APP下载

基于多层感知人工神经网络的执行机构末端综合定位

2016-04-09胡燕祝李雷远北京邮电大学自动化学院北京100876

农业工程学报 2016年1期
关键词:机械臂机械化控制

胡燕祝,李雷远(北京邮电大学自动化学院,北京100876)



基于多层感知人工神经网络的执行机构末端综合定位

胡燕祝,李雷远
(北京邮电大学自动化学院,北京100876)

摘要:非标准化执行机构的雅可比矩阵和连杆坐标系往往难以确定,导致任务空间的定位性难以分析。论文提出并证明综合型定位方法的充分必要条件,即完成多种特别定位任务的充要条件;用反向传播的多层感知人工神经网络(MLP, multilayer perceptron neural network)求解逆运动学模型,在笛卡尔空间,把执行机构D-H(denavit-hartenberg)参数作为训练集,对神经网络进行训练;定义一个函数,判断执行机构定位到目标点的性能,即可定位性。经仿真验证,神经网络求解逆运动学模型,较传统方法缩短了计算时间,计算效率提高20%,精度提高2.4%,可定位性最小值为0.96,最优运动学函数值4.0349×1014。

关键词:机械化;控制;模型;机械臂;神经网络;逆运动学

胡燕祝,李雷远.基于多层感知人工神经网络的执行机构末端综合定位[J].农业工程学报,2016,32(01):22-29.doi:10.11975/j.issn.1002-6819.2016.01.003 http://www.tcsae.org

Hu Yanzhu, Li Leiyuan.Series actuator end integrated positioning analysis based-on multilayer perceptron neural network [J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2016, 32(01): 22-29.(in Chinese with English abstract)doi:10.11975/j.issn.1002-6819.2016.01.003 http://www.tcsae.org

0 引言

标准化执行机构较为通用,但也不能保证执行最优的任务,工业执行机构只能重复执行一系列给定任务。由此,特殊任务或带有优化任务的非标准化执行机构是急需的,如个性化精密制造、装配和包装等。若要完成这些个性化任务,则必须对执行机构的定位性或可到达。

空间性进行分析。本文分为3步,第1步,确定D-H (denavit-hartenberg)参数,建立正运动学模型[1],证明综合定位任务的充要条件;第2步,人工神经网络(ANNs,artificial neural network)求解逆运动学;第3步,建立定位性函数,评价定位任务性能。

非标准化执行机构定位性分析方法可分为3种,几何分析法、参数优化分析法和基于任务分析法。几何分析法有其局限性,不能扩展和应用到棱形连杆结构,同时不满足多任务定位需求;参数优化法的主要缺点是受限于关节自由度和关节极限位置等;基于任务的分析方法应用先验知识,生成齐次变换矩阵和定位动态参数;Paredis和Kholsa[2]应用基于任务分析方法产生D-H参数,并对6-DOF(degree of freedom)标准化执行机构末端进行定位分析;Kholsa等[3]在任务分析法基础上,提出任务描述概念,进行运动学建模、定位规划和定位控制等。本文在任务分析法的基础上,对非结构化执行机构进行定位问题描述、建立综合充要条件和定位性评价。

雅可比矩阵在执行机构的运动学分析中具有重要地位,机器人的分离速度控制、静力分析和灵活性和可操作度分析等都要用到机器人的雅可比矩阵[4]。雅可比矩阵的构造方法有矢量积法、微分变换法、力和力矩递推法和速度递推法。基于雅可比矩阵能够分析稳定性(特征根)、雅可比矩阵的奇异性用矩阵的秩来描述,满秩时,可进行奇异值分解;不满秩时,执行机构处于奇异位形。执行机构的灵活性与运动学逆解的精度与雅可比矩阵奇异值有关。同时,雅可比矩阵是由关节速度映射到执行机构末端速度,因此也是构成综合定位[5]充要条件的关键因素之一。

已知执行机构末端在操作空间中的位姿,利用逆运动学解出关节角度。传统的逆运动学求解方法有几何法、迭代法、代数法和Particle Swarm优化法等。其封闭解也不是万能的,只有在执行机构的雅可比矩阵为满秩时才成立。其次,逆运动学方程通常没有独一无二的解,因为在关节空间中,执行机构存在多个位姿,使之定位到任务空间中的目标位置。逆运动学求解时,应避免奇异性域,奇异性即是执行机构的2个或更多个旋转轴共线引起的不可预测的运动和速度。奇异性的存在影响执行机构末端的定位,人工神经网络逆运动学求解方法可以尽量消除奇异域[6]。在网络训练和学习时,通过Levenberg-Marquart (LM)算法优化均方差(MSE)。以奇异点处的笛卡尔坐标作为测试集,以执行机构笛卡尔坐标和D-H参数作为训练集。

为了判断非标准化执行机构末端能否定位到给定点,及到达给定点的收敛程度,引入可到达性函数,即可定位性函数[7-8]。可定位性函数反映非标准化执行机构运动学性能。

1 运动学分析

首先,对论文中用到的一些空间参数和变量进行说明,ΓT表示任务空间,ΓQ关节空间,r1表示大臂长度,r2表示小臂长度,r3腕部长度,ΓQC受限的关节空间,qi各关节运动矢量,ξE执行机构末端位姿,ΓC配置空间,0AE基座相对于执行机构末端的变换矩阵,ΓW可到达或可定位空间,ΓCW受关节限制的可到达或可定位空间。

非标准化执行机构具有5个自由度3连杆,如图1a。5个旋转轴分别为腰部旋转轴,大臂俯仰轴,小臂俯仰轴,腕部俯仰轴和腕部旋转轴。5关节分别为腰部旋转关节,大臂俯仰关节,小臂俯仰关节,腕部俯仰关节和腕部旋转关节。角度仪测量各关节极限角度,以车体水平面作为参考平面,如表1所示。

图1 非标准化执行机构及坐标系Fig.1 Non standardized execution mechanism and DH parameter coordinate system

表1 执行机构工作空间和最大转速Table 1 Working space and maximum speed of actuator

{a,α,d}表示旋转型连杆参数,{a,α,θ}表示棱型连杆的参数。标准D-H参数存在限制性,其关节必须绕z轴旋转,连杆在x轴上产生位移。在配置空间ΓC中,5(N)自由度执行机构具有15(3N)个配置参数,因此D-H参数集构成了一个15维的ΓC空间,表达如下:

正运动学模型可用下列函数表示:

表示执行机构末端的运动矢量,q为各关节运动矢量。正运动学变换矩阵是1个4×4方阵。n,b和t分别表示执行机构末端在x,y和z轴的方向,p表示执行机构末端的位置(笛卡尔坐标系)。

在空间ΓCW内,执行机构末端的空间坐标为:

2 综合定位充要条件

非标准化5轴执行机构完成综合定位任务的充要条件为:能够找到所有的D-H参数满足(DH,q)=p且rank(Jacobian(q))=5。证明如下。

充分性:若非标准化5轴执行机构可以完成综合定位任务,则能够找到所有的D-H参数满足∀p∈ΓT,∃q∈ΓQCf(DH,q)=p且rank(Jacobian(q))=5。

众所周知,DH∈ΓC,ΓCW⊂ΓW,ΓQC⊂ΓQ,设P是ΓT内的一个点集,

ΓT内的每一个点含有6个维度,分别用执行机构末端的位置和方向进行定义,如下:

对于5自由度的非标准化执行机构,其ΓQ维数为5,所以,关节向量为:

每个关节在ΓQC内,都有其极限位姿,上限位姿和下限位姿约束为:

定义ΓW为无关节限制时非标准化执行机构末端能够达到或定位到的世界坐标系内所有点的集合[11-15]。根据正运动学原理(2)得到映射,

同理,在ΓWS内,且ΓCW⊂ΓW,ΓQC⊂ΓQ,

再由(1)式,得

由于执行机构任务空间存在奇异性,通过雅可比矩阵予以避免。对(2)求导,

执行机构雅可比矩阵[16-17]是1个6×N矩阵,N为关节数。为了避免奇异性,rank(J(DH,q))=5。推导出结论:存在D-H参数满足且rank(Jacobian(q))=5。

必要性:如果能够找到D-H参数满足∀p∈ΓT,∃q∈且rank(Jacobian(q))=5,则非标准化5轴执行机构能够完成综合定位任务。

3 人工神经网络逆运动学求解

给定任务空间执行机构末端的位置坐标(X,Y,Z),通过ANNs确定执行机构各关节角度θ1,θ2,θ3,θ4和θ5。神经网络采用前馈多层感知(MLP,multilayer perceptron neural network),把执行机构的笛卡尔坐标和D-H参数作为训练集[18-20],不断更新神经网络权值,使均方误差参数(MSE, mean square error)达到最小;验证集,确定网络结构或者控制模型复杂程度的参数,当泛化值停止改善时,停止训练;训练后,用测试集对神经网络性能进行独立测试。

MLP前馈反向传播网络用权值(w)和偏移量(b)表示如下:

xi为网络输入,即(X,Y,Z);wi为每个输入的权值;b为偏移量;S为输出,即(θ1,θ2,θ3,θ4,θ5);神经网络架构,如图2所示。

图2 神经网络架构Fig.2 Neural network architecture

采用Levenberg-Marquardt(LM)算法[21-23]训练MLP网络,通过调整学习速率,获得最优权值wi,并且使均方误差(MSE)取得最小值。LM算法以Newton算法和梯度下降算法为基础,取误差函数Ei的1阶导数,使全局误差最小[24]。表达式为,

d为Ei的1阶导数,ds为Ei的2阶导数,e为自然对数函数,λ为阻尼因子。均方误差函数的表达式如下,

Ei为第i个输入数据的误差,n为输入数据数量。

MLP神经网络采用有监督学习,包含3个输入,带有20个神经元的隐层,5个输出。隐层具有tansigmoid激励函数,范围[-1,1];输出层具有pureline线性激励函数。

神经网络训练集、验证集和测试集是归一化后的数据,要求取值范围在(0,1)内,所以采用归一化函数f(x)=1/(1+e-x)。证明如下,令x∈(-∞,∞),

4 可定位性函数

神经网络训练出来的模型,进行逆运动学求解时[25],不存在复数解,因此,不考虑复数解情况。建立一个可定位性函数,判定执行机构末端能否按照需要的方向到达任务空间中目标点[26-29]。利用归一化模型,评价ΓT空间中任意点的可定位性,

g为点p对应所有运动学逆解的数量,函数reachability(DH)取值范围为[0,1]。当取(0,1)时,逆运动学解中至少有一组受关节限制而无法定位到;当取0时,最优解中至少有一个关节角度超过极限位置;当取1时,最优解中所有关节都处于中间位置,无论哪一组解都可以定位到目标点[30-31]。最优逆运动学解选取,即执行机构的最优配置,函数如下,

其中,J(DH,q1)是6×5的矩阵,JT(DH,q1))J(DH,q1)为5×5矩阵,评价ΓQ内NUM个点的可定位性能,

评价ΓT内定位到NUM个点的运动学性能,有

取目标函数的最大值,是为了找到目标点处的最合适的速度变换矩阵,即雅可比矩阵。雅可比矩阵是由关节速度到执行机构末端速度的映射,能够反映执行机构的运动学性能。

5 试验与分析

此执行机构的标准D-H参数如表2。DH参数对应的正运动学变换矩阵为,

所以,初始状态末端空间坐标为(433.5,0,-255.4)。由正运动学推导末端运动区域,如图3所示,图中各个点表示执行机构末端所能达到的空间坐标,近似球形。执行机构末端运动范围构成ΓT,所以∀p∈ΓT,∃q∈ΓQCf(DH,q)=p。此执行机构的雅可比矩阵是一个6*5矩阵,初始状态下DH参数对应的雅可比矩阵为,

表2 标准D-H参数Table 2 Standard D-H parameters

图3 末端运动范围Fig.3 Manipulator end motion range

利用传统方法计算逆运动学解,共2 000组数据,在ΓT内,(X,Y,Z)数据随机生成,如图3中的点集,逆运动学解为(Θ1,Θ2,Θ3,Θ4,Θ5),并将(X,Y,Z,Θ1,Θ2,Θ3,Θ4,Θ5)数据按列归一化,归一化函数为f(x)=1/(1+e-x)。1 400组(X,Y,Z,Θ1,Θ2,Θ3,Θ4,Θ5)作为训练样本,构成1400*8维矩阵,用试凑法确定最佳隐层节点数,先设置较少的隐节点训练网络,然后逐渐增加隐节点数,进行训练,确定网络误差最小时对应的隐节点数为20;最大训练次数为28 302,训练目标误差设置为1×10-4,动量因子常数为1×10-4,学习速率为1×10-5,学习速率增加比率为5,学习速率减少比率0.5;引起训练结束的条件是Validation Checks为20,训练时间47 s,迭代30次,均方误差为5.96×10-5,梯度值为0.028 8;500组作为验证样本,维数500×8,100组测试样本,维数100×8。训练样本和测试样本相互独立。θ1到θ5的网络输出和理论计算值之间的误差Err=网络估计值-理论计算值,如图4,θ1的估计误差最大约为3.7,θ2的最大估计误差约为3.1,θ3的最大估计误差约为3.5,θ4的最大估计误差约为3.3,θ5的最大估计误差约为4.5,所有实际误差均在5以内,能够满足实际需求。

采用神经网络解逆运动学,需要在计算时间和精度之间进行权衡,往往是缩短了计算时间,而精度却不理想。传统算法计算时间为1.2 s,神经网络训练好后,计算时间为0.9 s,效率提高了20%。Luv Aggarwal等用神经网络求解精度为87.5%,论文神经网络求解精度为89.9%,提高了2.4%。因此,在实时性要求不高而精度要求较高时,应该采用传统计算方法,而在实时性要求较高而精度要求不高且系统为非线性时,可以选择神经网络求解方法。

表3 定位到(41.4, 89.0, 104.5)时第1组解Table 3  First group solutions of positioning to(41.4, 89.0, 104.5)

图4 网络估计值与理论计算值的误差Fig.4 Error between estimated value and calculated value

在ΓT内,∀p∈ΓT,设定位点p=(41.4,89.0,104.5),逆运动学解如表3和表4,共2组解。由式(18),可计算每一组逆运动学解的可定位性值,如图5(a),用红色’.’表示,轴表示第几组逆运动学解,y轴表示对应的定位性值。第21组逆运动学解的可定性函数值最小,因此在p点处的可定位性为reachability(DH)=0.96,蓝色’o’表示;最优运动学性能为configuration(DH)=4.034 9×1014,1~21组解的最优运动学性能如图5(b)所示,用红色’.’表示,x轴表示第几组逆运动学解,y轴表示对应的最优运动学性能值,蓝色’o’表示最优运动学性能值中最大值。从图中可以看出,第12组逆运动学解(21.61,125.73,108.42,99.41,0)可以达到最优运动学。

表4 定位到(41.4, 89.0, 104.5)时第2组解Table 4 Second group solutions of positioning to(41.4, 89.0, 104.5)

图5 点的可定位性及运动学性能分布Fig.5  Distribution of localization and kinematic performance for a point

6 结论

为满足用户个性化需求,需对执行机构的结构重新设计,提出可定位性充要条件,在满足精度要求的前提下,尽量提高执行机构逆运动学求解效率,并对可定位性定量分析,其实质是基于可定位性的最优配置。论文对可定位性充要条件进行证明,计算执行机构末端任务空间的运动范围,训练基于MLP的神经网络并逆运动学求解,效率提高了20%,精度提高2.4%,并举例计算p=(41.4,89.0,104.5)时,可定位性值reachability(DH)=0.96,configuration(DH)=4.039×1014。接下来工作完成一整套环形或平面多点等任务的最低功耗研究。

[参考文献]

[1]张晓燕,孙剑桥,丁千.5自由度机械臂的运动学分析与时滞控制[J].西安交通大学学报,2013,10(47);103-108.Zhang Xiaoyan, Sun Jianqiao, Ding Qian.Kinematics analysis and time delayed control of a five-degree of freedom manipulator [J].Journal of Xi’An Jiaotong University, 2013, 10(47): 103-108.(in Chinese with English abstract)

[2] Paredis C J, Khosla P K.Kinematic design of serial link manipulators from task specifications[J].IntJ Robotics Res, 1993, 12(3): 274-87.

[3] Khosla P K.A multi-population genetic algorithm and its application to design of manipulators[J].In: Proc.IEEE/RSJ int conf on intell robots and syst, 1992, 3(24): 7-10.

[4]李诚,谢志江,倪卫,等.六自由度装校机器人雅可比矩阵的建立及奇异性分析[J].中国机械工程,2012,5(11):1165-1169.Li Cheng, Xie Zhijiang, Ni Wei, et al.Establishment of jacobian matrix and singularity analysis of a 6-DOF installing calibrating robot[J].China Mechanical Engineering, 2012, 5(11): 1165-1169.(in Chinese with English abstract)

[5] Sarosh P, Tarek S.Task based synthesis of serial manipulators[J].Journal of Advanced Research, 2015, 39(8):2-7.

[6] Luv A, Kush A, Ruth J U.Use of artificial neural networks for the development of an inverse kinematic solution and visual identification of singularity zone [J].Variety Management in Manufacturing, 2014,8(10):812-817.

[7] Tian T X, Jiang H Z, Tong Z Z, et al.An internal parameter identification method of eliminating system damping effect for a six-degree-of-freedom parallel manipulator[J].Chinese Journal of Aeronautics, 2015, 12(24): 450-457.

[8] Monika Z F, Ana M D.Complexity analysis for calculating the jacobian matrix of 6-DOF reconfigurable machines[J].Variety Management in Manufacturing, 2014, 2(19): 218-223.

[9]任子武,王振华,李娟,等.基于混合类电磁机制算法的机械臂逆运动学解[J].机械工程学报,2014,17(48):21-27.Ren Ziwu, Wang Zhenhua, Li Juan, et al.Inverse kinematics solution for robot manipulator based on hybrid electromagnetism-like mechanism algorithm [J].Journal ofMechanical Engineering, 2014, 17(48):21-27.(in Chinese with English abstract)

[10]高自成,李立君,李昕,等.齿梳式油茶果采摘机采摘执行机构的研制与试验[J].农业工程学报,2013,10(27):38-44.Gao Zicheng, Li Lijun, Li Xin, et al.Development and test of picking actor in oil-tea camellia fruit picking machine of tooth comb type[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2013, 10(27): 38-44.(in Chinese with English abstract)

[11]章德宾,徐家鹏,许建军,等.基于监测数据和BP神经网络的食品安全预警模型[J].农业工程学报,2010, 1(6):55-62.Zhang Debin, Xu Jiapeng, Xu Jianjun, et al.Model for food safety warning based on inspection data and BP neural network [J].Transactions of the Chinese Society of Agricultural (Transactions of the CSAE), 2010,1(6):55-62.(in Chinese with English abstract)

[12] Yong J K, Shan B C, Sang B K, et al.A stiffness-adjustable hyper redundant manipulator using a variable neutral-line mechanism for minimally invasive surgery [J].IEEE Transactions on Robotics, 2014,2(30): 382-394.

[13] Matteo C P, Luca C, Giacomo P, et al.Analysis and design of a reconfigurable 3-DoF parallel manipulator for multimodal tasks [J].IEEE/ASME Transactions on Mechatronics, 2015, 4(20): 1975-1984.

[14] Janne K, Jouni M.Stability-guaranteed force-sensorless contact force/motion control of heavy-duty hydraulic manipulators [J].IEEE Transactions on Robotics, 2015, 4(31): 918-934.

[15] Rong J W, Rajkumar M.Design of fuzzy-neural-networkinherited back stepping control for robot manipulator including actuator dynamics [J].IEEE Transactions on Fuzzy Systems, 2014, 4(22): 709-721.

[16] Ahmet D, Koksal E.Trajectory tracking control for a 3-DOF parallel manipulator using fractional-order control [J].IEEE Transactions on Industrial Electronics, 2014, 7(61): 3417-3423.

[17] Sehoon O, Kyoungchul K.Two-degree-of-freedom control of a two-link manipulator in the rotating coordinate system[J].IEEE Transactions on Industrial Electronics, 2015, 9(62): 5598-5607.

[18] Kim S M.Lumped element modeling of a flexible manipulator system[J].IEEE/ASMETransactionson Mechatronics,2015,2(20): 967-973.

[19] Chu Z Y, Cui J, Sun F C.Fuzzy adaptive disturbance-observerbased robust tracking control of electrically driven free-floating space manipulator[J].IEEE Systems Journal, 2014, 2(8):343-351.

[20] Luca C, Massimo C, Giacomo P.Analysis of kinematics and reconfigurability of a spherical parallel manipulator[J].IEEE Transactions on Robotics, 2014, 6(30):1541-1546.

[21]吴玉香,王聪.基于确定学习的机器人任务空间自适应神经网络控制[J].自动化学报,2013,6(39):806-815.Wu Yuxiang, Wang Cong.Deterministic learning based adaptive network control of robot in task space[J].Acta Automatica Sinica, 2013, 6(39): 806-815.(in Chinese with English abstract)

[22] Mai T L, Wang Y N.Adaptive force/motion control system based on recurrent fuzzy wavelet CMAC neural networks for condenser cleaning crawler - type mobile manipulator robot[J].IEEE Transactions on Control systems Technology, 2014, 5(22):1973-1981.

[23] Long J, Zhang Y N.Discrete-time neural network for online timevarying nonlinear optimization with application to manipulator motion generation[J].IEEE Transactions on Neural Networks and Learning Systems, 2015,7(26):1525-1531.

[24]张凯良,杨丽,张铁中.草莓收获机器人采摘执行机构设计与试验[J].农业机械学报,2011,9(42):155-160.Zhang Kailiang,Yang Li, Zhang Tiezhong.Design and experiment of picking mechanism for strawberry harvesting robot [J].Transactions of the Chinese Society for Agricultural Machinery, 2011, 9(42): 155-160.(in Chinese with English abstract)

[25] TanN.Calibrationforaccuracyimprovementofserialmanipulators based on compressed sensing[J].Electronics Letters, 2015, 11 (51): 820-822.

[26] Luciano C, Giovanni M, Marco N, et al.A joint-angle estimation method for industrial manipulators using inertial sensors [J].IEEE/ASME Transactions on Mechatronics, 2015, 5(20): 2484-2494.

[27] Hamid S, Luigi V, Mehdi K, et al.Task-space control of robot manipulators with null-space compliance [J].IEEE Transactions on Robotics, 2014, 2(30): 493-505.

[28] Liu YC,Nikhil C.Gravity-compensation-drivenpositionregulation forroboticsystemsunderinput/outputdelays[J].IEEETransactions on Control Systems Technology, 2014, 3(22): 995-1003.

[29] Kern J, Jamett M, Urrea C.Development of a neural controller applied in a 5-DOF robot redundant[J].IEEE Latin America Transactions, 2014, 2(12): 98-106.

[30] Spencer B B, Aaron M D.Robust resonant frequency-based contact detection with applications in robotic reaching and grasping[J].IEEE/ASME Transactions on Mechatronics, 2014, 5 (19): 1552-1561.

[31] Corrado G, Lo B, Fabio G.Real-time planner in the operational space for the automatic handling of kinematic constraints [J].IEEE Transactions on Automation Science and Engineering, 2014, 3(11): 730-738.

Series actuator end integrated positioning analysis based-on multilayer perceptron neural network

Hu Yanzhu, Li Leiyuan
(College of Automation, Beijing University of Posts and Telecommunications, Beijing, 100876, China)

Abstract:It is difficult to establish Jacobian matrix and determine the coordinate frames of links for non-standard actuator.A new analytical method to establish the Jacobian matrix and determine the coordinate frames for joints and links are proposed in this paper.The proposed method made the positioning analysis of end-effector easier in space.At the same time, it is necessary to prove the effectiveness of the proposed method theoretically and verify the localization and configuration capabilities through simulations.First of all, forward kinematics model was set up based on a non-standard five Degree Of Freedom(5-DOF)actuator.A frame transformation is performed from base coordinate to end-effector coordinate.The relation between two adjacent joints is defined by a homogenous pose matrix.Secondly, the necessary and sufficient conditions for comprehensive localization are derived.They can guide the actuator to perform various tasks, such as tracking, assembly and autonomous grasping.A 5-DOF actuator is considered here as an example and this holds good for any N-DOF.Thirdly, inverse kinematics solutions are obtained by using artificial Neural Network(NN)based on backpropagation Multi-Layer Perceptron(MLP, multilayer perceptron NN)and are not unique.A unique solution using nonlinear minimization optimization is found.A NN based on supervisory learning method including three inputs, twenty neurons and five outputs has been used.Excitation function tansigmoid and linear excitation function pureline are in hidden and outer layers respectively.In Cartesian coordinate space, NN is trained by means of Levenberg Marquardt(LM)algorithm.The training sets used are Denav Hartenberg(DH)parameters and Cartesian coordinates.The weights are updated continuously which reduces the Mean Square Error(MSE)gradually.When MSE reaches the threshold set up, NN training will be terminated.After training, the test sets are used to examine the capability of NN.Fourthly, there are two evaluation functions viz., localization and cost functions.The localization function is defined to evaluate the positioning property of end-effector.At the same time, in task space, it will check whether the actuator has reached the target point along the direction needed or not.The cost function is defined to evaluate the kinematics configuration.There is a great relevance between cost function and Jacobian matrix.Velocity mapping from each joint to the end-effector was described by Jacobian matrix.So the cost function could give expression for kinematic configuration.At the end, simulations and experiments are conducted.The settings include industrial computer UNO2184G, 5-DOF non-standard actuator, Windows 7, MATLAB2012a.Coordinate frames for each joint are established and D-H parameters are determined.Then relative pose matrix is obtained between each of the two adjacent joints.Initial end-effector pose is obtained following right multiplication rule.The end-effector space range is formed under each joint operation range.Then, simulation is performed using NN, obtained localization and cost functions.The following results are obtained.The rank of Jacobian matrix is equal to 5.Therefore, this actuator met necessary and sufficient conditions for comprehensive positioning.NN method for solving inverse kinematics has reduced the computational complexity compared to conventional method.There are 21 groups of solutions when positioning to(41.4, 89.0, 104.5).The optimal solution obtained is(21.61, 91.44, 135.52, 221.42, 0)according to localization function rule.The optimal solution obtained according to cost function rule is(21.61, 125.73, 108.42, 221.99.41, 0).NN accuracy is 89.9%(approximately)while conventional method is 87.5% .By approximate estimation, the errors for θ1,θ2,θ3,θ4and θ5are 3.7°, 3.1°, 3.5°, 3.3°and 4.5°respectively.NN used 1.2 seconds while conventional method completed in 0.9 seconds.Therefore, computation accuracy has improved by 20% and efficiency by 2.4%.If the system is linear, the conventional method is chosen when less demand in real-time.In contrast, if the system is nonlinear, new method proposed in this paper is chosen when more demand in real-time.The minimum value of localization function is 0.96.The maximum value of cost function is 4.0349×1014.These two parameters decide the comprehensive positioning and the kinematics configuration.From the results presented, it can be concluded that the non-standard actuator with MLP has better localization and optimal configuration.

Keywords:mechanization; control; models; manipulator; neural networks; inverse kinematics

作者简介:胡燕祝(1970-),教授,博士后,博士生导师,主要从事视觉测量与机器人方向。北京北京邮电大学自动化学院,100876。Email:YZH@263.net

基金项目:北京市计划课题《轨道交通事故现场应急处置装备研制与示范应用》(Z131100004513006)

收稿日期:2015-07-25

修订日期:2015-11-13

中图分类号:TP212

文献标志码:A

文章编号:1002-6819(2016)-01-0022-08

doi:10.11975/j.issn.1002-6819.2016.01.003

猜你喜欢

机械臂机械化控制
大棚有了机械化 一人管理也不怕
关于水稻一种两收机械化栽培技术要点探讨
机械臂平面运动控制与分析
机械臂工作空间全局相对可操作度图的构建方法
人机交互课程创新实验
社会转型期行政权控制的路径探索
会计预算控制现状及方法
浅谈高层建筑沉降监测关键环节控制
保险公司财务风险管理及控制研究
从骡马化到机械化、信息化