Exploring cognitive approach through the neural network paradigm: "trajectory planning application"

In recent years, artificial neural networks have received a great deal of attention for their ability to perform nonlinear mappings. In trajectory control of robotic devices, neural networks provide a fast method of autonomously learning the relation between a set of output states and a set of input states. In this paper, we will apply the cognitive approach to solve the problems related to the position controller using the inverse geometrical model. In order to control a robot manipulator to accomplish a task, trajectory planning is required in advance or in real time. The desired trajectory is usually described in Cartesian coordinates and needs to be converted to joint space for the purpose of analyzing and controlling the system behavior. In this paper, we use the memory neural network MNN to solve the optimization problem concerning the inverse of the direct geometrical model of the redundant manipulator subject to some constraints. Our approach offers substantially better accuracy, avoids the computation of the inverse or pseudoinverse Jacobian matrix and do not produce problems such as singularity, redundancy, and considerably increased computational complexity, etc.

[1]  Amar Ramdane-Cherif,et al.  Optimization schemes for learning the forward and inverse kinematic equations with neural network , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[2]  Vassilios Morellas,et al.  Neural network learning of the inverse kinematic relationships for a robot arm , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[3]  Manja V. Kiréanski,et al.  Combined Analytical- Pseudoinverse Inverse Kinematic Solution for Simple Redundant Manipulators and Singularity Avoidance , 1993, Int. J. Robotics Res..

[4]  Amar Ramdane-Cherif,et al.  Penalty approach for a constrained optimization to solve on-line the inverse kinematic problem of redundant manipulators , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[5]  M. Drouin,et al.  Acceleration of back-propagation for learning the forward and inverse kinematic equations , 1995, The Second International Symposium on Neuroinformatics and Neurocomputers.

[6]  P. S. Sastry,et al.  Memory neuron networks for identification and control of dynamical systems , 1994, IEEE Trans. Neural Networks.

[7]  K. H. Hunt.  Robot Kinematics—A Compact Analytic Inverse Solution for Velocities , 1987 .

[8]  Yasmina Bestaoui,et al.  An unconstrained optimization approach to the resolution of the inverse kinematic problem of redundant and nonredundant robot manipulators , 1991, Robotics Auton. Syst..

[9]  A. Guez,et al.  Accelerated convergence in the inverse kinematics via multilayer feedforward networks , 1989, International 1989 Joint Conference on Neural Networks.

[10]  Véronique Perdereau,et al.  Real-time control of redundant robotic manipulators for mobile obstacle avoidance , 2002, Robotics Auton. Syst..

[11]  Roy Featherstone,et al.  Accurate trajectory transformations for redundant and nonredundant robots , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[12]  John Baillieul,et al.  Kinematic programming alternatives for redundant manipulators , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.