OBSTACLE-AVOIDANCE NAVIGATION OF MULTIPLE MOBILE ROBOTS

IntroductionRobo Cup,which involves multiple robots in acomplicated environment to achieve specific objec-tives,poses a common standard problem for aboard spectrum of specialize sub- fields in AI andintelligentrobotic agents[1] .The majorcharacteris-tic of the Robo Cup Soccer competition is the dy-namic nature of environment surrounding robots,which includes the problem addressed in this pa-per.In the current research of it[2 ,3 ] ,when the re-searchers think about the problem of avoiding ob…     

���ڳ���ǰ��������Ĺ��������

轨道交通线路净空安全是确保列车平稳、不间断运行的基础.由于轨间异物对行车安全产生严重影响,所以基于非轨道电路的轨道异物入侵检测系统在铁路系统中具有十分广泛的应用前景.本文提出了一种基于移动车载摄像机检测轨间异物的方法.首先,通过钢轨识别算法自动定位钢轨位置,并确定列车前方轨道是否有其它列车或公路车辆等大型异物,若有则进行报警;之后,基于边缘检测的异物检测算法自动检测轨间可疑小异物,同时提取可疑异物的尺度信息和颜色索引参数等相关特征;最后,用支持向量机（SVM）来对可疑小异物区域进行分类和辨识.车载实验结果表明,该方法可以有效地检测出轨间异物.     

Dynamic Obstacle Avoidance for Application of Human-Robot Cooperative Dispensing Medicines

For safety reasons,in the automated dispensing medicines process,robots and humans cooperate to accomplish the task of drug sorting and distribution.In this dynamic unstructured environment,such as a human-robot collaboration scenario,the safety of human,robot,and equipment in the environment is paramount.In this work,a practical and effective robot motion planning method is proposed for dynamic unstructured environments.To figure out the problems of blind zones of single depth sensor and dynamic obstacle avoidance,we first propose a method for establishing offline mapping and online fusion of multi-sensor depth images and 3D grids of the robot workspace,which is used to determine the occupation states of the 3D grids occluded by robots and obstacles and to conduct real-time estimation of the minimum distance between the robot and obstacles.Then,based on the reactive control method,the attractive and repulsive forces are calculated and transformed into robot joint velocities to avoid obstacles in real time.Finally,the robot's dynamic obstacle avoidance ability is evaluated on an experimental platform with a UR5 robot and two KinectV2 RGB-D sensors,and the effectiveness of the proposed method is verified.     

面向动静态混合环境的智能车运动规划方法

针对存在动态和静态障碍物环境中的智能车运动规划问题，本文提出一种基于三维搜索的方法。该方法首先在笛卡尔坐标系中增加时间维度以建立时间-空间栅格，构建不同车速下的车辆运动基元；将智能车转化为多个圆心组成的线段，采用膨胀静态障碍物的方法进行不规则障碍物碰撞检测，运用时间间隔法将动态障碍物碰撞检测简化为线段交叉性检测；构建包含最大速度和加速度约束的速度启发式函数，用于引导搜索树在时空空间中快速到达目标位置和速度；最后基于启发式方法和局部运动规划方法在时空栅格中进行搜索，获取融合时间信息和“停止-等待”等决策信息的运动轨迹。实验结果表明：本文运动规划方法在动静态混合环境中能够引导智能车安全行驶，相比速度障碍方法，安全行驶的平均成功率提升23%；相比混合A*方法，平均成功率提升19%，行驶耗时缩短21%。     

IIR数字滤波器设计的搜寻者优化算法

为进一步提高无限冲击响应(IIR)数字滤波器的性能,提出了一种基于搜寻者优化算法(SOA)的IIR数字滤波器设计方法.SOA基于模拟人的随机搜索行为,由利用位置变化评价得到的经验梯度确定搜索方向,由采用简单模糊规则的不确定性推理确定搜索步长,通过搜寻者在搜索空间的位置更新,实现对优化问题的求解.2个典型设计实例的仿真结果表明,与差分进化算法(DE)和3种改进的粒子群算法(PSO)相比,SOA具有较好的全局寻优能力和较快的收敛速度,能有效地应用于IIR数字滤波器的没计.     

A generalized two-level Bregman method with dictionary updating for non-convex magnetic resonance imaging reconstruction

In recent years, it has shown that a generalized thresholding algorithm is useful for inverse problems with sparsity constraints. The generalized thresholding minimizes the non-convex p-norm based function with p 1, and it penalizes small coefficients over a wider range meanwhile applies less bias to the larger coefficients.In this work, on the basis of two-level Bregman method with dictionary updating(TBMDU), we use the modified thresholding to minimize the non-convex function and propose the generalized TBMDU(GTBMDU) algorithm.The experimental results on magnetic resonance(MR) image simulations and real MR data, under a variety of sampling trajectories and acceleration factors, consistently demonstrate that the proposed algorithm can efficiently reconstruct the MR images and present advantages over the previous soft thresholding approaches.     

八轮驱动行走机构越障越壕能力分析

提出一种能自行跨越宽沟槽的八轮行走机构,为确定其越障及越壕能力,在简化力学模型的基础上进行理论推导,分析行走机构尺寸参数与最大越障高度及越壕宽度的关系,并重点分析车轮与接触地面间的附着系数与行走机构越障和越壕能力的关系,从而推导出该新型行走机构可以越过的最大垂直障碍高度,以及可以跨越的最大壕沟宽度.     

智能电动车弯曲道路场景中的避障路径规划

为研究智能电动车在弯曲道路场景下进行避障规划的有效性, 提出了一种将笛卡尔坐标系转换为曲线坐标系的方法, 利用5次贝塞尔曲线对弯曲道路场景中的车道线进行逼近得到参考路径, 通过对参考路径进行弧长参数化, 以弧长为横坐标, 横向偏移为纵坐标的方法建立曲线坐标系, 根据车辆和子目标点在曲线坐标系中的位置关系, 采用3次多项式实时生成候选路径, 利用序列二次规划算法对候选路径进行优化; 为验证所提算法的有效性, 以某智能电动车为平台, 利用单目相机、64线激光雷达、工控机等设备搭建试验车, 通过Apollo平台对车辆在弯曲道路场景中的避障算法进行在线仿真, 在园区实车试验中对避障算法进行了GPS位置误差和航向角累计误差分析。研究结果表明: 在曲线坐标系中进行车辆弯曲道路场景下的避障路径规划, 能有效地描述规划路径曲率半径、车辆中心位置偏移车道线距离等信息, 容易确定自身车辆的可行驶区域、前方障碍物位置信息, 从而生成最优路径; 在园区场景的避障过程中, GPS位置误差发生在初始点、转弯点以及避障点, 最大误差为0.15 m, 航向角累计误差为12°, 突然增大的弯道位置误差主要由车辆姿态瞬时改变及障碍物匹配过程引起, 但是误差都能够很好地控制在一定范围之内, 利用曲线坐标系解决弯曲道路场景中的避障路径规划是可行的。      

Automatic outer surface extraction of femoral head in CT images

Computer-aided hip surgery planning and implant design applications require accurate segmentation of femoral head and proximal acetabulum. An accurate outer surface extraction of femoral head using marching cubes algorithm remains challenging due to deformed shapes and extremely narrow inter-bone regions. In this paper, we present an automatic and fast approach for segmentation of femoral head and proximal acetabulum which leads to accurate and compact representation of femoral head using marching cubes algorithm. At first, valley-emphasized images are constructed from original images so that valleys stand out in high relief. Otsu’s multiple thresholding technique is applied to seperate the images into bone and non-bone classes. Region growing method and threedimensional (3D) morphological operations are performed to fill holes in the bone. In the reclassification process, the bone regions are further segmented, and the boundaries of the bone regions are further refined based on Bayes decision rule. Finally, marching cubes algorithm is applied to reconstruct a 3D model and extract the outer surface of femoral head and proximal acetabulum. Experimental results show that this method is an accurate segmentation technique for femoral head and proximal acetabulum and it can be applied as a tool in medical practice.     

区分障碍物特性的客车乘客疏散模型与分析

近年来,疏散性能评估已成为客车车厢设施布局及设计流程中的必要环节.考虑狭长通道下障碍物特性对人员疏散影响显著,引入感知域概念,刻画疏散人员翻越座椅等行为决策特性;进一步引入一类多值函数扩充元胞状态集合,量化障碍物的可翻越特性,建立障碍物模型,模拟紧急状态下人员无序疏散行为;为对模型结果验证分析,建立基本模型,构建其与AnyLogic®均可模拟的基本场景,在此场景下对二者模拟结果交叉验证.模拟分析结果及结论是,移动规则合理有效,结合障碍物模型并考虑可翻越障碍物影响的模拟结果是可信的;发现N k O -tk evac 曲线与此情形下的疏散动画具有一定的时空关联性,可为车体设计提供进一步参考;此外,随疏散人员感知域的增大,疏散时间逐渐减小.     

试论行政机关在发展循环经济中的努力途径

作为一种全新的经济发展模式,循环经济在我国尚处于研究探索阶段,我国目前实行循环经济还存在严重的制度障碍、法律障碍和技术障碍。作为国家代表的行政机关应积极发挥主导作用,采取多种途径排除障碍,努力促进循环经济的发展。本文首先论述了行政机关在循环经济中的地位和作用,然后分析了目前我国发展循环经济的主要障碍,最后提出了行政机关在发展循环经济中的努力途径:加快制定循环经济政策;加强行政立法和执法工作;加大循环经济技术研究力度;建立适应循环经济发展要求的行政机关干部考核体系;加强宣传培训,增强公众的循环经济意识等六项措施。     

出租车超速行为道路因素随机系数空间模型构建

为准确揭示道路因素与路段出租车超速行为特征的关联关系，本文以成都市中心城区主 干道路段为研究单元，通过车载GPS设备获取大范围出租车超速行为样本。在筛选出10类典型城市道路特征的基础上，选择路段超速线密度和不同百分位数超速严重度作为研究对象；为减少空间效应对估计的干扰，本文验证了超速特征的空间相关性，并分别构建基于对数-高斯分布的标准线性模型和空间条件自回归模型、空间误差模型及空间滞后模型这3类空间模型，探究不同空间模型与出租车超速行为特征的拟合情况；同时，考虑道路组间异质性，进一步构建随机系数空间模型。结果表明：出租车路段超速线密度和超速严重度均存在显著空间自相关性，空间模型 对其拟合效果普遍优于传统模型；不同超速行为特征适用不同的空间模型，随机系数空间条件自回归模型对超速线密度拟合效果最优，而不同百分位数超速严重度适用的最佳拟合模型差异较大；路段限速、一块板横断面及非机动车车道这3类因素表现出对出租车超速行为特征的组间影响异质性；因素解释方面，路段限速、一块板横断面、非机动车车道、路段施工区与超速线密度显著相关；路段限速、非机动车车道、上下坡匝道、路段施工区及路段长度与超速严重度显著相关。     

基于改进蚁群算法的山区无人机路径规划方法

对无人机在山区执行应急物资运输任务时的飞行路径规划问题进行研究.基于对无人机的性能分析与比选,探讨了路径规划的约束条件,提出了一种考虑路径安全度的改进蚁群算法.首先,基于高海拔山峰的位置构造泰森多边形,获取无人机在山区避障飞行条件下的路径可行解;其次,为避开山峰密集区域,建立路径安全度约束,缩小可行解范围;进而,利用蚁群算法搜索最短路径;最后,消除路径中不必要的障碍点以进一步缩短距离,并综合考虑无人机性能参数对拐角进行平滑处理,获得最终可用于实际飞行的最优安全路径.算例分析表明,改进的蚁群算法较传统算法收敛速度更快,且生成的路径更短.     

基于激光雷达的无人驾驶障碍物检测和跟踪

针对激光雷达动态障碍物检测与跟踪过程中聚类适应性差、实时性低和跟踪准确度不高等问题，提出一种自适应的密度聚类算法和多特征数据关联方法，分别用于检测和跟踪. 首先，对激光雷达采集的点云进行路沿检测、感兴趣区域提取和地面分割等预处理，去除无关点云；然后，基于自适应的密度聚类算法对非地面的点云进行聚类，完成障碍物点云检测；最后，利用加权多特征数据关联算法结合卡尔曼滤波器实现对动态障碍物跟踪. 通过实验表明:本算法能够根据10 Hz的激光雷达数据实现对障碍物准确、稳定的检测和跟踪，且聚类时间缩短32%.      

平行双跑道机场净空障碍物评定

对军用机场净空规格进行了分析,建立了单跑道和平行双跑道机场净空区障碍物限制面的数学模型.在此数学模型的基础上,使用ArcGIS系列软件建立平行双跑道机场净空限制面三角网高程模型,并进行三维显示,将数字高程模型与平行双跑道机场地形图相叠加,对军用平行双跑道机场净空障碍物进行了评定.分析结果表明:障碍物O1、O2、O3三点...     

波流联合作用下隔水套管的涡激非线性振动

考虑流及波流联合作用,研究了套管的涡激非线性振动.将套管简化为梁模型,计及莫里森非线性流体动力和涡激荷载,建立套管的涡激振动方程.采用克雷洛夫函数求解套管的固有频率和模态,提出了计算涡激非线性动力响应的迦辽金方法.以东海勘探3号钻井隔水套管为例,研究了流引起的主共振和波流联合引起的组合共振.计算结果表明:流对套管的动力响应占主导地位,而波的影响不大.分析了前四阶模态、升力系数、流体阻尼系数对套管动力响应的影响.揭示了波流联合激励下套管复杂的动力响应特性.     

A real-time collision-free path planning of a rust removal robot using an improved neural network

In this paper, a real-time collision-free path planning of the rust removal robot in a ship environment is proposed, which is based on an improved biologically inspired neural network algorithm. This improved algorithm is based on the biologically inspired neural network and modified with obstacle detection sensors and kinematic state templates, and is implemented in a ship rust removal robot planning system for dynamic trajectory generation. The real-time optimal trajectory is generated by the biologically inspired neural network, and the moving obstacle detection process of a ship robot working on the wall is simulated with the obstacle detection sensors models. The local real-time trajectory can be re-planned by the updated local map information, where the obstacle detection sensors are used to inspect partial environment information and update the robot nearby information in real time in the original neural network algorithm. At the same time, the method of the kinematic state templates matching and searching is used to solve the pipes’ influence of the rust removal robot climbing on the wall, which can not only provide a smooth path, but also can judge the motion direction and turning angle of the robot. Comparison of the proposed approach with the simulation shows that the improved algorithm is capable of planning a real-time collision-free path with achieving the local environmental information and judging the rust removal robot’s motion direction and turning angle. This proposed algorithm can be good used in the ship rust removal robot.     

字符图像混合二值化方法研究

在模式识别中,二值化效果的好坏直接影响着识别率。针对几种常用的图像二值化自动选取阈值方法,通过计算机仿真试验比较,提出一种全局阈值法和局部阈值法相结合的新的图像混合阈值二值化方法。     

A rapid path planner for autonomous ground vehicle using section collision detection

Rapid path planner plays an important role in autonomous ground vehicle (AGV) operation. Depending on the non-holonomic kinematics constraints of AGV, its path planning problem is discussed. Since rapidly-exploring random tree (RRT) can directly take non-holonomic constraints into consideration, it is selected to solve this problem. By applying extra constraints on the movement, the generation of new configuration in RRT algorithm is simplified and accelerated. With section collision detection method applied, collision detection within the planer becomes more accurate and efficient. Then a new path planner is developed. This method complies with the non-holonomic constraints, avoids obstacles effectively and can be rapidly carried out while the vehicle is running. Simulation shows that this path planner can complete path planning in less than 0.5 s for a 170 m×170 m area with moderate obstacle complexity.