计算机科学 ›› 2025, Vol. 52 ›› Issue (5): 270-280.doi: 10.11896/jsjkx.240400173
汪黎明, 仲国民, 孙明轩, 何熊熊
WANG Liming, ZHONG Guomin, SUN Mingxuan, HE Xiongxiong
摘要： 针对等式约束的时变二次规划求解问题,提出一种有限值终态零化神经网络,以保证计算误差的有限时间收敛,其有限值特性易于实现;对有限值终态零化神经网络进行理论分析,并给出该神经网络的收敛时间表达式。冗余机械臂的重复运动规划问题可描述为时变二次规划问题,采用有限值终态零化神经网络作为求解器,以获取末端执行器轨迹对应的关节轨迹。考虑到机械臂关节初始偏差难以避免,采用定参数/自适应参数的终态优化指标,在实现机械臂末端位置误差的有限时间收敛的同时,提高重复运动规划的精度。为保证机械臂的平稳运行,提出一种平滑修正的有限值函数用于终态优化指标设计。理论分析机械臂末端执行器位置误差的有限时间收敛条件。数值仿真以及UR5机械臂仿真与实验结果,验证了所提计算方案的有效性。
中图分类号:
| [1]ZHANG Y N,JIANG D C,WANG J.A recurrent neural net-work for solving Sylvester equation with time-varying coefficients[J].IEEE Transactions on Neural Networks,2002,13(5):1053-1063. [2]JOHANSEN T A,FOSSEN T I,BERGE S P,Constrained nonlinear control allocation with singularity avoidance using sequential quadratic programming[J].IEEE Transactions on Control Systems Technology,2004,12(1):211-216. [3]LEITHEAD W E,ZHANG Y.O(n2)-operation approximationof covariance matrix inverse in gaussian process regression based on quasi-newton BFGS method[J].Communications in Statistics Simulation and Computation,2007,524:216-228. [4]ZHANG Y N,GE S S.A general recurrent neural network mo-del for time-varying matrix inversion[C]//Proceedings of the 42nd IEEE Conference on Decision and Control Maui.Hawaii USA,2003:6169-6174. [5]XIAO X C,JIANG C Z,LU H Y,et al.A parallel computing method based on zeroing neural networks for time-varying complex-valued matrix Moore-Penrose inversion [J].Information Sciences,2020,36(2):367-380. [6]XIAO L,ZHANG Y N,HU Z S,et al.Performance benefits of robust nonlinear zeroing neural network for finding accurate solution of Lyapunov equation in presence of various noises [J].IEEE Transactions on Industrial Informatics,2019,15(9):5161-5171. [7]ZHANG Z J,LU Y Y,ZHENG Y Y,et al.A new varying-parameter convergent-differential neural-network for solving time-varying convex QP problem constrained by linear-equality[J].IEEE Transactions on Automatic Control,2018,63(12):4110-4125. [8]ZHANG Y N,GE S S.Design and analysis of a general recurrent neural network model for time-varying matrix inversion[J].IEEE Transactions on Neural Networks,2005,13(5):1053-1063. [9]LI S,CHEN S F,LIU B.Accelerating a recurrent neural net-work to finite-time convergence for Solving time-varying Sylvester equation by using a Sign-Bi-power activation function[J].Neural Processing Letters,2013,37(2):189-205. [10]GUO D S,ZHANG Y N.Li-function activated ZNN with finite-time convergence applied to redundant-manipulator kinematic control via time-varying Jacobian matrix pseudoinversion[J].Applied Soft Computing,2014,24:158-168. [11]LU H Y,JIN L,LUO X,et al.RNN for solving perturbed time-varying underdetermined linear system with double bound limits on residual errors and state variables[J].IEEE Transactions on Industrial Informatics,2019,15(11):5931-5942. [12]JIN L,LIU F Y,LU H Y,et al.Saturation-allowed neural dynamics applied to perturbed time-dependent system of linear equations and robots[J].IEEE Transactions on Industrial Electronics,2021,68(10):9844-4854. [13]SHAMIR T,YOMDIN Y.Repeatability of redundant manipulators:mathematical solution of the problem[J].IEEE Transactions on Automatic Control,1988,33(11):1001-1009. [14]ZHANG Y N,TAN Z G,CHEN K,et al.Repetitive motion of redundant robots planned by three kinds of recurrent neural networks and illustrated with a four-link planar manipulator's straight-line example[J].Robotics and Autonomous Systems,2009,57(6/7):645-651. [15]ZHANG Y N,ZHANG Z J.Design and experimentation of acceleration-level drift-free scheme aided by two recurrent neural networks[J].IET Control Theory & Applications,2013,7(1):25-42. [16]KLEIN C A,HUANG C H.Review of pseudoinverse control for use with kinematically redundant manipulators[J]. IEEE Transactions on Systems,Man,and Cybernetics,1983,SMC-13(3):245-250. [17]KRZYSZTOF T,ADAM R,IDA G.Lagrangian Jacobian inverse for nonholonomic robotic systems[J].Nonlinear Dynamics,2015,82(4):1923-1932. [18]LIAO B L,LIU W.Pseudoinverse-Type Bi-Criteria Minimization Scheme for Redundancy Resolution of Robot Manipulators[J].Robotica,2015,33(10):2100-2113. [19]ZHANG P C,REN X H,ZHANG Z J.An efficient self-motion scheme for redundant robot manipulators:a varying-gain neural self-motion approach[J].Robotica,2021,39(10):1897-1908. [20]DANIEL E W.Resolved motion rate control of manipulators and human prostheses[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,1969,MMS-10(2):47-53. [21]CHENG F T,CHEN T H,SUN Y Y.Resolving manipulator redundancy under inequality constraints[J].IEEE Journal on Robotics and Automation,1994,10(1):65-71. [22]TAROKH M,ZHANG X M.Real-time motion tracking of robot manipulators using adaptive genetic algorithms[J].Journal of Intelligent & Robotic Systems,2014,74(3):697-708. [23]LIU F,HUANG H L,LI B.A parallel learning particle swarmoptimizer for inverse kinematics of robotic manipulator[J].International Journal of Intelligent Systems,2021,36(10):6101-6132. [24]LI S,ZHANG Y N,JIN L.Kinematic control of redundant manipulators using neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2243-2254. [25]ZHANG Y N,WANG J,XIA Y S.A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits[J].IEEE Transactions on Neural Networks,2003,14(3):658-667. [26]XIAO L,ZHANG Y S,DAI J H,et al.A new noise-tolerant and predefined-time ZNN model for time-dependent matrix inversion[J].Neural Networks,2019,117(1):124-134. [27]HU Z S,XIAO L,DAI J J,et al.A unified predefined-time con-vergent and robust ZNN model for constrained quadratic programming[J].IEEE Transactions on Industrial Informatics,2021,17(3):1998-2010. [28]SUN M X,ZHANG Y,WU Y X,et al.On a finitely activated terminal RNN approach to time-variant problem solving[J].IEEE Transactions on Neural Networks and Learning Systems,2022,33(12):7289-7302. |
|
||
首页