计算效率的潜力。阐述了昆虫和哺乳动物大脑导航机理及其互补对称关系，以及昆虫和哺乳动物大脑导航机理启发的端到端类脑导航技术内涵；论述了类脑导航技术研究进展，包括类脑环境感知、类脑空间认知、面向目标类脑导航；分析了类脑导航向智能化、神经形态系统以及群体导航发展的新趋势；最后讨论了类脑导航技术应用于无人机密集集群系统时存在的挑战。     

飞机智慧座舱发展技术研究

未来飞机座舱智慧化转型是必然趋势,研究飞机智慧座舱发展技术能够为未来飞机智慧座舱的设计提供参考支撑。本文探讨了智能与智慧的区别,提出了飞机智慧座舱的概念与设计内涵,总结出深度感知与沉浸式交互、类人的认知及开放性与个性化定制服务的智慧座舱功能设计要素;梳理了发展飞机智慧座舱亟需解决的五项关键技术：多维度深度信息感知与融合技术、先进信息显示技术、沉浸式自然交互技术、智能态势认知技术、多智能体自主适应技术。通过关键技术的分析对未来飞机智慧座舱的发展提出了新的思考。     

A distributed approach for lidar-based relative state estimation of multi-UAV in GPS-denied environments

In this paper, we present a distributed framework for the lidar-based relative state estimator which achieves highly accurate, real-time trajectory estimation of multiple Unmanned Aerial Vehicles(UAVs) in GPS-denied environments. The system builds atop a factor graph, and only onboard sensors and computing power are utilized. Benefiting from the keyframe strategy, each UAV performs relative state estimation individually and broadcasts very partial information without exchanging raw data. The com...     

基于非线性直方图变换的对比度畸变图像校正

在实际成像过程中,因受多种因素影响而导致图像对比度畸变,使其质量下降。为了改善图像质量并增强视觉效果,提出了一种基于非线性直方图变换与参数优化的降质图像对比度畸变校正方法。首先,针对常规直方图均衡方法的局限性,通过人眼视觉感知特性分析,引入图像直方图的先验约束条件,建立了非线性直方图变换模型;进而,从校正效果的最优化角度考虑,运用遗传算法的进化寻优进行校正参数的优化,从而形成了一种高性能的对比度畸变校正算法。一系列在不同场景实拍的对比度严重畸变图像的校正实验结果表明,本文方法校正结果的客观质量评价测算指标和实际视觉效果都有显著提升,和常规校正方法相比具有明显优势。      

带QoP反馈的实时视频服务质量控制框架

分析了实时视频在现有"尽力而为"IP网络上传输所面临的带宽、延迟和丢失等问题,介绍了需要采用的拥塞控制和差错控制等应用级服务质量控制策略,并提出了一种联合的支持应用级服务质量控制的实时视频传输框架.该框架既考虑了网络资源的动态变化和影响,又兼顾了视频的服务质量调整对视频的表现质量的限制因素,充分利用了服务质量和表现质量之间的映射关系,具有更广泛的实用价值.      

Shadow detection for mobile robots: Features,evaluation, and datasets

ABSTRACT

Shadows have long been a challenging topic for computer vision. This challenge is made even harder when we assume that the camera is moving, as many existing shadow detection techniques require the creation and maintenance of a background model. This article explores the problem of shadow modelling from a moving viewpoint (assumed to be a robotic platform) through comparing shadow-variant and shadow-invariant image features — primarily color, texture and edge-based features. These features are then embedded in a segmentation pipeline that provides predictions on shadow status, using minimal temporal context. We also release a public dataset of shadow-related image sequences, to help other researchers further develop shadow detection methods and to enable benchmarking of techniques.     

基于相关滤波器的嵌入式动态目标跟踪系统设计

针对空间非合作运动目标监控，提出了一种基于嵌入式技术的动态目标实时检测与跟踪方法，并完成了跟踪系统的研制设计和测试。该视觉目标跟踪系统以嵌入式处理器为控制器，通过相机模组获取实时视频图像，图像经过视觉检测与跟踪算法程序分析，得到目标的位置信息后，控制伺服运动系统调整相机姿态实现对动态目标跟踪。提出了基于相关滤波原理的跟踪算法，搭建了树莓派嵌入式测试系统，完成实时检测与跟踪的实验评估。实验结果表明，嵌入式处理器中检测与跟踪程序的平均运行帧率达到25FPS，伺服机构在水平360°和俯仰±60°范围内实现了对移动速度90°/s的目标的实时、稳定监控与跟踪。