小卫星技术的若干进展

本文评述了国际上应用小卫星在结构、电源和操作系统等领域新近的若干进展.在结构方面侧重于新材料、新器件和新工艺的介绍;在新型电源方面包括了有关太阳电池和蓄电池的内容;在操作系统方面强调了自主控制领域中的新观念和新方案.     

Deep learning enabled localization for UAV autolanding

This article concentrates on ground vision guided autonomous landing of a fixed-wing Unmanned Aerial Vehicle (UAV) within Global Navigation Satellite System (GNSS) denied environments. Cascaded deep learning models are developed and employed into image detection and its accuracy promoting for UAV autolanding, respectively. Firstly, we design a target bounding box detection network BboxLocate-Net to extract its image coordinate of the flying object. Secondly, the detected coordinate is fused into spatial localization with an extended Kalman filter estimator. Thirdly, a point regression network PointRefine-Net is developed for promoting detection accuracy once the flying vehicle’s motion continuity is checked unacceptable. The proposed approach definitely accomplishes the closed-loop mutual inspection of spatial positioning and image detection, and automatically improves the inaccurate coordinates within a certain range. Experimental results demonstrate and verify that our method outperforms the previous works in terms of accuracy, robustness and real-time criterions. Specifically, the newly developed BboxLocate-Net attaches over 500 fps, almost five times the published state-of-the-art in this field, with comparable localization accuracy.     

基于.NET平台的中小型企业车间生产管理系统

分析了典型中小型企业车间生产的特点,总结出一套切实可行的车间生产管理系统解决方案.该方案基于B/S架构,所开发的系统从易用性和效率上都有很大的提高.     

基于优化最小二乘支持向量机的小样本预测研究

统计学中的预测问题主要是通过对已知数据的分析,找到数据内在的相互依赖关系,从而获得对未知数据的预测能力。该文提出了最小二乘支持向量机参数优化方法———多层动态自适应优化算法,构建了基于最小二乘支持向量机的预测模型,并对Ti 26合金的性能预测进行了研究。结果表明:优化的最小二乘支持向量机具有优秀的小样本数据学习能力和预测能力。     

非线性系统在线模糊建模的快速算法

对于复杂、病态、非线性动态系统,基于模糊集合的模糊模型,利用模糊推理规则描述动态系统的特性,是一种有效方法。讨论了利用模糊方法实现非线性系统的建模方法。首先,利用在线模糊竞争学习方法划分输入变量的模糊空间,然后利用卡尔曼滤波算法辨识模糊模型的参数。仿真结果表明了该方法的实用性和有效性。     

基于分支深度强化学习的非合作目标追逃博弈策略求解

为解决航天器与非合作目标的空间交会问题,缓解深度强化学习在连续空间的应用限制,提出了一种基于分支深度强化学习的追逃博弈算法,以获得与非合作目标的空间交会策略。对于非合作目标的空间交会最优控制,运用微分对策描述为连续推力作用下的追逃博弈问题;为避免传统深度强化学习应对连续空间存在维数灾难问题,通过构建模糊推理模型来表征连续空间,提出了一种具有多组并行神经网络和共享决策模块的分支深度强化学习架构。实现了最优控制与博弈论的结合,有效解决了微分对策模型高度非线性且难于利用经典最优控制理论进行求解的难题,进一步提升了深度强化学习对离散行为的学习能力,并通过算例仿真检验了该算法的有效性。     

从王国维谈人文素质

撷王国维博大深沉学术之一粟,试对王国维所蕴含和阐发的人文素质做一个简约的梳理,以期窥其特质,集心香一瓣,并引为今人启迪。     

Perception,object kind,and object naming

Spatial Cognition and Computation - We investigated whether certain perceptual properties of objects could support children's and adults' judgments of the range of shape changes permissible...     

Age differences in adults' spatial abilities,learning environmental layout,and wayfinding behavior

Empirical relations among age, general spatialability as assessed by psychometric tests,wayfinding-related skills as assessed byexperimental tasks in the laboratory,environmental layout learning as assessed in afield experiment, and wayfinding behavior asobserved in a field experiment were modeled ina study involving 120 younger and 120 olderadults. The best-fitting model showed thatage-related differences in learningenvironmental layout were significantly, butnot exclusively, mediated by a single abilityfactor defined by psychometric tests. Knowledge of environmental layout was theexclusive mediator between general spatialability and wayfinding behavior. Thus, agedifferences in psychometric test performancewere found to be a major factor in accountingfor aging-related decline in learningenvironmental layout, but other variables notassessed in this study also play a significantrole.