An Unsupervised Neural Network Approach for Inverse Kinematics Solution of Manipulator following Kalman Filter based Trajectory

A novel unsupervised approach for inverse kinematics solution of a manipulator using artificial neural network is presented. Forward kinematics equations determine the motion of manipulator's arm and have a unique solution. But there is not a unique solution for inverse kinematics as manipulator may have more than one configurations to reach a particular point. Here in this paper, we have taken a PUMA 560 robot with six degrees of freedom with aim to grab an object moving in circular path in XY plane with a known constant height and kalman filter has been used to determine accurate position of that object. Contrary to supervised learning approach, which needs a huge amount of data to train the system, we have used a real time unsupervised approach to solve inverse kinematics problem which is more efficient. Joint angles of the robot are determined in real time using unsupervised feed forward neural network with backpropagation training algorithm.

[1]  Chunguang Xu,et al.  Inverse Kinematic Analysis and Evaluation of a Robot for Nondestructive Testing Application , 2015, J. Robotics.

[2]  Ishak Aris,et al.  Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations , 2010, Adv. Eng. Softw..

[3]  Craig Corcoran,et al.  A measurement model for tracking hand-object state during dexterous manipulation , 2010, 2010 IEEE International Conference on Robotics and Automation.

[4]  N. Sukavanam,et al.  An unsupervised learning based neural network approach for a robotic manipulator , 2017 .

[5]  Guanglong Du,et al.  A Markerless Human–Robot Interface Using Particle Filter and Kalman Filter for Dual Robots , 2015, IEEE Transactions on Industrial Electronics.

[6]  Santosh Kumar Nanda,et al.  A Novel Application of Artificial Neural Network for the Solution of Inverse Kinematics Controls of Robotic Manipulators , 2012 .

[7]  Kush Aggarwal,et al.  Use of Artificial Neural Networks for the Development of an Inverse Kinematic Solution and Visual Identification of Singularity Zone(s) , 2014 .

[8]  Guanglei Wu,et al.  Kinematics and Dynamics of an Asymmetrical Parallel Robotic Wrist , 2014, J. Robotics.

[9]  Joel W. Burdick,et al.  Combined shape, appearance and silhouette for simultaneous manipulator and object tracking , 2012, 2012 IEEE International Conference on Robotics and Automation.

[10]  Rasit Köker,et al.  A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization , 2013, Inf. Sci..

[11]  Tien C. Hsia,et al.  Obstacle avoidance inverse kinematics solution of redundant robots by neural networks , 1997, Robotica.

[12]  Grzegorz Karpiel,et al.  Kinematics Analysis of a Novel Five-Degree-of-Freedom Spatial Parallel Micromanipulator , 2014, J. Robotics.

[13]  Mohammad Farrokhi,et al.  Real-time inverse kinematics of redundant manipulators using neural networks and quadratic programming: A Lyapunov-based approach , 2014, Robotics Auton. Syst..

[14]  Yongdong Li,et al.  Formal Kinematic Analysis of a General 6R Manipulator Using the Screw Theory , 2015 .

[15]  Yu Liu,et al.  Geometric Parameter Identification of a 6-DOF Space Robot Using a Laser-Ranger , 2012, J. Robotics.

[16]  Ying Shang,et al.  A Geometric Approach for Robotic Arm Kinematics with Hardware Design, Electrical Design, and Implementation , 2010, J. Robotics.

[17]  Ping Zhang,et al.  IMU-Based Online Kinematic Calibration of Robot Manipulator , 2013, TheScientificWorldJournal.