The M-Space Feature Representation for SLAM

In this paper, a new feature representation for simultaneous localization and mapping (SLAM) is discussed. The representation addresses feature symmetries and constraints explicitly to make the basic model numerically robust. In previous SLAM work, complete initialization of features is typically performed prior to introduction of a new feature into the map. This results in delayed use of new data. To allow early use of sensory data, the new feature representation addresses the use of features that initially have been partially observed. This is achieved by explicitly modelling the subspace of a feature that has been observed. In addition to accounting for the special properties of each feature type, the commonalities can be exploited in the new representation to create a feature framework that allows for interchanging of SLAM algorithms, sensor and features. Experimental results are presented using a low-cost Web-cam, a laser range scanner, and combinations thereof.     

高度场八叉树的体特征表达算法

体特征表达对用户理解和认知虚拟环境有着至关重要的作用。当前的体特征表达算法由于存储量大且不易于在GPU中加速等问题,渲染效率低下,难以满足场景可视化的实时性需求。针对这一问题,提出了一种高效的高度场八叉树体特征表达算法,不仅解决了传统高度场仅能表达2.5维模型,无法表达真三维模型的问题,而且为体特征表达提供了一种新的可行途径。算法使用八叉树结构生成三维模型的高度场表示,将传统的z向高度场扩展到x,y,z三个方向的高度场。首先,提出了三角面片预处理方法,保证模型精度和数据的完整性;其次,提出了基于投影变换的高度场表示判断及栅格化方法,将几何图元转换成二维空间的高度场数据;最后,提出了基于高度场八叉树的光线投射算法。实验结果表明,算法能极大地减少存储量,具有较高的光线投射效率,表达三维模型时取得较好效果。     

Motion representation using composite energy features

This work tackles the segmentation of apparent-motion from a bottom-up perspective. When no information is available to build prior high-level models, the only alternative are bottom-up techniques. Hence, the whole segmentation process relies on the suitability of the low-level features selected to describe motion. A wide variety of low-level spatio-temporal features have been proposed so far. However, all of them suffer from diverse drawbacks. Here, we propose the use of composite energy features in bottom-up motion segmentation to solve several of these problems.Composite energy features are clusters of energy filters—pairs of band-pass filters in quadrature—each one sensitive to a different set of scale, orientation, direction of motion and speed. They are grouped in order to reconstruct independent motion patterns in a video sequence. A composite energy feature, this is, the response of one of these clusters of filters, can be built as a combination of the responses of the individual filters. Therefore, it inherits the desirable properties of energy filters but providing a more complete representation of motion patterns.In this paper, we will present our approach for integration of composite features based on the concept of Phase Congruence. We will show some results that illustrate the capabilities of this low-level motion representation and its usefulness in bottom-up motion segmentation and tracking.     

Interpretation control using a linear tree representation

A linear tree structure is considered for the internal representation of programs executed by interpreters. This representation is appropriate when one wishes to have an internal representation preserving the high level structures of the source language. The linear tree structure facilitates a simple mechanism for interpretation control in the context of high level control structures.     

采用SLAM方法的电脑鼠

与绝大部分采用红外对管进行简单测距的电脑鼠不同,在电脑鼠上使用线型激光器和摄像头搭建了一个小型激光测距系统并进行SLAM。摄像头以240 f/s的帧率输出分辨率为188×120的图像,使用Zynq-7010作为主控制器,在其可编程逻辑部分搭建了图像采集系统,在其双核处理器Cortex-A9部分搭建了用于运行图像处理、传感器数据融合和解迷宫算法的实时Linux操作系统。制作了一只重量为100.06 g、车体大小为7.45 cm(宽)×6.6 cm(长)的电脑鼠,能高速稳定地在迷宫中运动。     

利用边缘计算的多车协同激光雷达SLAM

目的 激光雷达实时定位与建图（simultaneous localization and mapping,SLAM）是智能机器人领域的重要组成部分,通过对周边环境的3维建模,可以实现无人驾驶车辆的自主定位和精准导航。针对目前单个车辆激光雷达建图周期长、算力需求大的现状,提出了基于边缘计算的多车协同建图方法,能够有效地负载均衡,在保证单个车辆精准定位的同时,增加多个车辆之间的地图重用性。方法 构建基于阈值的卸载函数,论证边缘计算下的多车卸载决策属于势博弈问题,设计实现基于边缘计算的势博弈卸载算法,在模型具有纳什均衡的基础上实现任务调度,引入α-Nash最佳响应动态加速算法收敛,并采用由粗到细的点云匹配方法提高地图匹配性能,实现车辆的精准定位。最后,基于地图的相对可信度,高效地合并基站覆盖范围内的多个车辆的建图数据。结果 实验表明,基于博弈论的调度方法在保证定位可靠性的前提下,能够有效地实现多车协同SLAM,且多车协同的定位与建图结果与使用载波相位差分技术（real-time kinematic,RTK）的高精度差分全球定位系统（differential global positioning system,DGPS）结果足够接近,相比于单车建图而言,横向定位和纵向定位的平均精度分别提高了6.0倍和3.9倍。结论 本文方法解决了基于边缘计算的多车协同激光雷达SLAM问题,借助边缘服务器的计算资源,无人驾驶车辆可以有效地减少本地资源需求和定位延迟。该方法通过各个车辆之间的资源博弈,最终实现纳什均衡。实现基于边缘计算的激光雷达定位服务,且高效地完成多车之间的地图合并,仿真和真实环境中的实验表明了方法的有效性。     

Knowledge representation and integration for portfolio evaluation using linear belief functions

This paper proposes a linear belief function (LBF) approach to evaluate portfolio performance. By drawing on the notion of LBFs, an elementary approach to knowledge representation in expert systems is proposed. It is shown how to use basic matrices to represent market information and financial knowledge, including complete ignorance, statistical observations, subjective speculations, distributional assumptions, linear relations, and empirical asset-pricing models. The authors then appeal to Dempster's rule of combination to integrate the knowledge for assessing the overall belief of portfolio performance and updating the belief by incorporating additional evidence. An example of three gold stocks is used to illustrate the approach.     

Graphic representation of linear recursive rules

Recursive rules are important to deductive databases. A recursive rule may be compiled into expansions. In this article, the variable-predicate graph (V-P graph) based on the α-graph by loannidis is developed to represent linear recursive function-free rules and their expansions. A naming convention is used for variables and predicates in the V-P graph so that all equivalent recursive rules may map into a unique V-P graph. We propose a graphic construction method (g.c.m.) which derives V-P graphs of expansions directly from the V-P graph of the original rule. This graphic representation reveals some expansion properties not easy to obtain otherwise. We also propose a rule rewriting method in the context of deductive database so that constants, repeated distinguished variables, and/or repeated recursive variables may be removed from recursive rules.     

Decentralized Cooperative SLAM for Sparsely-Communicating Robot Networks: A Centralized-Equivalent Approach

Communication between robots is key to performance in cooperative multi-robot systems. In practice, communication connections for information exchange between all robots are not always guaranteed, which adds difficulty in performing state estimation. This paper examines the decentralized cooperative simultaneous localization and mapping (SLAM) problem, in which each robot is required to estimate the map and all robot states under a sparsely-communicating and dynamic network. We show how the exact, centralized-equivalent estimate can be obtained by all robots in the network in a decentralized manner even when the network is never fully connected. Furthermore, a robot only needs to consider its own knowledge of the network topology in order to detect when the centralized-equivalent estimate is obtainable. Our approach is validated through more than 250 min of hardware experiments using a team of real robots. The resulting estimates are compared against accurate groundtruth data for all robot poses and landmark positions. In addition, we examined the effects of communication range limit on our algorithm’s performance.     

Polyhedral representation of fuzzy linear bases

 In [15], we introduced the concepts of fuzzy bases, fuzzy linear interpolation and fuzzy polygon of four-component fuzzy linear bases. In [16], these concepts were used in the maximal profile of the set of polygons generated from a set of break points for each variable dimension. Theconcept was operationalized in a fuzzy linear basis algorithm (FLBA) for nonlinear separable programming problems involving no more than a finite number of discontinuities. The FLBA provides a powerful platform forparallel processing of the fuzzy linear sub-problems included in the finite FLB-chain. In this paper we extend the theory of fuzzy linear bases from the set of polygons toapolyhedral representation of four-component fuzzy linear bases defined on a closed subset of the real line.     

基于特征稀疏策略的室内机器人SLAM研究

针对室内环境下的移动机器人的定位问题,研究了一种能够适应空间狭小、特征点密集的复杂环境的双目视觉SLAM方法。该方法以EKF-SLAM方法为基础,引入了一种特征点稀疏性控制机制,该机制对地图库中的特征点同时在位置空间和特征空间进行分布密度限制,克服了因特征点快速上升而导致的庞大的计算量问题,提高了数据关联的准确性。此外,降低了SIFT矢量的维数以降低计算量,且在左右试图的特征匹配中,引入了多个约束条件,以提高匹配的准确性。最终实验结果表明,方法能够实现特征点分布的均匀性,且在定位精度满足要求的前提下缩短定位时间。     

An efficient representation for linear constraints

An efficient representation for the linear constraints generated by a recent CACSD (computer-aided control system design) method has been developed. The linear constraints arise from engineering constraints on the time- and frequency-domain responses of the closed-loop system. The representation reduces the storage requirements and improves the efficiency of the quadratic programming algorithm used by the design method. The algorithm performs two distinct operations on the individual constraints. The first determines if a constraint has been satisfied and the second is the computation of the distance in a specified search direction     

一种结合ORB特征和视觉词典的RGB-D SLAM算法

同时定位与建图（Simultaneous Localization and Mapping,SLAM）是机器人领域的研究热点,被认为是实现机器人自主运动的关键。传统的基于RGB-D摄像头的SLAM算法（RGB-D SLAM）采用SIFT（Scale-Invariant Feature Transform）特征描述符来计算相机位姿,采用GPU加速的siftGPU算法克服SITF特征提取慢的缺点,但多数嵌入式设备缺乏足够的GPU运算能力,使其应用性受到局限。此外,常规算法在闭环检测时效率较低,实时性不强。针对上述问题,提出了一种结合ORB（oriented FAST and rotated BRIEF）特征与视觉词典的SLAM算法。在算法前端,首先提取相邻图像的ORB特征,然后利用k近邻（k-Nearest Neighbor,kNN）匹配找到对应的最临近与次临近匹配,接着采用比值检测与交叉检测剔除误匹配点,最后采用改进的PROSAC-PnP（Progressive Sample Consensus based Perspective-N-Point）算法进行相机姿态计算,得到对相机位姿的高精度估计。在后端,提出了一种基于视觉词典的闭环检测算法来消除机器人运动中的累计误差。通过闭环检测增加帧间约束,利用通用图优化工具进行位姿图优化,得到全局一致的相机位姿与点云。通过对标准fr1数据集的测试和对比,表明了该算法具有较强的鲁棒性。     

考虑通信状况的多机器人CSLAM问题综述

多机器人系统的通信状况能够直接影响协作同时定位与地图创建(Cooperative simultaneous localization and mapping, CSLAM)算法的设计和实现.根据对多机器人通信状况所作出假设的侧重点不同, 对多机器人CSLAM算法研究现状和进展进行综述.首先,简要介绍了基于完全连通通信条件的集中式CSLAM算法的特点和缺陷; 其次,结合多机器人系统初始相对位姿关系未知的情况,从地图配准、数据关联和地图融合等三个方面, 对基于通信范围或者带宽受限条件的分布式CSLAM算法的地图合并问题进行了分析和阐述; 进而重点对考虑稀疏动态通信状况的分布式CSLAM算法的最新研究成果进行了归纳总结. 最后指出多机器人CSLAM研究领域今后的研究方向.     

基于Kinect和视觉词典的三维SLAM

针对传统滤波器方法解决机器人同时定位与地图创建(SLAM)时的误差积累问题,提出了一种基于视觉词典(BOW)的三维SLAM算法,以有效解决机器人长时间运动下误差积累的问题。相比图优化SLAM中常用的随机检测和Kd树(Kd-Tree)算法,采用基于树结构的视觉词典闭环检测算法来提高相似场景的检索效率。首先采用基于GPU的特征提取算法提取图像特征,并利用交叉匹配和k最近邻(kNN)算法取得图像中鲁棒性较强的内点;然后通过基于随机抽样一致性奇异值分解(RANSAC SVD)算法计算出相邻帧的初始位姿变换,并利用通用迭代最近点(G-ICP)算法进行优化,得到高精度的位姿变换;最后利用增量平滑和建图(iSAM)图优化方法得出最终位姿,拼接出高精度的点云地图和运动轨迹。标准数据集的测试表明,所提算法在复杂情况下具有良好的鲁棒性和精度。     

Network representation with clustering tree features

This paper studies the relationship between a case-based decision theory (CBDT) and an ideal point model (IPM). We show that a case-based decision model (CBDM) can be transformed into an IPM under some assumptions. This transformation can allow us to visualize the relationship among data and simplify the calculations of distance between one current datum and the ideal point, rather than the distances between data. Our results will assist researchers with their product design analysis and positioning of goods through CBDT, by revealing past dependences or providing a reference point. Furthermore, to check whether the similarity function, presented in the theoretical part, is valid for empirical analysis, we use data on the viewing behavior of audiences of TV dramas in Japan and compare the estimation results under the CBDM that corresponds to a standard decision model with similarities and other various similarity functions and without a similarity function. Our empirical analysis shows that the CBDM with a similarity function, presented in this study, best fits the data.     

Image-based visual servo control of aerial robotic systems using linear image features

An image-based "eye-in-hand" visual servo-control design is proposed for underactuated rigid-body dynamics. The dynamic model considered is motivated by recent work on vertical takeoff and landing aerial robotic vehicles. The task considered is that of tracking parallel linear visual features. The proposed design exploits the geometry of the task considered and passivity-like properties of rigid-body dynamics to derive a control Lyapunov function using backstepping techniques.