中国象棋机器人棋子定位与识别方法

针对中国象棋机器人系统中棋子定位与识别问题,提出了一种基于最小外接圆二次定位的定位方法和一种旋转差分识别算法。首先,采用Hough圆检测进行粗定位获取棋子区域,并对棋子进行均值二值化处理。随后,对二值化图像进行形态学处理,提取最大面积轮廓,并利用其最小外接圆实现棋子二次精准定位。最后,对二次定位修正后的图像进行旋转差分识别。以直径为15 mm的棋子为测试对象,利用我们研制的象棋机器人采集图像进行测试,结果表明,棋子的定位精度为0.5 mm,平均定位时间为2.6 ms;在保证棋子识别正确率在98%以上的情况下,单个棋子平均全流程运算时间为10 ms,完全满足现有象棋机器人需求。     

基于改进RRT*FN算法的机器人路径规划

针对固定节点数的渐近最优快速扩展随机数算法(RRT*FN)精度低、收敛到最优值速度慢等问题,提出一种改进的RRT*FN路径规划算法,并用于解决二维静态环境下的移动机器人全局路径规划问题.首先,改进算法使用与RRT*FN算法相同的均匀采样方法进行路径搜索,当搜索到一条初始路径时,在之后的路径规划中使用启发式采样方法.在之后的每次迭代中,改进算法在椭圆子集采样方法与路径点邻近区域采样方法中随机选择一种作为当前采样方法.然后,当树中的总节点数达到预设值时,对树中的叶子结点采用加权方法进行删除.通过给予采样区域内的叶子结点更高的权重,从而将采样区域外的叶子结点以更高概率删除,得以保留树中的高性能节点,以便提高算法性能.最后,通过仿真实验验证改进算法的有效性.     

Nesterov加速梯度无人机姿态融合算法

传统的无人机梯度下降姿态融合算法的步长难以确定,收敛较慢,动态性能较差,并且对于非重力加速度敏感．针对上述不足,提出了一种Nesterov加速梯度姿态融合方法,融合加速度计与陀螺仪数据并对非重力加速度作抑制处理;利用Pixhawk开源飞控实验平台进行多组对比试验．实验结果表明,Nesterov加速梯度姿态融合算法在机体静止时误差在0.05°之内,在水平滑动实验中产生的误差在0.5°之内,在绕轴转动实验中角度跟随性好、无明显滞后,在实际飞行实验中也获得了良好的实验结果．因此,Nesterov加速梯度姿态融合算法收敛速度明显优于普通梯度下降姿态解算法,抑制非重力加速度的能力明显优于互补滤波与梯度下降法,可有效跟踪无人机的真实姿态变化．     

引入全局上下文特征模块的DenseNet孪生网络目标跟踪

近年来,采用孪生网络提取深度特征的方法由于其较好的跟踪精度和速度,成为目标跟踪领域的研究热点之一,但传统的孪生网络并未提取目标较深层特征来保持泛化性能,并且大多数孪生网络只提取局部领域特征,这使得模型对于外观变化是非鲁棒和局部的。针对此,该文提出一种引入全局上下文特征模块的DenseNet孪生网络目标跟踪算法。该文创新性地将DenseNet网络作为孪生网络骨干,采用一种新的密集型特征重用连接网络设计方案,在构建更深层网络的同时减少了层之间的参数量,提高了算法的性能,此外,为应对目标跟踪过程中的外观变化,该文将全局上下文特征模块(GC-Model)嵌入孪生网络分支,提升算法跟踪精度。在VOT2017和OTB50数据集上的实验结果表明,与当前较为主流的算法相比,该文算法在跟踪精度和鲁棒性上有明显优势,在尺度变化、低分辨率、遮挡等情况下具有良好的跟踪效果,且达到实时跟踪要求。     

非完整移动机器人领航-跟随编队分布式控制

针对非完整移动机器人运动学模型的特点,并且考虑机器人之间的交互关系是局部的,提出了一种基于领航-跟随的非完整多移动机器人分布式编队控制方法。首先提出了一种分布式估计策略,为每个跟随机器人估计(虚拟)领航机器人的位置、方向、线速度等状态;接着利用每个跟随机器人的跟踪误差设计了编队控制算法;使用Lyapunov工具对算法进行了渐近稳定性和收敛性分析;最后,构建了多移动机器人视觉定位与控制实验平台,通过仿真和实验验证了所提算法的有效性。     

Learning deep transmission network for efficient image dehazing

Multimedia Tools and Applications - Single image dehazing algorithms are recently attracting more and more attention from many researchers because of their flexibility and practicality. However,...     

Parallel meta-blocking for scaling entity resolution over big heterogeneous data

Entity resolution constitutes a crucial task for many applications, but has an inherently quadratic complexity. In order to enable entity resolution to scale to large volumes of data, blocking is typically employed: it clusters similar entities into (overlapping) blocks so that it suffices to perform comparisons only within each block. To further increase efficiency, Meta-blocking is being used to clean the overlapping blocks from unnecessary comparisons, increasing precision by orders of magnitude at a small cost in recall. Despite its high time efficiency though, using Meta-blocking in practice to solve entity resolution problem on very large datasets is still challenging: applying it to 7.4 million entities takes (almost) 8 full days on a modern high-end server.In this paper, we introduce scalable algorithms for Meta-blocking, exploiting the MapReduce framework. Specifically, we describe a strategy for parallel execution that explicitly targets the core concept of Meta-blocking, the blocking graph. Furthermore, we propose two more advanced strategies, aiming to reduce the overhead of data exchange. The comparison-based strategy creates the blocking graph implicitly, while the entity-based strategy is independent of the blocking graph, employing fewer MapReduce jobs with a more elaborate processing. We also introduce a load balancing algorithm that distributes the computationally intensive workload evenly among the available compute nodes. Our experimental analysis verifies the feasibility and superiority of our advanced strategies, and demonstrates their scalability to very large datasets.     

Adaptive Tracking Control of Nonholonomic Mobile Manipulators Using Recurrent Neural Networks

International Journal of Control, Automation and Systems - The trajectory tracking problem is considered for a class of nonholonomic mobile manipulators in the presence of uncertainties and...     

自由曲面打磨机器人非奇异终端滑模阻抗控制

针对传统控制方法难以实现对复杂曲面高精度打磨问题,在笛卡尔坐标系下设计了基于非奇异终端滑模的复杂曲面打磨机器人阻抗控制方法。该方法首先根据系统的阻抗模型参数,将设定的打磨轨迹转化为机器人末端可执行的阻抗轨迹,然后设计了基于非奇异终端滑模的控制方法对该阻抗轨迹进行跟踪。对于滑模控制的抖振问题,采用指数趋近律对其进行削弱。基于Lyapunov理论对系统的稳定性进行了证明,仿真和缸体打磨实验结果显示,该方法能够在有限的时间内达到收敛状态且避免了控制奇异的现象,提高了控制系统的鲁棒性和精度。     

Distributed Formation Control of Quadrotor UAVs Based on Rotation Matrices without Linear Velocity Feedback

This paper considers the problem of the formation control for multiple underactuated quadrotor UAVs without linear velocity measurements. The objective of this paper is expected to realize smooth formation performances for a quadrotor group. A distributed formation controller is designed directly using rotation matrices to obviate the singularities associated with the Euler-angles or the ambiguity of quaternions. A two-step procedure is adopted for the control development after transforming the dynamics of each quadrotor into a new form. At first, an intermediary control variable is introduced to achieve the formation control, where some auxiliary systems are designed in the presence of lacking linear velocity measurements. Then, based on the thrust force and reference angular velocity decoded from the intermediary control variable, the torque input of each quadrotor is proposed for angular velocity tracking. The case of formation control with a virtual leader is also investigated, where at least one quadrotor has the information of the leader. The asymptotic stability of the proposed control system is analyzed by Lyapunov-like tools, and the effectiveness of the proposed control method is verified by simulation studies. The simulation results show that the proposed method can guide the quadrotor group to form the desired formation smoothly without linear velocity feedback, which has great potentials for the UAV group to execute the challenging mission in hostile environments.