JIN Hu,CHEN Chao,CHEN Nian-wei.Optimal Inverse Kinematics Solution using Recurrent Neuron-Networks[J].Journal of Chengdu University of Information Technology,2016,(06):575-582.
回复式神经网络优化逆运动问题求解
- Title:
- Optimal Inverse Kinematics Solution using Recurrent Neuron-Networks
- 文章编号:
- 2096-1618(2016)06-0575-08
- Keywords:
- computational intelligence; Inverse Kinematics system; recurrent neural networks; trajectory planning; asynchronous calculation
- 分类号:
- TP183
- 文献标志码:
- A
- 摘要:
- 针对传统逆运动问题数值求解算法计算时间长,多解情况下计算结果单调的问题,采用回复式神经网络对逆运 动问题进行近似优化求解。通过针对逆运动问题建立基于回复式神经网络的动态求解模型,采用神经元异步更新计 算和初始状态扰动,保证多解情况下解运动迹线的多样性。文中算法在无解情况下有较好适应性和稳定性,能迅速 收敛到近似最优状态。算法理论计算时间复杂度为O(n2),可满足实时应用的需求。实 验对典型对子运动链运动系统进行模拟,结果表明算法具有稳定和收敛性。
- Abstract:
- The conventional Inverse Kinematics problem solving methods have many disadvantages such as slowly convergence speed or monotonous computation result. This issue presents a novel algorithm with recurrent neuron-networks model to treat the Inverse Kinematics problem as approximate optimization solving. This method designs proper optimization function for Inverse Kinematics system and utilizes recurrent neuron-networks computational model to resolve. During the computation, the neurons were updated asynchronously and the initial system state was disturbed to obtain diverse trajectories when multi-solutions exist. The algorithm has good stability and convergence ability even when no solution exists. The theoretical computation time complexity of the algorithm is O(n2), and can meet general real-time application requirements. Experiments were done to simulate the dyad kinematics system. The calculation results show that the computational time are increase with the neuron number but not exponentially, that are in good agreement with the algorithm convergence stability.
参考文献/References:
[1] Richard P Paul.Robot manipulators: mathematics, programming, and control: the computer control
of robot manipulators[M].Massachusetts.MIT Press,Cambridge,1981:65-85.
[2] Richard M Murray.Mathematical introduction to Robotic manipulation [M].CRC Press,1994:81-
146.
[3] Rick Parent.Computer Animation: Algorithms and Techniques[M].MORGAN KAUFMANN
Publishers,2002:175-216.
[4] AJ Turner,JF Miller.Recurrent Cartesian Genetic Programming Applied to Series Forecasting
[M].Springer International Publishing,2014:476-486.
[5] Oleg Ivlev, Axel Gräser. An Analytical Method for the Inverse Kinematics of Redundant
Robots[C].in Proc.3rd ECPD Int. Conf. on Advanced Robots,Intelligent Automation and Active Systems
1997:416-421.
[6] Deepak Tolani, Ambarish Goswami, Norma I Badler.Real-time inverse kinematics techniques
for anthropomorphic limbs[J].Graphical Models 2000,62:353-388.
[7] L Zhang,G Brunnett.Combining inverse blending and Jacobian-based inverse kinematics to
improve accuracy in human motion generation[J].Computer Animation and Virtual Worlds, 2016, 27
(1):3-13.
[8] I-Ming Chen, Guilin Yang.Inverse Kinematics for Modular Reconfigurable Robots
[C].Proceedings of the 1998 IEEE International Conference on Robotics and Automation, Leuven,
Belgium, May, 1998:1647-1652.
[9] N I Badler,D Tolani.Real-Time Inverse Kinematics of the Human Arm[J].Presence, 1996,5
(4):393-401.
[10] Gaurav Tevatia,Stefan Schaal.Inverse Kinematics for Humanoid Robots[C].In Proceedings of
the International Conference on Robotics and Automation(ICRA2000), 2000:294-299.
[11] KRZYSZTOF TCHON, JOANNA KARPINSKA, MARIUSZ JANIAK.Approximation of Jacobian Inverse
Kinematics Algorithms[J].Int.J.Appl.Math.Comput.Sci.,2009,19(4):519-531.
[12] Radek Grzeszczuk.NeuroAnimator: Fast Neural Network Emulation and Control of Physics-
Based Models[C].thesis for degree of Doctor of Philosophy, 1998:26-43.
[13] H J Tang,K C Tan,Zhang Yi.Neural Networks: Computational Models and Applications
[M].Springer-Verlag,2007:57-79.
[14] Dan B. Marghitu, Mechanisms and Robots Analysis with MATLAB[M].New York:Springer
Dordrecht Heidelberg London,2009:1-10.
[15] Samuel R Buss. Introduction to Inverse Kinematics with Jacobian Transpose, Pseudoinverse
and Damped Least Squares methods, ucsd.edu/sbuss/ResearchWeb,2004:1-19.
[16] P TSENG.Convergence of a Block Coordinate Descent Method for Non-differentiable
Minimization[J].Journal of Optimization Theory and Applications,2001,109(3):475-494.
[17] Mustafa,Z Mustafa,K Etinkaya.Comparison of four different heuristic optimization
algorithms for the inverse kinematics solution of a real 4-DOF serial robot manipulator[J].Neural
Computing and Applications archive,2016,27(4):825-836.
[18] Eimei Oyama, Arvin Agah.A modular neural network architecture for inverse kinematics
model learning[J], Neuro-computing,2001,38(40):797-805.
[19] M Z Al-Faiz, MIEEE. Inverse Kinematics Solution for Robot Manipulator Based on Neural
Network[J].MASAUM Journal of Basic and Applied Sciences,2009,(2):147-154.
备注/Memo
收稿日期:2016-10-20 基金项目:四川省科技厅科技支撑计划资助项目(2013GZX0169)