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…     

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%。     

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.     

Real-Time Fuzzy Obstacle Avoidance Using Directional Visual Perception

This paper presents a novel vision-based obstacle avoidance approach for the Autonomous Mobile Robot (AMR) with a PanTilt-Zoom (PTZ) camera as its only sensing modality. The approach combines the morphological closing operation based on Sobel Edge Detection Operation and the (μ-kσ) thresholding technique to detect obstacles to soften the various lighting and ground floor effects. Both the morphology method and thresholding technique are computationaUy simple. The processing speed of the algorithm is fast enough to avoid some active obstacles. In addition, this approach takes into account the history obstacle effects on the current state. Fuzzy logic is used to control the behaviors of AMR as it navigates in the environment. All behaviors run concurrendy and generate motor response solely based on vision perception. A priority based on subsumption coordinator selects the most appropriate response to direct the AMR away from obstacles. Validation of the proposed approach is done on a Pioneer 1 mobile robot.     

STATICS ANALYSIS AND OPENGL BASED 3D SIMULATION OF COLLABORATIVE RECONFIGURABLE PLANETARY ROBOTS

In the last few years,based on the wide rangeof application domains,multirobot coordination be-came one of the focuses of robotics.M.B.Dias andA.Stentz[1]described a market-based architecturefor coordinating a group of robots to achieve a givenobjective.Terry Huntsberger,Paolo Pirjanian,Pir-janian,Ashitey Trebi-Ollennu,etc,have developedan enabling distributed control architecture calledcontrol architecture for multirobot planetary out-posts(CAMPOUT)[2].CAMPOUT includes thenecessary …     

���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.     

视觉伺服机器人视界内的直接路径规划

建立了GRB-400单目视觉伺服机器人的图像雅可比矩阵，针对此动态双环系统设计了控制算法使视觉伺服闭环运动控制系统稳定．根据视觉伺服闭环运动控制系统的需要，提出了最速下降法与惩罚函数法相结合的平面规划方法,在机器人的视界内解决一定时间内最小能量的路径规划问题．仿真与实验结果表明。机器人根据在其视觉范围内的目标物体的位置即可采用上述方法确定优化的路径。     

COLLISION-FREE OF MULTI-ROBOT SYSTEMS IN VIRTUAL ENVIRONMENT

IntroductionWith the development of automation and con-trol technology,on car- body plant,at present,consideration of multi- robot systems has become abasic requirement. With the help of multi- robotsystems,we can shorten production time,improveproduction quality and quantity,and decrease pro-duction error rate. Buthow multi- robots can coop-erate with each other,especially on welding pro-duction line for car- body,is what we concernabout the most.We hope to find a good way toplan out paths fo…     

夜间动态环境中驾驶员空间距离判识规律

为研究在夜间地面动态环境中驾驶员空间距离判识规律,进行了实际道路试验.32名驾驶员在夜间环境中不同深度距离、速度下,判识红、绿色障碍物空间距离.检验样本差异显著度,分析被试距离判识结果,获得判识特征值.运用曲面回归分析判识距离与速度和深度距离之间关系,获得驾驶员在夜间动态环境中,对空间距离判识变化关系的数学模型.试验结果表明：绝对距离判识值随障碍物深度距离增加而增大,随速度增加而减小.相对距离判识受深度距离影响小,受速度变化影响大,二元二次函数可很好地逼近空间距离判识的变化规律.     

Dynamic Simulation Analysis of Humanoid Robot Walking System Based on ADAMS

Humanoid robots are a hot topic in the field of robotics research. The walking system is the critical part of the humanoid robot, and the dynamic simulation of the walking system is of great importance. In this paper, the stability of the walking system and the rationality of its structural design are considered in the study of dynamics for a humanoid robot. The dynamic model of humanoid robot walking system is established by using the Lagrange dynamics method. Additionally, the three-dimensional model of CATIA is imported into ADAMS. The humanoid robot walking system is added with the movement of the deputy and the driving force in the ADAMS.The torque and angular velocity of the ankle joint and hip joint are analyzed in the process of knee bends. The simulation results show that the overall performance of the humanoid robot walking system is favorable and has a smooth movement, and the specified actions can be completed, which proves the rationality of the humanoid robot walking system design.     

Safety Protection Method of Rehabilitation Robot Based on fNIRS and RGB-D Information Fusion

In order to improve the safety protection performance of the rehabilitation robot,an active safety protection method is proposed in the rehabilitation scene.The oxyhemoglobin concentration information and RGB-D information are combined in this method,which aims to realize the comprehensive monitoring of the invasion target,the patient's brain function movement state,and the joint angle in the rehabilitation scene.The main focus is to study the fusion method of the oxyhemoglobin concentration information and RGB-D information in the rehabilitation scene.Frequency analysis of brain functional connectivity coefficient was used to distinguish the basic motion states.The human skeleton recognition algorithm was used to realize the angle monitoring of the upper limb joint combined with the depth information.Compared with speed and separation monitoring,the protection method of multi-information fusion is safer and more comprehensive for stroke patients.By building the active safety protection platform of the upper limb rehabilitation robot,the performance of the system in different safety states is tested,and the safety protection performance of the method in the upper limb rehabilitation scene is verified.     

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%.      

空间数据库中连续可视反向最近邻查询

为了解决障碍物环境中连续反向最近邻的查询问题,考虑到障碍物的存在,将可视性加到连续反向最近邻查询中,提出了一种新的连续反向最近邻查询的变体——连续可视反向最近邻查询.给出了线段可视性判断方法和相应的剪枝策略,提出了连续可视反向最近邻查询算法.该算法通过过滤步骤得到一个候选集,通过精炼步骤去掉错误的候选,通过分裂步骤找到查询结果.实验结果表明,该算法的执行时间与查询线段的长度呈线性关系增长,查询效率较高.     

沥青路面表面纹理三维高精度激光非接触式检测

为实现沥青路面纹理构造高精度自动检测，借助三维激光技术实现路面纹理三维重构，提出模拟铺砂的沥青路面构造深度测量方法. 首先采用高精度三维激光扫描仪获取雅康高速公路沥青路面0.1 mm精度三维高程数据，同时人工铺砂法获取对应区域的宏观构造深度值；其次通过数字图像处理技术实现重构沥青路面三维云图并进行数据噪声处理；最后设计四连通多种子组合填充算法，实现在滤波后的三维路面纹理云图上自动铺砂并获取路面纹理宏观构造深度值. 研究结果表明:模拟铺砂测量方法与人工铺砂法测量的平均构造深度（MTD，M)的平均绝对误差为0.052 mm，两者相关系数为0.96. 研究成果验证了用非接触式路面纹理测试替代现有的接触式路面摩擦性能测试的可行性，为道路交通安全网级监测与管理奠定基础.      

Modified QUICK schemes for 3D advection-diffusion equation of pollutants on unstructured grids

In the framework of finite volume method (FVM), two modified schemes of quadratic upstream interpolation for convective kinematics (QUICK), namely quasi-QUICK (Q-QUICK) and normal quasi-QUICK (NQ-QUICK), for improving the precision of convective flux approximation are verified in 3D unsteady advection-diffusion equation of pollutants on unstructured grids. The constructed auxiliary nodes for Q-QUICK or NQQUICK are composed of two neighboring nodes plus the next upwind node; the later node is generated from intersection of the line of current neighboring nodes and their corresponding interfaces. The numerical results show that Q-QUICK and NQ-QUICK overwhelm central differencing scheme (CDS) in computational accuracy and behave similar numerical stability to upwind difference scheme (UDS), hybrid differencing scheme (HDS) and power difference scheme (PDS) after applying the deferred correction method. Their corresponding CPU time is approximately equivalent to that of traditional difference schemes. In addition, their abilities for adapting high grid deformation are robust. It is so promising to apply the suggested schemes to simulate pollutant transportation on arbitrary 3D natural boundary in the hydraulic or environmental engineering.     

智能果蔬分拣机器人系统设计

农业机器人的广泛应用是农业机械化得以实现的必由之路与重要标志，也是我国跻身世界农业强国之列的基本前提。基于虚拟样机与3D打印技术，研究建立果蔬分拣机器人运动模型，设计一种多功能欠驱动末端执行器，可对条形和类球形果蔬实施有效抓取；采用运动仿真等相关软件对重要工作部件进行结构分析和优化，确定其最佳参数值；最后搭建试验平台进行验证，并对农业机器人的发展前景进行展望。     

基于三维数值模拟的铁路路基动力特性分析

为探讨列车轴重和运行速度对土质路基动力特性的影响,用ANSYS与FLAC3D软件对有砟轨道-路基系统进行了三维动力数值模拟,在模拟过程中,利用滞后阻尼实现了土体在循环动荷载下的非线性特性.用该方法对达成线循环加载试验段的路基进行建模计算,所得路基动应力与现场实测数据有很好的一致性.在荷载振动频率与客车运行速度的转换过程中,取相邻车厢两个转向架的间距为相邻两个动应力波峰之间的距离,在此基础上,探讨了客车运行速度对土质路基动力性质的影响.研究表明:列车轴重和运行速度对路基表面动应力影响较大,随着轴重的增加和速度的提高,路基表面动应力呈马鞍形分布的趋势愈加明显;动应力沿路基深度的衰减规律受车速的影响很小,不同车速下的动应力在基床表层内都衰减了42%~46%,再经过基床底层的扩散,衰减值达79%~82%.      

基于DEMATEL-ISM的高速公路作业区交通安全影响因素辨识

为提高高速公路作业区交通安全水平,集成DEMATEL-ISM方法对其影响因素进行辨识和分析. 基于人-车-路及环境系统的观点,构建了高速公路作业区交通安全影响因素体系;采用Delphi法分析各因素之间的相互影响关系. 以集成DEMATEL-ISM方法构建了高速公路作业区交通安全影响因素辨识模型;根据多级递阶结构模型的分析结果,确定了影响高速公路作业区交通安全的最直接因素为驾驶员动态判断能力、超速行驶、速度限制、作业区交通量和安全设施布置. 研究结果表明,该方法切实可行,能够对高速公路作业区交通安全影响因素进行定量分析.     

����DEMATEL-ISM�ĸ��ٹ�·��ҵ����ͨ��ȫӰ�����ر�ʶ

为提高高速公路作业区交通安全水平,集成DEMATEL-ISM方法对其影响因素进行辨识和分析. 基于人-车-路及环境系统的观点,构建了高速公路作业区交通安全影响因素体系;采用Delphi法分析各因素之间的相互影响关系. 以集成DEMATEL-ISM方法构建了高速公路作业区交通安全影响因素辨识模型;根据多级递阶结构模型的分析结果,确定了影响高速公路作业区交通安全的最直接因素为驾驶员动态判断能力、超速行驶、速度限制、作业区交通量和安全设施布置. 研究结果表明,该方法切实可行,能够对高速公路作业区交通安全影响因素进行定量分析.     

Mobile Robot Hierarchical Simultaneous Localization and Mapping Using Monocular Vision

A hierarchical mobile robot simultaneous localization and mapping (SLAM) method that allows us to obtain accurate maps was presented. The local map level is composed of a set of local metric feature maps that are guaranteed to be statistically independent. The global level is a topological graph whose arcs are labeled with the relative location between local maps. An estimation of these relative locations is maintained with local map alignment algorithm, and more accurate estimation is calculated through a global minimization procedure using the loop closure constraint. The local map is built with Rao-Blackwellised particle filter (RBPF), where the particle filter is used to extending the path posterior by sampling new poses. The landmark position estimation and update is implemented through extended Kalman filter (EKF). Monocular vision mounted on the robot tracks the 3D natural point landmarks, which are structured with matching scale invariant feature transform (SIFT) feature pairs. The matching for multi-dimension SIFT features is implemented with a KD-tree in the time cost of O(lbN). Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.