基于单目视觉的移动机器人测距方法

本文针对多机器人编队过程中的跟踪控制,提出了一种跟踪机器人采用单目视觉技术获取前方被跟踪机器人距离信息的方法.该方法首先对跟踪机器人摄像机进行内参数标定,并在目标机器人背部设置视觉标记.然后系统获取目标机器人的含有视觉标记的单帧图像,预处理此图像,并识别出图像中的视觉标记所在的目标区域,用Hu氏不变矩计算该区域形心.最后推导出单目测距算法,利用图像信息和其它参数可以计算出两机器人之间的距离.实验结果表明,所设计的单目测距系统能得到准确的距离,为跟踪控制提供了重要的反馈信息.     

Tele-LightSaber——一种高对抗度竞争型网络机器人系统

竞争型网络机器人系统具有交互性强、对实时性要求高等特点．为了研究适用于强交互竞争型网络机 器人系统的控制模式和控制方法,本文设计并实现了一种高对抗度的竞争型网络机器人作业Tele-LightSaber,并在 此基础上提出了将上层人工遥操作与底层视觉伺服相结合的控制模式．最后,分别利用本文提出的控制模式与传统 人工遥操作模式对Tele-LightSaber 作业进行控制,实验结果表明,本文提出的控制模式具有更强的实时性以及更小 的跟踪误差．     

一种五自由度视觉伺服机器人的跟踪控制研究

提出了一种基于图像的视觉伺服机器人系统的结构，以及该系统跟踪平面运动目标的算法. 该系统有5个自由度，包括一个3自由度的机器人和一个2自由度的手腕，手腕安装在机器人末端，而摄像机安装在手腕末端. 由于具有较小的运动惯量，手腕可快速旋转，以实现对运动目标的跟踪. 而在需要时，3自由度的机器人可将摄像机移动到适当的位置， 对目标进行更为仔细的观察. 该系统实现了对运动目标的跟踪. 此外，还提出了提高系统性能的方法，实验证实这些方法是有效的.     

无线传感器网络中改进的多目标定位和跟踪算法

基于无线传感器网络的目标定位与跟踪技术是目前研究的热点,传统的目标跟踪算法均需要明确的目标定位系统观测模型,如无法获得该模型,则算法失效。为此,利用移动机器人客户端,提出一种分布式移动多目标定位和跟踪算法。该算法将所有机器人分为负责目标跟踪的领袖机器人与负责网络阵型和连接性维护的从属机器人,对收敛误差和系统参数间的关系进行分析,并通过仿真实验验证了该算法的有效性。     

基于多传感器的运动训练辅助机器人主动跟踪算法设计

针对运动训练辅助机器人对健美操运动员进行检测与跟踪的准确性问题,提出一种基于多传感器的运动训练辅助机器人主动跟踪算法。首先,对主动跟踪算法的总体方案进行设计,提出了基于视觉传感器的机器人主动跟踪方法和基于声纳传感器的机器人主动跟踪方法;然后,采用基于决策层的数据融合方法将两种跟踪方法获取的跟踪方案进行融合,彼此弥补获取最佳的跟踪方案;最后,通过实验测试提出的算法能否实现机器人对健美操运动员的主动跟踪。实验结果表明：设计的基于多传感器的运动训练辅助机器人主动跟踪算法能够让机器人对健美操运动员进行主动跟踪,且整个跟踪过程能够快速检测到目标并朝之靠拢,同时通过调整自身速度安全、平稳地对目标进行跟踪,能够实现辅助运动员进行训练的目的。     

交互式多模型算法的MT-R机器人视觉跟踪

针对机器人的视觉跟踪问题,提出了一种基于交互式多模型算法的视觉跟踪方法。该方法采用HSV颜色模型,通过交互式多模型算法进行滤波估计,获得目标的运动属性。利用交互式多模型算法对目标的位置进行一步或者N步预测,在获得下一帧的观测值后,在预测位置的区域进行目标搜索,可减少搜索区域,节省搜索时间,增加了跟踪的实时性。使用该方法对机器人足球比赛中的红色球进行搜索跟踪。实验结果表明,应用该方法可获得目标的运动属性,能快速搜索到运动目标,并能进行准确跟踪。     

室内单目机器人视觉目标发现与跟随

本文研究了室内单目机器人上的视觉目标人发现与跟随问题,分为场景变化检测,目标人检测,目标人视觉追踪和目标人主动跟随几个部分,主要研究了场景变化检测算法和目标人视觉追踪算法. 高速的场景变化检测算法通过对场景建模来分析该场景是否变化,为目标检测部分提供潜在变化帧和潜在变化区域. 实验结果表明能够提高系统运行速度,减少机器人运行时的卡顿. 视觉目标追踪算法结合表观模型和SLAM过程得到的地图点信息,估计目标区域内属于背景的部分,减少由于遮挡和目标尺度变化对于追踪算法的表观模型的影响,实验结果相比于对比算法取得较大效果提升. 本文尝试使用近年来效果较好的深度神经网络来进行目标检测. 使用小型深度网络并加强对于室内场景下人的学习,在运行速度和检测效果方面取得较好的平衡. 在视觉目标人的发现和跟踪的基础上,我们实现了机器人的跟随. 由于单目视觉仅能够提供目标的方向信息,所以机器人主动跟随的目标是保持目标人在成像平面的水平居中位置. 在目标无遮挡和部分遮挡的情况下,机器人能够成功的跟随人.     

基于DSP的主动视觉系统

为了提高目标检测的快速性与准确性,简化基于粒子滤波的目标跟踪算法中的直方图计算,提高检测和跟踪算法在基于DSP(数字信号处理器)的主动视觉系统上的运行速度,提出了一种基于DSP的机器人主动视觉系统.该系统通过改进的EMCV(embedded computer vision library)与启发式搜索方法,在DSP上实现了AdaBoost检测算法;利用增量式直方图计算算法实现粒子滤波中颜色直方图与边缘方向直方图的计算,将直方图融合到观测模型中,在DSP上实现并优化了目标跟踪算法.实验证实了该主动视觉系统中算法的快速性与系统的鲁棒性.     

竞争型网络机器人体系结构研究

为了研究适用于强交互竞争型网络机器人系统的通用体系结构,提出并设计了分层的竞争型网络机器人体系结构.在该体系结构中,策略层的职责是识别对手的意图、评估威胁和生成策略.执行层的功能是克服由于观测噪声和时延等因素而造成的系统状态观测的不确定性,以及处理由于对方的敌意行动造成的己方的行动不确定性.物理接口层可将执行层的指令转化为控制机器人的底层命令.设计实现了一种高对抗度的竞争型网络机器人对弈系统——Tele-LightSaber.通过在实际Tele-LightSaber网络机器人平台上的实验,表明了该体系结构的实用性和优越性.     

基于双目视差和主动轮廓的机器人手眼协调控制技术研究

提出一种基于双目视差和主动轮廓的机器人手眼协调技术;该方法利用主动轮廓的思想动态地逼近和跟踪机器人及目标物体的外部轮廓,通过控制双目视差趋零来实现机器人靠近目标和抓取物体.首先建立了机器人手指轮廓的几何参数模型和相应的观测概率密度模型,利用CONDENSATION算法对轮廓进行动态逼近和跟踪.然后针对动态轮廓的几何特征,探讨了基于双目视差的手眼协调控制策略.最后利用这种手眼协调控制技术进行了机器人抓取圆球目标的实验.实验表明,这种方法具有对图像噪声不敏感的特点,可以在杂乱的背景环境和复杂的纹理条件下执行视觉引导的跟踪和抓取任务,具有较强的鲁棒性.     

竞争型网络机器人系统的研究

随着机器人技术的不断发展,网络机器人已经成为当前机器人研究的一个新的热点课题.在网络机器人技术的研究中,大多数学者都关注于多机器人间协作的机器人系统,而另一类网络机器人系统--竞争型网络机器人直到近一两年才被研究者关注.该文讲述了网络机器人的发展历程和竞争型网络机器人概念的产生和基本定义,并分析了对竞争型网络机器人进行研究的意义,希望能够为网络机器人领域的研究者提供有价值的参考意见.     

基于多参数优化的多机器人图案构成的分配算法

在不同应用场景下多机器人系统的图案构成受到越来越多的关注,然而现有方法不能有效地优化在障碍物环境中的图案在线自主构成.为解决这一问题,提出一种新的基于目标匹配和路径优化的实时在线的优化算法.首先,以机器人与虚拟期望图案的距离为目标函数,建立一个多参数的图案构成模型,进而在一定的约束条件下求解得到最优的期望图案参数;其次,建立迭代控制器,使机器人在向目标点移动的过程中,可以实时在线地进行机器人与目标点的分配;然后,采用最佳避碰速度算法使机器人无碰撞地到达期望图案的目标点,完成图案构成;最后,通过在MATLAB和V-REP中的仿真实验,验证所提出方法的正确性和有效性.     

Optimal self assembly of modular manipulators with active and passive modules

In this paper, we develop self-assembling robot systems composed of active modular robots and passive bars. The target structure is modeled as a dynamic graph. We present two provably correct algorithms for creating the structure. A decentralized optimal algorithm for the navigation of multiple modular robots on a partial truss structure is used to guide the robots to their location on the target structure. A decentralized algorithm for scheduling the transportation and placement of truss elements is used to coordinate the creation of the target structure. Both algorithms rely on locally optimal matching. The truss self-assembly algorithm has quadratic competitive ratio for static as well as dynamic graph representation. We show simulation results and results for experiments with two 3DOF robots and passive bars that can create and control a 6DOF manipulation.     

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.     

Classifying the multi robot path finding problem into a quadratic competitive complexity class

We explore two motion planning problems where a group of mobile robots has to reach a target located in an a priori unknown environment while on-line planning the next step. In the first problem the target position is unknown and should be found by the robots, while in the second problem the target position is known and only a path to it should be found. We focus on optimizing the cost of the task in terms of motion time, which, under the assumption of uniform velocity of all the robots, correlates to the path length passed by the robot which reaches the target. The performance of an on-line algorithm is usually expressed in terms of Competitiveness, the constant ratio between the on-line and the optimal off-line solutions. Specifically, the ratio between the lengths of the actual path made by the robot which reached the target to the shortest path to the target. We use generalized competitiveness, i.e., the ratio is not necessarily constant, but could be any function. Classification of a motion planning task in the sense of performance is done by finding an upper and a lower bounds on the competitiveness of all algorithms solving that task. If the two bounds belong to the same functional class this is the Competitive Complexity Class of the task. We find the two bounds for the aforementioned common on-line motion planning problems, and classify them into competitive classes. It is shown that in general any on-line motion planning algorithm that tries to solve these problems must have at least a quadratic competitive performance. This is a lower bound of the problems. This paper describes two new on-line navigation algorithm which solve the problems under discussion. The first is called MRSAM, short for Multi-Robot Search Area Multiplication, and the second is called MRBUG, short for Multi-Robot BUG which extends Lumelsky famous BUG algorithm. Both algorithms have quadratic upper bounds, which prove that the problems they solve have quadratic upper bounds. Thus it is shown that navigation in an unknown environment by a group of robots belongs to a quadratic competitive class. MRSAM and MRBUG have a quadratic competitive performance and thus have optimal competitiveness. The algorithms’ performance is simulated in office-like environments.     

面向网络诱导时延和数据包丢失补偿的网络化广义预测控制

针对网络化控制系统中存在的网络诱导时延和数据包丢失, 考虑了网络化广义预测控制问题. 基于多个数据打包传送的通讯方式以及网络诱导时延和数据包丢失预先可知的假设, 提出了一种采用最小预测步长和预测控制增量向量分别补偿网络诱导时延和数据包丢失对系统性能影响的新方法, 给出了相应的网络化模型预测算法和网络化滚动优化算法, 对于被控对象参数未知或缓慢变化的情况, 给出了基于递推最小二乘辨识改进算法的网络化反馈修正算法, 通过仿真验证了所提出网络化算法的有效性.     

Chance-constrained target tracking using sensors with bounded fan-shaped sensing regions

We present a robust target tracking algorithm for a mobile robot. It is assumed that a mobile robot carries a sensor with a fan-shaped field of view and finite sensing range. The goal of the proposed tracking algorithm is to minimize the probability of losing a target. If the distribution of the next position of a moving target is available as a Gaussian distribution from a motion prediction algorithm, the proposed algorithm can guarantee the tracking success probability. In addition, the proposed method minimizes the moving distance of the mobile robot based on the chosen bound on the tracking success probability. While the considered problem is a non-convex optimization problem, we derive a closed-form solution when the heading is fixed and develop a real-time algorithm for solving the considered target tracking problem. We also present a robust target tracking algorithm for aerial robots in 3D. The performance of the proposed method is evaluated extensively in simulation. The proposed algorithm has been successful applied in field experiments using Pioneer mobile robot with a Microsoft Kinect sensor for following a pedestrian.     

Decentralized Coordinated Tracking with Mixed Discrete–Continuous Decisions

In this paper, we study the problem of dynamically positioning a team of mobile robots for target tracking. We treat the coordination of mobile robots for target tracking as a joint team optimization to minimize uncertainty in target state estimates over a fixed horizon. The optimization is inherently a function of both the positioning of robots in continuous space and the assignment of robots to targets in discrete space. Thus, the robot team must make decisions over discrete and continuous variables. In contrast to methods that decouple target assignments and robot positioning, our approach avoids the strong assumption that a robot's utility for observing a target is independent of other robots’ observations. We formulate the optimization as a mixed integer nonlinear program and apply integer relaxation to develop an approximate solution in decentralized form. We demonstrate our coordinated multirobot tracking algorithm both in simulation and using a pair of mobile robotic sensor platforms to track moving pedestrians. Our results show that coupling target assignment and robot positioning realizes coordinated behaviors that are not possible with decoupled methods.     

未知环境下单目视觉移动机器人路径规划

针对室内未知环境下的避障和局部路径规划,提出了一种单目移动机器人路径规划算法,该算法通过对环境图像的自适应阈值分割,获取障碍物与地面交线轮廓点集。通过对现有几种单目测距方法的分析比较,提出一种改进的空间几何约束单目视觉测距计算方法,并依据单目测距的几何关系建立了图像坐标系与机器人坐标系的映射,绘建了一定比例的局部地图。在局部地图上通过改进的人工势场算法为机器人规划路径,改进的人工势场算法解决了传统算法目标点不可到达的问题。通过MATLAB进行仿真实验,结果表明该方法可以规划出有效合理的路径。