The Implementation of An Inverse Kinematics Solution of A 3-joint Robotic Manipulator Using Neural Network and Genetic Algorithm

Raşit KÖKER, Tarik ÇAKAR


The inverse kinematics problem of a 3-joint robotic manipulator has been implemented by using neuro-genetic technique in this paper. Firstly, a neural network has been designed for the inverse kinematics solution of 3-joint robotic manipulator. Then, to minimize the error at the end effector a genetic algorithm has been applied to the neural based solution method. The genetic algorithm has been used after the implementation of the neural network to improve the obtained results. The genetic algorithm has been following the neural network based solution to improve. The error at the end effector has been significantly reduced.


Robotics, neural networks, genetic algorithms, inverse kinematics solution, machine learning.

Full Text:



Craig J.J. Introduction to Robotics: Mechanics and Control. (3rd Edition), Prentice-Hall; 2004.

Denavit J., R. Hartenberg. A kinematic notation for lower-pair mechanisms based on matrices. ASME Journal of Applied Mechanics 1955; 215–221.

Gravagne I.A., Walker I.D., Manipulability, force, and compliance analysis for planar continuum manipulators. Robotics and Automation 18 2002; 3: 263–273.

Horacio M.A., Simon G.G. Mobile robot path planning and tracking using simulated annealing and fuzzy logic control. Expert System Apply 1998; 15: 421–429.

Khoogar A.R., Parker J.K. Obstacle avoidance of redundant manipulators using genetic algorithms. IEEE Proceedings of Southeastcon’91, 07–10 April 1991, Williamsburg, Virginia, 1991; Vol. 1: pp. 317–320.

Köker R., A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization. Information Sciences, 10 February 2013, Volume 222:528- 543.

KökerR.,ÖzC.,ÇakarT.,EkizH. A study of neural network based inverse kinematics solution of a three- joint robot. Robotics and Autonomous Systems 2004; Vol. 49: pp. 227-234.

Mao Z., Hsia T.C., Obstacle avoidance inverse kinematics solution of redundant robots by neural networks. Robotica 1997; 15 (1): 3–10.

Marcos M.G., Machado J.A.T., Perdicoulis T.P.A., An evolutionary approach for the motion planning of redundant and hyper-redundant manipulator. Nonlinear Dynamics 2010; 60: 115–119.

Nearchou A.C. Solving the inverse kinematics problem of redundant robots operating in complex environments via a modified genetic algorithm. Mechanism and Machine Theory (3) 1998; 33:273–292.

Perez A., McCarthy J.M. Clifford Algebra exponentials and planar linkage synthesis equations. Journal of Mechanical Design 2005; 127: 931– 940.

Sardana L. ,Sutar M.K. , Pathak P.M. A geometric approach for inverse kinematics of a 4-link redundant In- Vivo robot for biopsy. Robotics and Autonomous Systems 2013; 61: 1306– 1313.

Wang J., Li Y., Zhao X. Inverse kinematics control of a 7-DOF redundant manipulator based on the closed-loop algorithm. Advanced Robotic Systems 2010; 7 (4):1–10.

Yahya S., Moghavvemi M., Mohamed H.A.F. Geometrical approach of planar hyper-redundant manipulators: inverse kinematics, path planning and workspace. Simulation Modelling Practice and Theory 2011; 19:406–

Martin J.A., Lope J.D. A method to

learn the inverse kinematics of 422.

multi-link robots by evolving neuro-controllers. Neurocomputing. Vol. 72 (13-15): 2806-2814.

McCarthy J.M. Introduction to Theoretical Kinematics. Cambridge MA: MIT Press; 1990.

Youshen X., Wang J. A dual neural network for kinematic control of redundant robot manipulators. IEEE Transactions on Systems, Man and Cybernetics 2001; 31 (1):147–154.