A novel robot co-worker system for paint factories without the need of existing robotic infrastructure

This paper presents a human–robot co-working system to be applied to industrial tasks such as the production line of a paint factory. The aim is to optimize the picking task with respect to manual operation in a paint factory. The use of an agile autonomous robot co-worker reduces the time in the picking process of materials, and the reduction of the exposure time to raw materials of the worker improves the human safety. Moreover, the process supervision is also improved thanks to a better traceability of the whole process. The whole system consists of a manufacturing process management system, an autonomous navigation system, and a people detection and tracking system. The localization module does not require the installation of reflectors or visual markers for robot operation, significantly simplifying the system deployment in a factory. The robot is able to respond to changing environmental conditions such as people, moving forklifts or unmapped static obstacles like pallets or boxes. The system is not tied to specific manufacturing orders. It is fully integrated with the manufacturing process management system and it can process all possible orders as long as their components are placed into the warehouse. Real experiments to validate the system have been performed in a paint factory by a real holonomic platform and a worker. The results are promising from the evaluation of performance indicators such as exposure time of the worker to raw materials, automation of the process, robust and safe navigation, and the assessment of the end-user.     

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

多分量数据全波形反演在气藏检测中的关键问题——以苏里格气田为例

苏里格气田是中国典型的致密砂岩气藏，构造简单、平缓，横向非均质性强，有效储层与围岩声学特征差别小，地震响应不明显，常规地震监测方法预测难度大，但气田含气砂岩泊松比低，是地震气藏检测的有效参数。利用弹性全波形反演精度高和能处理复杂非均质介质的优势，反演地层拉梅常数、剪切模量和密度，并计算泊松比，从而进行气藏预测。重点阐述了苏里格气田多分量数据全波形反演初始模型建模、先验模型建模和地震数据预处理3个关键问题的处理方法。二维三分量数据反演和"甜点"预测结果表明：①对于具有强非均质性的苏里格气田，利用全波形反演获得精度较高的地层弹性参数能显著提高气藏预测的准确度；②苏里格地区构造简单、平缓，利用常规叠加速度并结合构造解释可以建立比较好的初始模型，从而有效地解决了周波跳跃和局部极小的难题；③先验知识的约束和地震数据的预处理是全波形反演成功应用于苏里格气田气藏检测的关键。     

Adaptive GLR-, Rao- and Wald-based CFAR detectors for a subspace signal embedded in structured Gaussian interference

The problem of detecting a subspace signal embedded in subspace Gaussian interference and thermal noise is studied in this paper. In this problem, both the signal-independent and signal-dependent interferences are assumed to be present, therefore the overall interference subspace covers the signal subspace. The approach of this paper extends previous works involving either of those two kinds of interferences. A set of secondary data containing only interference plus noise is employed to estimate the interference covariance matrix and the noise power. Three new detectors are designed via the generalized likelihood ratio (GLR), Rao and Wald tests, respectively. Their probabilities of false alarms (PFAs) and detections are analytically derived. The PFAs show that the new detectors have the constant false alarm rate (CFAR) property against the interference and noise. Numerical results show that the new detectors outperform their counterparts for the studied problem. Furthermore, the new detectors are less sensitive to the secondary data size and to the mismatched subspace signal than some other detectors, such as the GLR detector (GLRD), the adaptive matched filter (AMF), the adaptive subspace detector (ASD), etc.     

基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络，直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序，并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面，对近年来基于深度学习的人体姿态估计方法进行系统介绍，从而初步了解如何通过深度学习的方法得到人体姿态的各个要素，包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系，甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述，清晰地呈现出该领域的发展脉络。     

MIMO-GFDM系统中低复杂度动态禁忌搜索检测算法的改进

针对多输入多输出的广义频分复用（MIMO-GFDM）系统的等效信道矩阵维度极大，传统的MIMO检测算法复杂度高且性能不佳的问题，将大规模MIMO系统中的动态禁忌搜索（RTS）检测算法运用到MIMO-GFDM系统中，并解决了RTS算法初始值的求解复杂度高的问题。首先利用最小均方误差（MMSE）检测算法所用到矩阵的正定对称性将矩阵Cholesky分解，并结合Sherman-Morrison公式迭代计算初始值，降低了初始值求逆的高复杂度；然后以改进的MMSE检测结果作为RTS算法的初始值，从初始值逐步全局搜索最优解；最后通过仿真，对不同算法的迭代次数和误码率（BER）性能进行了研究。理论分析与仿真结果表明：在MIMO-GFDM中，所提改进RTS信号检测算法误码率远低于传统信号检测算法。在4QAM时，RTS算法大约有低于MMSE检测6 dB的信噪比性能增益（误码率在10^-3时）；在16QAM时，RTS算法大约有低于MMSE检测4 dB的信噪比性能增益（误码率在10^-2时）。与传统RTS算法性相比，所提改进算法在不影响误码率性能的同时降低了算法复杂度。     

一种基于压缩感知的运动目标检测技术

运动目标检测是计算机视觉、图像处理等相关领域的研究热点，其核心就是对视频图像中的每一帧图像进行相应的研究和处理。本文主要研究思路是从压缩感知技术采样信号的角度出发，将每一帧的二维图像压缩采样成具有少量信息的一维信号，再通过信号重构用少量数据量将图像重构出来，最后通过目标检测技术对每一帧的图像进行运动目标提取。仿真实验表明该方法是可行和有效的，同时可以大大减少目标检测中所记录的数据量，解决海量数据的存储与传输问题。     

具有双通道数据包丢失的Delta算子系统故障检测

研究同时存在双通道数据包丢失和时变时延的Delta算子网络控制系统（NCSs）故障检测问题.假定数据包丢失发生在控制器到执行器、传感器至控制器的数据传输过程中，并且利用两个相互独立的伯努利随机变量描述是否发生丢包.将上述的NCSs建模为网络切换系统，提出任意切换律下故障检测滤波器的设计方法.利用线性矩阵不等式（LMIs）方法、Lyapunov-Krasovskii泛函和平均驻留时间等得出所考虑的网络切换系统具备指数均方稳定性的充分条件.证明了所用的网络切换系统满足H_∞性能，并推导出了滤波器参数的显式表达.数值仿真结果验证了所提方法的有效性.     

Improved non-maximum suppression for object detection using harmony search algorithm

Non-maximum suppression (NMS) plays a key role in many modern object detectors. It is responsible to remove detection boxes that cover the same object. NMS greedily selects the detection box with maximum score; other detection boxes are suppressed when the degree of overlap between these detection boxes and the selected box exceeds a predefined threshold. Such a strategy easily retain some false positives, and it limits the ability of NMS to perceive nearby objects in cluttered scenes. This paper proposes an effective method combining harmony search algorithm and NMS to alleviate this problem. This method regards the task of NMS as a combination optimization problem. It seeks final detection boxes under the guidance of an objective function. NMS is applied to each harmony to remove imprecise detection boxes, and the remaining boxes are used to calculate the fitness value. The remaining detection boxes in a harmony with highest fitness value are chosen as the final detection results. The standard Pattern Analysis, Statistical Modeling and Computational Learning Visual Object Classes dataset and the Microsoft Common Objects in Context dataset are used in all of the experiments. The proposed method is applied to two popular detection networks, namely Faster Region-based Convolutional Neural Networks and Region-based Fully Convolutional Networks. The experimental results show that the proposed method improves the average precision of these two detection networks. Moreover, the location performance and average recall of these two detectors are also improved.     

一种结合区域检测和语义分割的SLAM技术

提出一种结合区域检测和语义分割的即时定位和建图（SLAM）技术，通过引入高精度图像描述子SIFT来实现前端视觉里程计（VO）过程中帧间像素匹配的精度。为了降低引入操作带来的计算复杂度，设计一个实时区域检测算法，在相邻帧间检测大致相似的ROI(Region of Interest)关键区域，使得SIFT描述子的提取和匹配只在ROI区域内完成，其余区域仍旧采用精度略低、效率更高的ORB算子。同时，为了提高后端BA(Bundle Adjustment)的精度，减少累积误差，结合语义图，在原有的基本投影误差函数上添加一个语义误差。该语义图采用实时语义分割算法完成，同时只针对ROI区域进行分割。通过与原SLAM方案对比实验，表明本文提出的方法，在提高一定精度的同时，仍能满足SLAM实时定位和建图的要求。最后，在电力作业场景下验证了该方案的效果。