智能空间下基于WIFI指纹定位与粒子滤波的服务机器人复合全局定位系统设计

针对机器人在没有任何初始位姿先验知识的情况下,通过传感器感知信息确定位姿的全局定位问题,将智能空间技术与ROS(robot operating system)服务机器人相结合,设计了一种智能空间技术支持下的基于WIFI指纹定位和蒙特卡洛粒子滤波定位的复合服务机器人全局定位系统.在该复合定位方法中,首先利用智能空间中的基于BP(backpropagation)神经网络的WIFI指纹定位对机器人进行粗定位,并将估计位置与估计误差发送给ROS服务机器人;在粗定位的基础上使用蒙特卡洛粒子滤波算法方法最终获得服务机器人的精确位置.实验结果表明,本文设计的系统实现了ROS机器人与智能空间之间的零配置与松耦合,可有效地提高服务机器人全局定位精度,缩短计算迭代时间.     

基于5G通信技术的巡逻机器人定位误差自动补偿方法

以提升巡逻机器人执行巡逻任务能力为目的,提出基于5G通信技术的巡逻机器人定位误差自动补偿方法。该方法在巡逻机器人工作区域架设5G无线通信网络,并将AD7380型号位置传感器安装在巡逻机器人上,利用位置传感器获取巡逻机器人工作时的位置信息后,利用5G无线通信网络将其传输到用户PC端,得到巡逻机器人位置采样点数据；以该数据为基础,使用拉丁超立方采样方法描述巡逻机器人在其巡逻空间内的位置,得到巡逻机器人空间位置数据；再依据巡逻机器人空间位置数据,计算该机器人预设目标点误差矢量,并构建巡逻机器人定位误差补偿模型,利用该模型补偿巡逻机器人定位误差。实验结果表明：该方法可全面获取巡逻机器人在其巡逻空间内的位置信息,可有效且精准的对其定位误差进行自动补偿,使巡逻机器人定位误差保持在可允许范围内,应用效果较为显著。     

自动化立体仓库搬运机器人精定位视觉系统

本文介绍一个搬运机器人的视觉系统.该系统是为机器人在具有较大相对位置偏差的货架中准确存取而研制的.系统由 CCD 摄象机获取货架图象,经过处理,给出精定位数据,从而引导机器人准确定位.     

机器人全向视觉定位系统的建模与应用

针对机器人对目标定位的需要,根据机器人结构及全向视觉系统的特点,研究并建立了包括双曲面镜的反射模型、成像模型在内的一套数学模型.确立了由先验信标位置求机器人位置,由像点和机器人位置求目标位置的数学过程.为目标定位提供了必要的数学模型和算法.定位时,为了减小视觉定位中单幅图像存在的不确定性,提出了基于图像序列及多传感器信息融合的目标定位方法.与传统方法相比,该方法抗外部和系统干扰的能力更强,且精度更高.实验结果证明了方法的有效性.     

基于视觉的机器人定位精度提高方法

定位是确定机器人在其工作环境中所处位置的过程,精确、可靠地实现定位是移动机器人应该具备的一项最基本也是最重要的功能之一。针对机器人在完成穿过门的导航任务过程中,现有的视觉定位方法存在精度不高,不能为机器人的导航提供精确位置信息的问题,提出了一种基于离线学习的方法来得到摄像机的内部参数随机器人位置的变化关系,使机器人在粗定位的基础上,自适应地调节摄像头的内部参数,修正定位结果,达到提高定位精度的目的。实验证明了该方法的有效性。     

基于Netvlad神经网络的室内机器人全局重定位方法

针对已知地图的室内机器人全局重定位、绑架恢复问题,提出一种基于改进的Netvlad卷积神经网络的室内机器人全局重定位方法,通过激光雷达获取的障碍物信息引导机器人到达空旷区域,粗定位阶段,使用栅格地图最短连通域距离作为正样本判据,并对Netvlad引入残差网络,通过图像检索得到机器人的粗略位置及角度信息。使用粗定位阶段得到的位置和角度信息作为自适应蒙特卡罗定位的初始值来估计机器人的精确位姿。实验结果表明,与传统定位方法相比,该方法可以使机器人从绑架问题中快速恢复准确位姿。     

基于红外传感器的移动微机器人定位研究

综合概率论的思想,采用基于红外传感器的微机器人粒子滤波定位方法在已知环境中实现微机器人的自定位.因微机器人受尺寸效应影响无法安装位置传感器,故采用计步的方法存储机器人的运动信息.观测模型采用适合小尺寸微型机器人的红外测距地图匹配方式.因微机器人的存储能力有限,故采用分块存储地图的方法,便于微机器人快速加载地图而完成地图匹配,从而加速其定位过程.实验验证了微机器人的定位性能.     

基于视觉定位的机器人智能拆垛系统

针对传统示教再现机器人仅能进行位置确定、轨迹固定的拆垛任务,局限于固定场景的问题,设计了一个基于视觉定位的机器人智能拆垛系统.该系统利用目标像素中心坐标转换求得对应世界坐标.针对眼在手外的安装相机方式,导致目标经图像处理算法求得的旋转角度可能由于相机自身的偏转而产生误差的问题,提出利用相机外参系数补偿目标旋转角度.最后设计拆垛策略,通信引导机器人以由近及远的抓取顺序执行拆垛任务,并无需人工干预自动完成整垛拆卸.经过实验数据表明,该系统可在未知工作场景中对未知位置目标进行抓取,位置误差可达1.1 mm,角度误差可达1.2°,堆垛一层定位时间为1.2 s左右,满足工业场景中对拆垛机器人的精度与效率需求.     

机器人传感器定位中的模糊性干扰消除仿真

研究机器人准确定位问题.机器人装备的传感器数量较多,不同类型数据采集传感器对环境中突变性因素的敏感程度不同,造成用于定位的传感器信息反馈到终端后融合,结果存在偏差,出现了传感定位信息的模糊性.传统的传感信息融合方法多是根据先验信息进行信息融合,但是机器人传感器采集的多是随机信息,大大增加了融合后定位信息模糊性的可能,造成定位不准.提出了一种机器人定位模糊性寻优遗传算法.通过固定较大小的基因位来改善遗传算法的机器人位置寻优性能,每次基因位的固定都能改变机器人定位的寻优空间,对寻优位置进行细化,消除融合中带来的特征模糊性干扰.后期的仿真结果表明,改进方法可以改善机载机器入的定位能力,定位准确性大幅提高.     

基于多传感器信息融合的机器人导航与定位技术研究

移动机器人已经服务于各个领域,作为室内移动机器人服务的前提是实现机器人精准定位。文章介绍了一种射频识别（Radio Frequency IDentification,RFID）和即时定位与地图构建（Simultaneous Localization and Mapping,SLAM）多传感器融合库存盘点机器人精准导航与定位的方法。通过读取布置在环境中的RFID标签,获取机器人的大概位置信息和准确运动状态,然后结合SLAM技术实现精准定位。实验结果表明,该方法可以使库存盘点机器人精准定位,且系统搭建简单、成本低,对室内机器人定位具有参考价值。     

Introduction of welding robots in shipyards

The great participation of direct human work characterizes today's shipbuilding industry. The actual status in the development of science and technology makes possible the replacement of humans with industrial robots in a large number of these work places. The strategy of the introduction of industrial robots in shipyards has to be adapted to existing working conditions, and the introduction has to be done gradually. This paper deals with a new method for priority setting of industrial robot work places and structures for welding operations in shipyards, based on the analytic hierarchy process. The numerical measure of priority of work places is based on the comparative pairwise judgments of social, psychological, technological, technical, safety, productivity and economical factors on different working locations. After the priority work places and priority working operations are chosen, the priority structures of adequate industrial robots are suggested according to their geometric, kinematic, dynamic and control characteristics.     

Mechatronics and robotics for service applications

Led by the Japanese, industrial robots have been in use for some 20 years. While the level of development in industrial production is already well advanced, the service area is just now emerging as the future field application. The number of service robots currently in operation is small, but the number of people working in the service field shows a constant growth rate. Consequently, there is an enormous potential for the expansion of this sector     

Approach to the dynamically reconfigurable robotic system

In this paper, a newly proposed robotic system called the dynamically reconfigurable robotic system (DRRS), is reconfigurable for given tasks, so that the level of flexibility and adaptability is much higher for a change of working environments than conventional robots which have un-metamorphic shapes and structures. This robotic system consists of many cells which have fundamental mechanical functions. Each cell is able to detach and combine autonomously, so that the system can self-reorganize depending on a task or on working environments, and can also be self-repairing. DRRS has many applications in many fields, e.g. maintenance robots, more advanced working robots, free-flying service robots in space, more evolved flexible automation, etc. This paper shows the concept of this system, the mechanism of cells, the basic experimental results of the rough approach control between cells, and the decision method of such cell-structured manipulator configurations. This method is based on the reachability of the manipulators for working points, and so is able to apply the design of ordinary manipulators.     

On a bio-inspired hybrid pheromone signalling for efficient map exploration of multiple mobile service robots

This paper presents a novel bio-inspired hybrid communication framework that incorporates the repelling behaviour of anti-aphrodisiac pheromones and attractive behaviour of pheromones for efficient map exploration of multiple mobile service robots. The proposed communication framework presents a scheme for robots to efficiently serve large areas of map, while cooperating with each other through proper pheromone deposition. This eliminates the need of explicitly programming each service robot to serve particular areas of the map. The paths taken by robots are represented as nodes across which pheromones are deposited. This reduces the search space for tracking pheromones and reduces data size to be communicated between robots. A novel pheromone deposition model is presented which takes into account the uncertainty in the robot’s position. This eliminates robots to deposit pheromones at wrong places when localization fails. The framework also integrates the pheromone signalling mechanism in landmark-based Extended Kalman Filter (EKF) localization and allows the robots to capture areas or sub-areas of the map, to improve the localization. A scheme to resolve conflicts through local communication is presented. We discuss, through experimental and simulation results, two cases of floor cleaning task, and surveillance task, performed by multiple robots. Results show that the proposed scheme enables multiple service robots to perform cooperative tasks intelligently without any explicit programming.     

Relational Model for Robotic Semantic Navigation in Indoor Environments

The emergence of service robots in our environment raises the need to find systems that help the robots in the task of managing the information from human environments. A semantic model of the environment provides the robot with a representation closer to the human perception, and it improves its human-robot communication system. In addition, a semantic model will improve the capabilities of the robot to carry out high level navigation tasks. This paper presents a semantic relational model that includes conceptual and physical representation of objects and places, utilities of the objects, and semantic relation among objects and places. This model allows the robot to manage the environment and to make queries about the environment in order to do plans for navigation tasks. In addition, this model has several advantages such as conceptual simplicity and flexibility of adaptation to different environments. To test the performance of the proposed semantic model, the output for the semantic inference system is associate to the geometric and topological information of objects and places in order to do the navigation tasks.     

Service robot for the elderly

In recent years, service robots have received a lot of attention from both industry and academia. They are individually designed to performtasks in an unstructured environment for working with or assisting humans [1], [2]. Such robots thus have to be able to actively interact with potential users in their surroundings and to appropriately offer their services. Until now, a number of service robots have been introduced such as vacuum cleaning robots, home security robots, entertainment robots, and guide robots [2]?[4]. In particular, robots that are able to assist the elderly are becoming very important with a dramatic increase in the aging population and costs of elderly care [1], [2], [5]. Several projects have been initiated in some developed countries to develop service robots, especially robotic aid systems [2], [5].     

Web interfaces for mobile robots in public places

The growth of the World Wide Web provides unique opportunities to bring robots closer to people. The vision behind such endeavors ranges from relatively simple web-based inspections and surveillance applications to highly versatile applications that use robots connected to the web to establish a remote telepresence in dynamic and populated environments. In the latter scenario, robots play the role of a physical mediator, enabling remote people to acquire information, explore, manipulate, communicate, and interact physically with people far away. The article describes a series of web interfaces designed to remotely operate mobile robots in public places through the web. The design of these interfaces specifically addresses issues such as low bandwidth of interconnections, control brokering, and shared control as well as interaction with people in the robot's environment, which arise naturally in applications with web-based robot control. The interfaces have been tested extensively using two deployed service robots, which were installed as interactive tour guides in two museums. The article also discusses trade-offs and limitations of web-based robots that interact with people in populated public places     

面向迁移实例旅行图动态适应性的目录服务研究*

迁移工作流是一种基于迁移实例在工作位置之间连续迁移并就地利用位置服务执行任务的工作流管理模式,许可的工作位置及迁移顺序由预先规划的旅行图约定。针对一旦工作位置故障或服务发生变化,预先规划的迁移路线就不能实现,从而影响迁移工作流的可靠执行,提出了一种分布式目录服务结构。该结构通过对目录服务组件的设计,不仅支持迁移实例旅行图的静态规划,而且支持基于服务推荐的迁移路线的动态修正,从而大大提高了迁移实例旅行图的动态适应性。     

Identification of types of obstacles for mobile robots

For service robots coexisting with humans, both safety and working efficiency are very important. In order for robots to avoid collisions with surrounding obstacles, the robots must recognize obstacles around them. In dynamic environments, not only currently moving obstacles but also movable obstacles should be recognized. In this paper, three types of obstacles, such as stationary, movable and moving, are defined, and a method to identify the type of obstacles is proposed. The experiments using a mobile robot were conducted to evaluate the usefulness of the method.     

基于“原型”的机器人开放式室内场所感知算法

随着现代开放式室内设计理念的流行,一些功能场所逐渐转变为开放或半开放式,对这类场所的认知成为服务机器人面临的新挑战.文中提出一种基于认知心理学原型理论的算法来提高机器人对开放式室内场所的认知能力.首先,设计场所概念的原型模型,主要包括场所概念的特征物品描述和物品间典型空间关系描述.然后提出一种相似性度量函数及一种空间关系评分准则,将两者用于度量当前环境与场所概念原型的相似程度.最后,讨论场所区域感知问题及区域交叠对场所概念感知的影响.仿真实验表明,该算法能够解决对开放式室内场所的感知,具有一定灵活性和鲁棒性.