基于红外传感皮肤的多关节机器人自主运动方法研究

本文研究了障碍环境下多关节机器人自主实时避碰运动理论、技术与方法. 研制的新型红外传感皮肤, 可以为多关节机器人提供所需要的周围环境信息. 针对非结构化环境下的多关节机器人实时避障问题, 提出了一种未知环境下的机器人模糊路径实时规划新方法. 实验结果表明: 基于研制的红外传感皮肤和模糊运动规划算法, 多关节机器人可以在未知或时变环境下自主工作.     

机器人导航中势场局部最小的水流解决法

机器人导航理论和技术是机器人技术和智能控制的一个重要研究领域,一般地可分为基于模型的环境已知的全局导航和基于传感器的环境未知的局部导航两种类型.对模型环境提出了一种新的基于虚拟水流的机器人导航算法,它整合了虚拟水流法和势场法用于机器人在已知环境中导航,并时现实的未知环境导航具有指导意义.利用虚拟水流法可以解决势场法中的局部最小的问题.仿真实验表明该算法能够克服势场法中的局部最小点问题.     

未知环境下基于椭圆约束的机器人路径规划

针对未知环境下机器人路径规划问题,提出一种基于椭圆约束的路径规划方法。借助椭圆约束规划路径,将路径规划问题转化为椭圆参数优化问题。通过建立椭圆约束优化模型,引入障碍物和目标位置的约束,考虑机器人运动步长及运动方向的影响,实现复杂未知环境下机器人路径规划。基于不同算法的仿真实验结果表明,该方法有效解决了未知环境下机器人路径规划问题,在大量障碍物存在的未知环境,也能快速有效地进行无碰撞路径规划。     

动态未知环境下基于相对坐标系的移动机器人实时运动规划

提出了一种简单、新颖的在动态未知环境下的移动机器人运动规划方法 .此方法基于相对坐标系 ,通过传感器信息实时调整机器人的行为来实现规划 .在规划过程中 ,机器人有两种行为 :向目标运动和避碰 ,且避碰行为具有优先权 .机器人两种行为的切换是基于加速度空间的 ,首先解决的是避碰问题 ,而向目标运动是作为避碰的反问题来考虑的 .仿真研究验证了此规划方法的有效性     

无路标环境下遥操作机器人SLAM系统

为了提高遥操作机器人的实用性和高效性,设计与开发了一种基于无线网络的无路标未知环境下探索移动机器人系统,其包括移动机器人子系统和机器人远程状态监视子系统.根据机器人功能需求,提出一种多控制器协作及多传感器信息融合的移动机器人硬件结构.利用机器人实时定位和激光测距扫描的能力,提出了一种改进的VFH算法,进行机器人自主局部路径规划.机器人远程状态监视子系统通过无线网络设定机器人的目标点,实时监视机器人状态,并绘制机器人所探索的环境地图.实验表明,开发的探索移动机器人系统具备了在未知环境探索的能力.     

一种动态未知环境下的机器人路径搜索方法

提出了一种新的路径搜索算法——"触觉感知法"来实现机器人在未知静态与动态环境情况下的路径搜索。该方法不需要提供地图信息,机器人仅收集目标点的距离和方位信息以及通过自带传感器作为触觉器收集周围局部环境信息。机器人以BP神经网络作为决策器,经过训练,可以在静态和动态环境中搜索出一条光滑无碰撞且便捷并能有效避开动态障碍物的运动轨迹。对所提出的方法进行了仿真实验,仿真结果表明算法在静态和动态环境下均能有高效率的路径搜索表现。     

基于神经网络的未知环境路径规划算法研究

文章提出了一种新的神经网络算法——“距离定位法”来实现机器人在未知环境情况下的路径规划。地图采用神经元阵列表示,机器人通过自带传感器收集周围局部环境信息以及与目标点的距离信息,经过对局部神经网络的实时训练,可以快速地产生一条光滑无碰撞且简捷有效的运动轨迹。算法在静态和动态环境下均能有高效率的路径搜索表现。模拟仿真结果也证明了算法的有效性。     

智能空间下基于异质传感信息融合的目标跟踪

针对大范围未知环境下的机器人目标跟踪问题,在智能空间下分布式智能网络设备与机器人本体二维激光的基础上,提出了一种基于异质信息融合结构以实现机器人对目标实时检测和跟踪的方法。系统通过颜色信息进行移动目标匹配,根据三角测量原理基于最小二乘法对目标进行三维重建;检测出运动目标后,通过激光传感器扫描目标人腿进行近邻点聚类获得目标的准确深度信息;利用一种优化的迭代扩展卡尔曼滤波算法对异质传感器进行信息融合,以实现基于智能空间的机器人定位与目标跟踪。实验结果验证了方法的有效性。     

未知动态环境下非完整移动群机器人围捕

针对未知动态障碍物环境下非完整移动群机器人围捕,提出了一种基于简化虚拟受力模型的自组织方法.首先给出了个体机器人的运动方程,然后给出了未知动态环境下目标和动态障碍物的运动模型.通过对复杂环境下围捕行为的分解,抽象出简化虚拟受力模型,基于此受力模型,设计了个体运动控制方法,接着证明了系统的稳定性并给出了参数设置范围.不同情况下的仿真结果表明,本文给出的围捕方法可以使群机器人在未知动态障碍物环境下保持较好的围捕队形,并具有良好的避障性能和灵活性.最后分析了本文与基于松散偏好规则的围捕方法相比的优势.     

基于模糊控制器的未知环境下移动机器人导航

研究机器人导航控制优化难题时,为实现未知环境中移动机器人自主导航并解决反应式导航策略中存在的局部陷阱问题,提出一种局部路径规划与目标切换相结合的导航方法.首先分析了移动机器人动力学模型,应用模糊推理构建反应式模糊控制器实现局部路径规划,并提出一种改进的目标切换方式,以机器人与目标相对方向的变化作为陷阱区域判断条件,当检测到陷阱情况时,引入合理的虚拟子目标,面向运动,直到脱离陷阱状态并恢复实际目标.方法可有效驱动机器人在复杂未知环境下以合理的路径脱离陷阱区域到达目标.仿真结果验证了方法的可行性和有效性,为应用于实际系统提供了可靠依据.     

Path planning in GPS-denied environments via collective intelligence of distributed sensor networks

This paper proposes a framework for reactive goal-directed navigation without global positioning facilities in unknown dynamic environments. A mobile sensor network is used for localising regions of interest for path planning of an autonomous mobile robot. The underlying theory is an extension of a generalised gossip algorithm that has been recently developed in a language-measure-theoretic setting. The algorithm has been used to propagate local decisions of target detection over a mobile sensor network and thus, it generates a belief map for the detected target over the network. In this setting, an autonomous mobile robot may communicate only with a few mobile sensing nodes in its own neighbourhood and localise itself relative to the communicating nodes with bounded uncertainties. The robot makes use of the knowledge based on the belief of the mobile sensors to generate a sequence of way-points, leading to a possible goal. The estimated way-points are used by a sampling-based motion planning algorithm to generate feasible trajectories for the robot. The proposed concept has been validated by numerical simulation on a mobile sensor network test-bed and a Dubin’s car-like robot.     

New Traversability Indices and Traversability Grid for Integrated Sensor/Map‐Based Navigation

This paper presents new measures of terrain traversability at short range and long range of a mobile robot; namely, local and global traversability indices. The sensor‐based local traversability index is related by a set of linguistic rules to large obstacles and surface softness within a short range of the robot measured by on‐board sensors. The map‐based global traversability index is obtained from the terrain topographic map, and is based on major surface features such as hills and lakes within a long range of the robot. These traversability indices complement the mid‐range sensor‐based regional traversability index introduced earlier. Each traversability index is represented by four fuzzy sets with the linguistic labels {POOR, LOW, MODERATE, HIGH}, corresponding to surfaces that are unsafe, moderately‐unsafe, moderately‐safe, and safe for traversal, respectively. The global terrain analysis also leads to the new concepts of traversability map and traversability grid for representation of terrain quality based on the global map information. The traversability indices are used in two sensor‐based traverse‐local and traverse‐regional behaviors and one map‐based traverse‐global behavior. These behaviors are integrated with a map‐based seek‐goal behavior to ensure that the mobile robot reaches its goal safely while avoiding both sensed and mapped terrain hazards. This provides a unified system in which the two independent sources of terrain quality information, i.e., prior maps and on‐board sensors, are integrated together for reactive robot navigation. The paper is concluded by a graphical simulation study. © 2003 Wiley Periodicals, Inc.     

一种基于人机交互的移动机器人反应式导航方法

针对未知环境中移动机器人的自主导航问题,提出了一种基于人机交互的反应式导航方法。在采用模糊逻辑实现机器人基本智能行为的基础上,利用基于优先级和有限状态机的混合行为协调方法建立"环境刺激-反应"机制,提高机器人的局部自主能力。提出将"人刺激-反应"机制引入机器人系统,提高机器人系统对环境的理解与决策能力。在不同环境模型中利用提出的方法对移向指定目标的机器人自主导航进行了仿真,仿真结果验证了该方法的有效性。     

Design and Implementation of a Novel Outdoor Road-Cleaning Robot

In order to clean unknown outdoor environments, we devised a novel outdoor cleaning robot using mainly on-board vision-based auto-navigation in this paper. The track-driven and cleaning mechanisms of the robot are designed for cleaning tasks in outdoor rough terrain. A single image sensing module is exploited for clean-region detection and three ultrasonic ranging modules are used for obstacle avoidance. The cleaning task is performed autonomously after the boustrophedon path planning is completed in the grid-cell map. The map is obtained from transforming the two-dimensional images captured by the image sensor. The robot also self-localizes based on the deduced boundary lines at the end of each cleaning stage to continue its unfinished cleaning work. The experimental results prove that our outdoor cleaning robot performs well in general outdoor environments.     

Application of Localization Based on the DC Magnetic Field that Occurs in the Environment on Wheel-Type Mobile Agricultural Robots

A wheel-type mobile robot is simply able to localize with odometry. However, for mobile agricultural robots, it is necessary to consider that the environment is uneven terrain. Therefore, odometry is unreliable and it is necessary to augment the odometry by measuring the position of the robot relative to known objects in the environments. This paper describes the application of localization based on the DC magnetic field that occurs in the environment on mobile agricultural robots. In this research, a magnetic sensor is applied to scan the DC magnetic field to build a magnetic database. The robot localizes by matching magnetic sensor readings against the magnetic database. The experimental results indicate that the robot is able to localize accurately with the proposed method and the cumulative error can be eliminated by applying the localization results to compensate for the odometry.     

基于激光雷达的动态障碍物实时检测

动态障碍的存在直接影响到环境地图的构建精度,可靠实时地检测出动态障碍物是未知环境下移动机器人构建环境地图的根本前提。基于2D激光雷达传感器,提出了一种移动机器人在未知环境下实时检测动态障碍物的方法。将激光雷达的观测数据经过滤波映射到世界坐标系,构建相邻采样时刻的三幅栅格地图;判断相邻时刻三幅栅格地图上对应栅格的占用状态,确定环境中的静态障碍物,以静态障碍物为参考,根据当前的栅格地图可以检测出环境中的动态障碍物。基于激光雷达时空关联性分析,采用八邻域滚动窗口的方法处理不确定性因素。在实际移动机器人MORCS-1上进行的实验结果表明,该方法可使移动机器人准确有效地检测出未知环境中的动态障碍物,实时性好,可靠性高。     

An algorithm for safe navigation of mobile robots by a sensor network in dynamic cluttered industrial environments

Mobile robots have been widely implemented in industrial automation and smart factories. Different types of mobile robots work cooperatively in the workspace to complete some complicated tasks. Therefore, the main requirement for multi-robot systems is collision-free navigation in dynamic environments. In this paper, we propose a sensor network based navigation system for ground mobile robots in dynamic industrial cluttered environments. A range finder sensor network is deployed on factory floor to detect any obstacles in the field of view and perform a global navigation for any robots simultaneously travelling in the factory. The obstacle detection and robot navigation are integrated into the sensor network and the robot is only required for a low-level path tracker. The novelty of this paper is to propose a sensor network based navigation system with a novel artificial potential field (APF) based navigation algorithm. Computer simulations and experiments confirm the performance of the proposed method.     

基于多传感器信息融合的移动机器人避障

为了更好地解决移动机器人在未知环境下的自主避障问题,采用多传感器信息融合的方法,通过多个超声传感器对障碍物信息进行采集。合理确立模糊控制器的输入输出,通过模糊推理将障碍物距离信息模糊化,建立模糊规则并解模糊,以达到对移动机器人的安全避障的控制。通过建立移动机器人运动模型,设计了仿真平台,得到实验结果表明:该算法具有良好的可行性。     

全地形移动机器人轮－地几何接触角估计

研究全地形移动机器人在不平坦地形中轮－地几何接触角的实时估计问题. 本文以带有被动柔顺机构的六轮全地形移动机器人为对象, 抛弃轮－地接触点位于车轮支撑臂延长线上这一假设, 通过定义轮－地几何接触角 δ 来反映轮－地接触点在轮缘上位置的变化和地形不平坦给机器人运动带来的影响, 将机器人看成是一个串－并联多刚体系统, 基于速度闭链理论建立考虑地形不平坦和车轮滑移的机器人运动学模型, 并针对轮－地几何接触角 δ 难以直接测量的问题, 提出一种基于模型的卡尔曼滤波实时估计方法. 利用卡尔曼滤波对机器人内部传感器的测量值进行噪声处理, 基于机器人整体运动学模型对各个轮－地几何接触角进行实时估计, 物理实验数据的处理结果验证了本文方法的有效性, 从而为机器人运动学的精确计算和高质量的导航控制奠定了基础.     

未知环境下移动机器人遍历路径规划

为提高未知环境下移动机器人遍历路径规划的效率,提出了一种可动态调节启发式规则的滚动路径规划算法.该算法以生物激励神经网络为环境模型,通过在线识别环境信息特征,动态调用静态搜索算法和环绕障碍搜索算法,有效减少了路径的转弯次数.引入虚拟障碍和直接填充算法,解决了u型障碍区域的连续遍历问题.最后通过仿真实验表明了该方法在未知复杂环境下的有效性.