Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations. (English) Zbl 1355.70005
Summary: Singularities and uncertainties in arm configurations are the main problems in kinematics robot control resulting from applying robot model, a solution based on using Artificial Neural Network (ANN) is proposed here. The main idea of this approach is the use of an ANN to learn the robot system characteristics rather than having to specify an explicit robot system model.
Despite the fact that this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint for a six Degrees of Freedom (DOF) industrial robot. The network was designed to have one hidden layer, where the input were the Cartesian positions along the \(X, Y\) and \(Z\) coordinates, the orientation according to the \(RPY\) representation and the linear velocity of the end-effector while the output were the angular position and velocities for each joint, In a free-of-obstacles workspace, off-line smooth geometric paths in the joint space of the manipulator are obtained.
The resulting network was tested for a new set of data that has never been introduced to the network before these data were recorded in the singular configurations, in order to show the generality and efficiency of the proposed approach, and then testing results were verified experimentally.
Despite the fact that this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint for a six Degrees of Freedom (DOF) industrial robot. The network was designed to have one hidden layer, where the input were the Cartesian positions along the \(X, Y\) and \(Z\) coordinates, the orientation according to the \(RPY\) representation and the linear velocity of the end-effector while the output were the angular position and velocities for each joint, In a free-of-obstacles workspace, off-line smooth geometric paths in the joint space of the manipulator are obtained.
The resulting network was tested for a new set of data that has never been introduced to the network before these data were recorded in the singular configurations, in order to show the generality and efficiency of the proposed approach, and then testing results were verified experimentally.
Keywords:
neural networks; inverse kinematics; Jacobian matrix; singularities; back propagation; robot controlReferences:
| [1] | Tsai, L. W.: Robot analysis, the mechanics of serial and parallel manipulators, (1999) |
| [2] | Zurada, J. M.: Introduction to artificial neural systems, (1992) |
| [3] | Kuroe Y, Nakai Y, Mori T. A new neural network learning on inverse kinematics of robot manipulators. In: International conference on neural networks, IEEE world congress on computational intelligence, vol. 5; 1994. p. 2819 – 24. |
| [4] | Karilk, B.; Aydin, S.: An improved approach to the solution of inverse kinematics problems for robot manipulators, J eng appl artif int 13, 159-164 (2000) |
| [5] | Dahl, O.; Nielsen, L.: Torque-limited path following by on line trajectory time scaling, IEEE trans robot automat 6, 554-561 (1990) |
| [6] | Kirc´anski M, Kirc´anski N. Resolved-rate and resolved-acceleration based robot control in the presence of actuators constraints, In: Proceedings of the 1997 IEEE international conference on robotics and automation, Albuquerque, NM; 1997. p. 235 – 40. |
| [7] | Faiz N, Agrawal SK. Trajectory planning of robots with dynamics and inequalities. In: Proceedings of the IEEE international conference on robotics and automation, San Francisco, CA; 2000. p. 3977 – 83. |
| [8] | Antonelli, G.; Chiaverini, S.; Fusco, G.: A new on-line algorithm for inverse kinematics of robot manipulators ensuring path-tracking capability under joint limits, IEEE trans robot automat 19, No. 1, 162-167 (2003) |
| [9] | Cheah CC, Lee K, Kawamura S, Arimoto S. Asymptotic stability of robot control with approximate Jacobian matrix and its application to visual servoing. In: Proceedings of the 39th IEEE conference on decision and control, Sydney, Australia; 2000. p. 3939 – 44. |
| [10] | Whitney, E.: Resolved motion rate control of manipulators and human prostheses, IEEE trans man – Mach syst 10, 47-53 (1969) |
| [11] | Hu Z, FU Z, Fang H. Study of singularity robust inverse of Jacobian matrix for manipulator. In: Proceedings of the first international conference on machine learning and cybernetics, Beijing; 2002. p. 406 – 10. |
| [12] | Nakamura, Y.; Hanafusa, H.: Inverse kinematic solutions with singularity robustness for robot manipulator control, J dyn syst measure control 108, 163-171 (1986) · Zbl 0609.93044 · doi:10.1115/1.3143764 |
| [13] | Wampler, C. W.: Manipulator inverse kinematic solutions based on vector formulations and damped least-squares methods, IEEE trans syst, man, cybern 16, 93-101 (1986) · Zbl 0585.70030 · doi:10.1109/TSMC.1986.289285 |
| [14] | Balestrino A, De Maria G, Sciavicco L. Robust control of robotic manipulators. In: International proceedings of the 9th IFAC world congress, vol. 6, Budapest, Hungary; 1984. p. 80 – 5. |
| [15] | Wampler, C. W.; Leifer, L. J.: Applications of damped least-squares methods to resolved-rate and resolved-acceleration control of manipulators, J dyn syst measure control 110, 31-38 (1988) · Zbl 0649.93053 · doi:10.1115/1.3152644 |
| [16] | D’Souza A, Vijayakumar S, Schaal S. Learning inverse kinematics. In: Proceedings of the 2001 IEEE/RSJ international conference on intelligent robots and systems Maui, Hawaii, USA; 2001. p. 298 – 303. |
| [17] | Ogawa T, Matsuura H, Kanada H. A Solution of inverse kinematics of robot arm using network inversion. In: Proceedings of the 2005 international conference on computational intelligence for modelling, control and automation. |
| [18] | Köker, R.: Reliability-based approach to the inverse kinematics solution of robots using elman’s networks, J eng appl artif int 18, 685-693 (2005) |
| [19] | Hasan, A. T.; Hamouda, A. M. S.; Ismail, N.; Al-Assadi, H. M. A.A.: An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 D.O.F. Serial robot manipulator, J adv eng software 37, 432-438 (2006) |
| [20] | Al-Assadi, H. M. A.A.; Hamouda, A. M. S.; Ismail, N.; Aris, I.: An adaptive learning algorithm for controlling a two-degree-of-freedom serial ball-and-socket actuator, Proc I mech E part I J syst control eng 221, No. 7, 1001-1006 (2007) |
| [21] | Hagan, M. T.; Demuth, H. B.; Beale, M.: Neural network design, (1995) |
| [22] | Denavit, J.; Hertenberg, R. S. A.: Kinematics notation for lower pair mechanism based on matrices, Appl mech 77, 215-221 (1955) · Zbl 0064.15603 |
| [23] | Fu, K. S.; Gonzalez, R. C.; Lee, C. S. G.: Robotics control, vision, and intelligence, (1987) |
| [24] | Dulęba I, Sasiadek JZ. Modified Jacobian method of transversal passing through singularities of nonredundant manipulators. In: Proceedings of the American control conference Chicago, Illinois, June 2000. p. 2839 – 43. |
| [25] | Hasan, A. T.; Hamouda, A. M. S.; Ismail, N.; Al-Assadi, H. M. A.A.: A new adaptive learning algorithm for robot manipulator control, Proc I mech E, part I: J syst control eng 221, No. 4, 663-672 (2007) |
| [26] | Funahashi, K. I.: On the approximate realization of continuous mapping by neural networks, Neural networks 2, No. 3, 183-192 (1998) |
| [27] | Bingual Z, Ertunc HM, Oysu C. Comparison of inverse kinematics solutions using neural network for 6R robot manipulator with offset. In: 2005 ICSC congress on computational intelligence. |
| [28] | Köker, R.; Öz, C.; ç, T.; Akar; Ekiz, H.: A study of neural network based inverse kinematics solution for a three-joint robot, Robot autonom syst 49, 227-234 (2004) |
| [29] | Driscoll JA. Comparison of neural network architectures for the modeling of robot inverse kinematics. In: Proceedings of the IEEE, south aston; 2000. p. 44 – 51. |
| [30] | Hornik, K.: Approximation capabilities of multi-layer feed forward networks, IEEE trans neural network 4, No. 2, 251-257 (1991) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
