一种基于条件证据网络的多源异类知识融合识别方法

针对融合识别领域中不同框架下多源异类传感器的不确定证据信息无法有效融合的问题, 提出一种基于条件证据网络的多源异类知识融合识别方法. 该方法将战场协同作战中不同框架下多源异类传感器的领域知识统一在证据网络的结构下, 形成多源异类知识融合识别模型, 对多源异类传感器的不确定性证据信息进行基于条件证据网络的融合推理, 得到识别结果. 仿真实例验证了所提出方法的优越性.

     

一种基于Pignistic概率距离的合成公式

针对多证据源信息融合过程中证据源间存在的冲突问题,提出了一种基于Pignistic概率距离的合成公式。利用Pignistic概率距离构造证据可信度;再利用证据可信度修正证据体,以改进合成公式;利用改进的合成公式对证据源进行融合。算例结果表明,改进合成公式的融合结果合理有效,与其他方法相比有更好的适用性、可靠性和较快的运算速度。     

多传感器冲突信息的加权融合算法

针对在多传感器目标识别系统中,DS规则对高冲突信息融合结果不合理的问题,提出了一种新的加权融合算法.在多源证据信息融合时,首先根据两证据距离大小来确定其相互支持度,将证据支持度矩阵模最大特征值对应的特征向量作为证据的权重向量,然后确定各证据的相对折扣因子,并修正证据信息,最后用DS规则融合.通过实验仿真对比分析了多种方法的融合效果,表明了新方法可以较好的解决高冲突信息融合的问题.     

DSmT与DST融合门限改进方法

Dezert-Smarandache理论（DSmT）是一种能够高效实现多源信息融合,成功处理强冲突证据源的数据融合方法,而Dempster-Shafer理论（DST）在证据源冲突低时的融合效果好,运算代价低。将两种技术结合,在冲突距离函数变化率较低时采取DST证据理论,反之采用DSmT融合算法是一种提高信息融合效率的可行方式。研究人员对DSmT和DST二者的单点值转换门限方法已做了探讨,针对单点值门限方法的不足,提出了将冲突距离函数作为判别依据来确定转换门限的方法。该方法有很强的适应性,根据不同的证据组合,能划分是单点值门限还是多点值门限。     

基于证据理论的信息融合在图像分类中的应用

该文在阐述Dempster-Shafer证据理论的基础上,给出了基于Dempster-Shafer证据理论的多源信息融合的方法,并将Dempster-Shafer证据理论的信息融合技术应用于遥感图像纹理的分类。提取纹理图像不同特征构成该理论中的证据,利用一定的决策规则,选择融合证据作用下最大的假设。实验结果表明,该文提出的基于Dempster-Shafer证据理论的多特征融合分类识别图像纹理的新方法是切实有效的,能极大地提高图像纹理的识别分类能力。     

基于支持度D-S证据理论与模糊积分的多源节点簇信息时空融合

为了获得传感器网络中监测目标的准确状态,需要同时考虑多源节点簇信息融合的时间性和空间性.本文提出了一种多源传感器信息的时空两级融合结构.对同一时刻多源节点簇信息,利用D-S证据理论和支持度进行空间融合,对经空间融合后的时间序列,利用模糊积分、支持度和遗传算法进行时间上的信息融合.仿真实验表明,据此形成的分布式多源节点簇信息融合系统具有目标探测能力、抗干扰能力和容错能力.     

基于改进D-S证据理论的多源空战信息博弈融合方法

多传感器系统与单传感器系统相比能够更大限度地获取被探测目标的信息量,但在空战中无人机传感器探测得到的数据在一定程度上具有欺骗性,利用博弈融合技术对多传感器数据进行融合,能够获得更加符合空战实际需要的信息。为此,研究了一种基于改进D-S(Dempster-Shafer)证据理论的多源空战信息博弈融合技术,在信息融合前采用Jousselme距离进行预处理,并利用费雪信息进行冲突数据博弈,所得策略集使空战数据更加可靠。在此基础上,根据邓熵方法对基于D-S证据理论的融合方法进行改进,与传统D-S证据理论方法相比,融合数据符合空战实际。最后对存在冲突的多源空战信息进行博弈融合仿真,仿真结果验证了该方法的可行性与优势。     

DSmT相关证据模型及反问题近似解求法

介绍了一种新的信息融合理论——DSmT（Dezert-Smarandache Theory）。在DSmT下,鉴于实际处理的证据经常是相关证据,提出了一种新的模型表示相关证据。其中两个相关证据各自由一个独立源证据和一个相关源证据正交和合成,相关证据的合成就归结为这两个独立源证据和这个相关源证据的正交和合成。辨识独立源证据是一个反问题,该反问题可能不存在唯一精确解,此时采用了粒子群优化算法求其近似解。     

一种基于近邻思想的证据合成规则

D-S证据合成规则在遇到冲突证据时常有悖常理。针对现有规则的不足,通过理论分析和对几种常用组合规则的比较,提出一种基于近邻思想的冲突证据修正规则,综合考虑证据源的有效性和证据源间的距离,进行信息融合。实验结果表明,该规则对合理的合成方向具有较快的收敛速度,在证据源完全冲突的情况下也能适用。     

一种新的冲突表征下的异类源信息融合算法

异类源信息融合时常遇到证据高度冲突的情况,此时应用传统Dempster-Shafe(rD-S)证据理论进行融合将出现错误的结果。针对以往冲突证据融合研究中使用冲突系数k表征证据之间的冲突程度所存在的不足,提出了一种新的证据冲突表征方法。在此基础上确定证据间的冲突度和相似度,得到证据的权重。对加权修正后的证据利用D-S证据理论进行融合。算例验证表明该方法可以有效地对冲突证据进行融合,收敛效果较好。     

Evidence supporting measure of similarity for reducing the complexity in information fusion

This paper presents a new method for reducing the number of sources of evidence to combine in order to reduce the complexity of the fusion processing. Such a complexity reduction is often required in many applications where the real-time constraint and limited computing resources are of prime importance. The basic idea consists in selecting, among all sources available, only a subset of sources of evidence to combine. The selection is based on an evidence supporting measure of similarity (ESMS) criterion which is an efficient generic tool for outlier sources identification and rejection. The ESMS between two sources of evidence can be defined using several measures of distance following different lattice structures. In this paper, we propose such four measures of distance for ESMS and we present in details the principle of Generalized Fusion Machine (GFM). Then we apply it experimentally to the real-time perception of the environment with a mobile robot using sonar sensors. A comparative analysis of results is done and presented in the last part of this paper.     

多传感器融合改进的机器人定位决策

在复杂的不确定环境里,采用单一传感器对机器人进行定位时精度较低,并且易受干扰,可靠性较差。针对这一问题在粒子滤波器移动机器人SLAM算法的基础上,利用多传感器融合对算法进行改进,将观测信息进行特征级融合,充分利用各种传感器采集的冗余信息,并将融合后的观测信息分别用来估计机器人路径和环境特征的后验概率分布。仿真试验表明,改进后的算法在SLAM定位精度及可靠性上都有较大的提高,证明了该种方法的可行性。     

Preface

This paper discusses the problems in teleoperation systems for a mobile robot and the utilization of a virtual world in such systems. In order to achieve smooth operation of the mobile robot through a communication link, we should consider time delays in data transfer. To compensate for the incomplete data sets, the virtual images can be generated by computer graphics when the information on the working environment can be acquired beforehand. In this paper, we construct a teleoperation system with a virtual world. The performance of the system is examined through experiments with actual mobile robots which show that the virtual robot can be operated by an operator in almost the same manner as the teleoperated real robot. In an experimental environment with a second moving robot, we can keep the status of the second robot under perfect control and operate the first robot with no interference.     

基于多传感器信息融合的移动机器人导航系统

介绍了多传感器信息融合的基本原理,给出了基于多传感器信息融合的移动机器人导航系统结构。建立了移动机器人数学模型,运用基于扩展卡尔曼滤波的信息融合方法实现了移动机器人导航算法。通过实验验证了基于多传感器信息融合的移动机器人导航系统和导航算法的有效性。     

基于软传感器的信息融合

为了利用”凝视视觉几何约束”的信息来确定移动机器人的位置和方位角,就需要解决数据融合的问题。”几何约束”不是来自真实传感器的直接可测量的数据,这种特殊形式的信息不能被直接融合。为此目的,该文提出了一种融合特殊形式信息的新途径,也即利用”软传感器”的方法来融合来自”几何约束”的信息。软传感器的输出与其它真实传感器的输出一起经过扩展信息滤波器最终实现融合。文中最后提供了利用该方法进行移动机器人定位的计算机仿真例子。仿真结果表明了软传感器信息融合方法的可行性和有效性。软传感器可以广泛应用在很多类似的信息融合问题中。     

Robot teaching system based on hand-robot contact state detection and motion intention recognition

This paper presents a robot teaching system based on hand-robot contact state detection and human motion intent recognition. The system can detect the contact state of the hand-robot joint and extracts motion intention information from the human surface electromyography (sEMG) signals to control the robot's motion. First, a hand-robot contact state detection method is proposed based on the fusion of the virtual robot environment with the physical environment. With the use of a target detection algorithm, the position of the human hand in the color image of the physical environment can be identified and its pixel coordinates can be calculated. Meanwhile, the synthetic images of the virtual robot environment are combined with those of the physical robot scene to determine whether the human hand is in contact with the robot. Besides, a human motion intention recognition model based on deep learning is designed to recognize human motion intention with the input of sEMG signals. Moreover, a robot motion mode selection module is built to control the robot for single-axis motion, linear motion, or repositioning motion by combining the hand-robot contact state and human motion intention. The experimental results indicate that the proposed system can perform online robot teaching for the three motion modes.     

Path planning based on geographical features information for an autonomous mobile robot

We propose a path-planning algorithm for an autonomous mobile robot using geographical information, under the condition that the robot moves in an unknown environment. Images input by a camera at every sampling time are analyzed and geographical elements are recognized, and the geographical information is embedded in an environmental map. Then the path is updated by integrating the known information and the prediction on the unknown environment. We used a sensor fusion method to improve the mobile robot's dead-reckoning accuracy. The experimental results confirm the effectiveness of the proposed algorithm as the robot reached the goal successfully using the geographical information.     

基于多传感器融合的全地形机器人系统设计

针对因强降雨、堤防溃决、暴雨增水等因素导致的水位突然上升而泛滥和山洪暴发,形成复杂多变灾后的地形环境。设计了以FPGA为控制器的多传感器融合机器人,提高灾后救援效率。该机器人通过GPS为机器人作业划定区域,生命特征仪、力矩仪和空气质量仪等传感器采集环境数据,搭建非线性全地形机器人动态模型,利用六轴陀螺仪和霍尔传感器获取机器人状态,数据经过扩展卡尔曼滤波算法融合以及航迹算法推算后,获得机器人在灾后环境中的实际信息,使得机器人能够按要求进行搜救作业。实验结果表面,多传感器融合的机器人系统,能够在灾后环境完成信息采集与传输,具有较高的稳定性及准确性。     

信息融合算法在机器人足球系统中的应用

最优信息融合Kalman滤波算法给出了实时动态环境中线性方差最小的融合估计。采用该算法对机器人足球系统中的小球进行状态估计和预测,并给出了信息融合处理结构和该算法的具体实现步骤。实验结果表明,该算法可以克服单一视觉传感器采集的数据含有较大噪声等局限性,实现了对小球精确的状态估计和预测,具有可行性和优越性,并且在某一机器人视觉传感器出错时,系统仍具有良好的容错性和鲁棒性。     

Probabilistic terrain classification in unstructured environments

Autonomous navigation in unstructured environments is a complex task and an active area of research in mobile robotics. Unlike urban areas with lanes, road signs, and maps, the environment around our robot is unknown and unstructured. Such an environment requires careful examination as it is random, continuous, and the number of perceptions and possible actions are infinite.We describe a terrain classification approach for our autonomous robot based on Markov Random Fields (MRFs ) on fused 3D laser and camera image data. Our primary data structure is a 2D grid whose cells carry information extracted from sensor readings. All cells within the grid are classified and their surface is analyzed in regard to negotiability for wheeled robots.Knowledge of our robot’s egomotion allows fusion of previous classification results with current sensor data in order to fill data gaps and regions outside the visibility of the sensors. We estimate egomotion by integrating information of an IMU, GPS measurements, and wheel odometry in an extended Kalman filter.In our experiments we achieve a recall ratio of about 90% for detecting streets and obstacles. We show that our approach is fast enough to be used on autonomous mobile robots in real time.