基于Kinect的机器人辅助超声扫描系统研究

提出一种采用Kinect传感器作为视觉伺服的机器人辅助超声扫描系统,来规划引导机器人的扫描路线,以实现机器人辅助的超声扫描操作。系统由Kinect传感器、机器人和超声探头组成。采用Kinect实时获取超声探头的RGB图像和深度图像,并计算探头当前位姿,结合坐标系配准结果,得到机器人的位姿信息,再根据术前的机器人轨迹规划,引导机器人的超声扫描路径。开展腿部模型实验验证本系统的可行性,通过对Kinect传感器的相机标定实验,计算得到了RGB相机和深度相机的内外参数,通过对探头上标识物的定位,进而计算出探头当前位姿,结合Kinect与机器人坐标系的配准结果,得到了两者的转换矩阵,并对机器人的位置给出指令,引导机械臂夹持探头到达指定扫描位置。在机器人夹持超声探头扫描过程中,实时计算探头与腿部之间的距离,以保证所采集超声图像的质量及扫描操作的安全性。实验结果表明,在Kinect视觉系统的导航引导下,机器人可以夹持超声探头实现自主超声扫描,以减少超声医师的扫描时间,降低医师的劳动强度。     

基于视觉定位的脑外科机器人坐标变换问题研究

视觉定位脑外科手术机器人是近年来发展起来的一种新型医疗机器人。该文首先介绍了整个视觉定位脑外科手术机器人系统的构成和手术过程,随后在传统的通过机器人机械臂点取病人头部四个标记点来建立机器人坐标系与患者头部仿射坐标系之间转换关系的基础上,引入视觉定位功能,通过双目视觉建立起机器人坐标系与患者仿射坐标系之间的关系,从而在根本上提高了系统的机器人坐标系,患者仿射坐标系,3维模型坐标系以及世界坐标系之间的转换精度,有利于进一步的机器人精确手术实现。     

双臂搬运机器人结构设计与动态仿真分析

针对棒料搬运和无人机翼下弹药挂装,设计了一种基于双六自由度结构的双臂搬运机器人.对机器人总体构型和各驱动回转及末端执行器等重要部分结构加以阐述.双臂机器人由10个驱动转动环节组成,其中腰部和肩部回转为2个共用关节,双臂各有4个回转关节,组成双六自由度机械臂.机器人通过两臂间的协作可以准确地调整搬运对象的位姿,完成复杂的...     

Arm path planning of a space robot with angular momentum

Arm path planning of a space robot with angular momentum is considered in this paper. A space robot changes its attitude by the arm motion and angular momentum of the space robot has the possibility to reduce the attitude change. A path planning method of the arm where the final satellite attitude becomes the same as the initial one is proposed. The method derives an approximate path first based on the attitude change when the arm moves along an infinitely small closed curve and then modifies the path by the Newton method. The amplitude of the arm motion decreases with the magnitude of the angular momentum, which shows that the proposed method utilizes the angular momentum effectively.     

Vision-based path following by using a neural network Guidance System

This article describes a neural network controller for guidance of a robot arm, used to model some aspects of autonomous vehicle technology. The controller uses video images with adaptive view-angles for the sensory input, and the system was configured to simulate an autonomous vehicle guidance system on a flat terrain using a high-contrast guiding path. To demonstrate the feasibility of using neural networks in this type of application, an Intelledex 405 robot fitted with a video camera and associated vision system was used. Phase I of the project consisted of a single-speed implementation and limited network training. Phase II featured a multi-speed implementation using adaptively varied view-angles based on robot arm velocity. It was shown that the neural network controller was able to control the robot arm along a path composed of path segments unlike those with which it was trained. In addition it was shown that a multi-speed implementation with adaptive view angles improved system performance. © 1994 John Wiley & Sons, Inc.     

基于DH标定的机器人正向运动学形式化验证

DH坐标系在机器人运动学分析中发挥着重要的作用。在基于DH坐标系构建的机器人控制系统中,机器人结构的复杂性使得构建安全的控制系统成为一个难题,仅仅依靠人工方法可能导致系统漏洞和安全风险,从而危及机器人的安全。形式化方法通过演绎推理与代码抽取实现了对软硬件系统的设计、开发及验证。基于此,本文设计了基于DH标定的机器人正向运动学的形式化验证框架。在Coq中构建了机器人运动理论的形式化证明,并验证控制算法的正确性以确保机器人的运动安全。首先,对DH坐标系进行形式化建模,构建相邻坐标系间转换矩阵的形式化定义,并验证了该转换矩阵与复合螺旋运动的等价性;其次,构建了机械臂正向运动学的形式化定义,并对机械臂运动的可分解性进行形式化验证;再次,本文对工业机器人中常见连杆结构及机器人进行形式化建模,并完成了正向运动学的形式化验证;最后,本文实现了Coq到OCaml的代码抽取,并对抽取的代码进行分析与验证。     

基于鱼群算法的智能机器人全覆盖路径规划

为保证机器人的行驶轨迹可以全方位地的覆盖地图的全部坐标点,并降低路径重复率,基于鱼群算法设计智能机器人全覆盖路径规划方法。建立智能机器人死区脱困模型,计算栅格地图模型中的目标活性值,获取整体栅格数量,描述地图中栅格状态,得到脱困时的行驶角度差。基于鱼群算法设计全路径覆盖判定方法,描述不同目标鱼个体之间的距离,在三重移动目标坐标系下,获取元素坐标向量,建立每个目标点的求解代价和,计算下一个目标点行驶的最小距离。设计机器人全覆盖路径规划算法,判断当前位置是否为死区,获取路径规划的全局最优解,实现智能机器人的全覆盖路径规划。利用Matlab仿真软件完成智能机器人全覆盖路径规划实验。结果表明,在简单环境下,该路径规划方法覆盖率为100%,重复率为5.23%,路径长度为15.36m；在复杂环境下,该路径规划方法的覆盖率为100%,重复率则为10.24%,路径长度为20.34m。由此证明,该方法具有较好地规划效果较好。     

基于MATLAB的模块化机器人手臂运动学算法验证及运动仿真

针对由模块化关节构成的六自由度串联机器人手臂, 采用DH法对手臂的操作空间进行了描述, 得到了正运动学模型; 采用欧拉角表示手臂姿态, 得到了包含六个参数的用于表示手臂位姿的完备广义坐标, 并对欧拉角的几何关系进行了分析。针对SolidWorks虽然实体建模简洁方便但计算并非其强项的缺点, 编写相应接口程序, 将建立的手臂三维实体模型保留几何约束关系简化后导入MATLAB软件。基于MATLAB编写正逆运动学算法验证程序以及连杆驱动程序, 实现了手臂的仿真运动。通过仿真, 不仅更进一步验证了手臂正逆运动学解算的正确性, 而且非常直观地看出手臂末端在空间中运行的路径以及各关节的动作情况。机器人手臂正逆运动学算法正确性的验证及运动仿真为手臂的精确定位及其路径规划提供了必要的保证。     

A flexible-arm as manipulator position and force detection unit

This paper presents a self-sensory robot arm to two basic sensing problems in control of flexible manipulators: detection of the position and orientation variations due to structural deformation and detection of the contact force of end-effector when manipulator interacts with its environment. Taking advantage of structural flexibility, a flexible robot arm with strain gauges distributed on it acts as a sensing unit. The position and orientation of flexible arm are expressed as a function of curvature of the arm. An interpolation technique gives this continuous curvature function from a finite set of measurements made with strain gauges. A relation between strain measurements and endpoint force of flexible arm is developed and the contact force of end-effector is then determined using a force propagation algorithm. The proposed technique and algorithm were implemented and evaluated in a laboratorial flexible arm. Experimental validations using a vision system and two force sensors have shown that the self-sensory flexible arm can provide accurate endpoint position and force in both static and dynamic loading situations.     

基于视觉与RFID的机器人自定位抓取算法

为实现机器人灵活的自定位,并使其准确地抓取物体,提出一种基于视觉与无线射频识别(RFID)技术的机器人自定位抓取算法。构建网格化环境,利用RFID技术确定机器人的初始位置、行进路线和方向,使用视觉系统获取物体的空间坐标,将其转换到手臂坐标系,采用改进的D-H模型对手臂进行建模,并给出机械臂逆解抓取算法。实验结果表明,该算法使得机器人定位的成功率达到76.7%,抓取成功率高达90%。     

移动机器人自适应视觉伺服镇定控制

对有单目视觉的移动机器人系统,提出了一种自适应视觉伺服镇定控制算法;在缺乏深度信息传感器并且摄像机外参数未知的情况下,该算法利用视觉反馈实现了移动机器人位置和姿态的渐近稳定.由于机器人坐标系与摄像机坐标系之间的平移外参数(手眼参数)是未知的,本文利用静态特征点的位姿变化特性,建立移动机器人在摄像机坐标系下的运动学模型.然后,利用单应矩阵分解的方法得到了可测的角度误差信号,并结合2维图像误差信号,通过一组坐标变换,得到了系统的开环误差方程.在此基础之上,基于Lyapunov稳定性理论设计了一种自适应镇定控制算法.理论分析、仿真与实验结果均证明了本文所设计的单目视觉控制器在摄像机外参数未知的情况下,可以使移动机器人渐近稳定到期望的位姿.     

Feedback control of robot Arm with discrete nonlinear model

This article looks at the problem of controlling a robot arm from a discrete time perspective. We develop the theories and obtain results that feedback linearizes the discrete nonlinear system representing a PUMA 560 robot arm. The effect of sampling on the performance of the arm has been studied and shown through experiments. The results presented here, where the nonlinear robot model has been linearized and controlled completely in discrete time, are new to the robotics literature. We shown certain restrictions necessary on the sampling time of the system. The results obtained have been experimentally verified at the Center for Robotics and Automation at Washington University. Because a number of researchers have addressed the problem of loss of feedback linearizability under sampling, it was important to develop theories and obtain results in discrete time that take into consideration the effects due to sampling. This problem has been addressed here. Analysis of the control law under the assumptions of bounded input is performed and a recursive sensitivity function is derived. The results we obtain in discrete time show the dependency of the performance of the arm on the sampling time. It has been seen that with a higher sampling frequency the performance of the arm substantially improves and it is expected that close to 1000 Hz sampling rate, the peak performance of the PUMA 560 robot arm, will be reached.     

基于EAIDK的智能煤矸分拣系统设计

现有基于图像识别的煤矸石分拣方法实时性较差且整体分拣准确率不高,而基于密度的分拣方法适用于井下初选,成本较高。针对上述问题,设计实现了一种基于EAIDK的智能煤矸分拣系统。采用嵌入式人工智能开发平台EAIDK构建矸石识别和分拣控制硬件平台,在嵌入式深度学习框架Tengine下利用深度学习算法搭建卷积神经网络,建立端到端可训练图像检测模型,并利用智能摄像机获取的图像数据训练模型;通过手眼标定获得摄像机坐标系与机械臂坐标系之间的关系,控制机械臂进行矸石追踪和分拣。实验结果表明,该系统矸石识别准确率稳定保持在95%以上,机械臂跟踪时间小于30 ms,执行误差为1 mm左右,可以满足煤矸分拣工艺要求。     

配电线路维护机器人虚拟现实仿真系统设计

针对配电线路维护机器人遥显示和在线作业轨迹规划的应用需要,设计了一套机器人虚拟现实三维仿真系统.通过将机械臂姿态信息实时传输到虚拟现实环境中,实现了作业场景3D遥显示功能;根据机器人带电作业需求,设计了一种基于虚拟现实环境的机械臂轨迹规划运动学仿真软件,可在三维虚拟空间测试机械臂作业路径的可行性,具有直观、安全和高效的...     

A path following algorithm for mobile robots

This paper considers path following control for a robotic platform. The vehicle used for the experiments is a specially designed robotic platform for performing autonomous weed control. The platform is four-wheel steered and four-wheel driven. A diesel engine powers the wheels via a hydraulic transmission. The robot uses a Real Time Kinematic Differential Global Positioning System to determine both position and orientation relative to the path. The deviation of the robot to the desired path is supplied to two high level controllers minimizing the orthogonal distance and orientation to the path. Wheel angle setpoints are determined from inversion of the kinematic model. At low level each wheel angle is controlled by a proportional controller combined with a Smith predictor. Results show the controller performance following different paths shapes including a step, a ramp, and a typical headland path. A refined tuning method calculates controller settings that let the robot drive as much as possible along the same path to its setpoint, but also limit the gains at higher speeds to prevent the closed loop system to become unstable due to the time delay in the system. Mean, minimum and maximum orthogonal distance errors while following a straight path on a paving at a speed of 0.5 m/s are 0.0, −2.4 and 3.0 cm respectively and the standard deviation is 1.2 cm. The control method for four wheel steered vehicles presented in this paper has the unique feature that it enables control of a user definable position relative to the robot frame and can deal with limitations on the wheel angles. The method is very well practical applicable for a manufacturer: all parameters needed are known by the manufacturer or can be determined easily, user settings have an easy interpretation and the only complex part can be supplied as a generic software module.     

Lag-Stabilized Force Feedback Damping

A lag-stabilized, force feedback controller for damping initial and residual oscillations of a planar, cantilevered flexible arm has been analytically developed and experimentally implemented on a commercial robot. The controller feeds back force sensor measurements that are delayed in time and proportional to the displacement (angular orientation) of the arm in order to damp the oscillation. As a result of the lag (contrary to popular belief), the controlled robot system is stable and provides tunable performance on a Cincinnati Milacron T3-786 robot.     

A new moving target interception algorithm for mobile robots based on sub-goal forecasting and an improved scout ant algorithm

It is difficult to make a robot intercept a moving target, whose trajectory and speed are unknown and dynamically changing, in a comparatively short distance when the environment contains complex objects. This paper presents a new moving target interception algorithm in which the robot can intercept such a target by following many short straight line trajectories. In the algorithm, an intercept point is first forecasted assuming that the robot and the target both move along straight line trajectories. The robot rapidly plans a navigation path to this projected intercept point by using the new ant algorithm. The robot walks along the planned path while continuously monitoring the target. When the robot detects that the target has moved to a new grid it will re-forecast the intercept point and re-plan the navigation path. This process will be repeated until the robot has intercepted the moving target. The simulation results have shown that the algorithm is very effective and can successfully intercept a moving target while moving along a relatively short path no matter whether the environment has complex obstacles or not and the actual trajectory of the moving target is a straight line or a complex curve.     

基于立体视觉的串联机器人跟踪检测系统

建立一种六自由度串联机器人视觉跟踪检测系统框架,包括图像采集、摄像机标定、机器臂跟踪检测、机器臂位姿建模与计算等。提出利用CamShift算法对机器人进行在线粗跟踪,搜寻和画定出机器臂操作器在当前窗口的区域位置。对跟踪到的机器臂按照SURF算法进行特征提取与立体匹配。该方法被用于对串联机器人位姿检测进行实验。实验结果表明,2种算法的结合适用于六自由度串联机器人在空间复杂运动的跟踪检测。     

A robot to detect and control broad‐leaved dock (Rumex obtusifolius L.) in grassland

Broad‐leaved dock is a common and troublesome grassland weed with a wide geographic distribution. In conventional farming the weed is normally controlled by using a selective herbicide, but in organic farming manual removal is the best option to control this weed. The objective of our work was to develop a robot that can navigate a pasture, detect broad‐leaved dock, and remove any weeds found. A prototype robot was constructed that navigates by following a predefined path using centimeter‐precision global positioning system (GPS). Broad‐leaved dock is detected using a camera and image processing. Once detected, weeds are destroyed by a cutting device. Tests of aspects of the system showed that path following accuracy is adequate but could be improved through tuning of the controller or adoption of a dynamic vehicle model, that the success rate of weed detection is highest when the grass is short and when the broad‐leaved dock plants are in rosette form, and that 75% of weeds removed did not grow back. An on‐farm field test of the complete system resulted in detection of 124 weeds of 134 encountered (93%), while a weed removal action was performed eight times without a weed being present. Effective weed control is considered to be achieved when the center of the weeder is positioned within 0.1 m of the taproot of the weed—this occurred in 73% of the cases. We conclude that the robot is an effective instrument to detect and control broad‐leaved dock under the conditions encountered on a commercial farm. © 2010 Wiley Periodicals, Inc.