Robot manipülatörler için akıllı GTGS sistemi

Öz

Görsel servolama (GS) yaklaşımları içinde görüntü-tabanlı görsel servolama (GTGS) duruş kestirimi gerektirmediğinden robot manipülatörler için popüler GS yaklaşımlarından biridir. Bu popülerliğin yanında GTGS, uygulanması sırasında ise iki temel sorun ile uğraşır: Etkileşim matrisinin tersinin eldesi ve kontrolör için uygun bir sabit kazanç değeri bulunması. GTGS için etkileşim matrisi her ne kadar yalancı tersi ile beraber kullanılsa da tekilliklerin oluşması durumunda kontrol yasası işleyememektedir. Diğer bir taraftan sabit kazanç değeri yakınsama hızı ile sonlandırıcı hızları arasında bir ödünleşmeye sebep olmaktadır. Bu çalışmada bu sorunları çözmek için akıllı bir GTGS sistemi önerilmiştir. Sistemin ilk aşaması olarak eğitilmiş bir yapay sinir ağı (YSA) etkileşim matrisinin tersinin yerini almakta ve tekillik sorunu çözülmektedir. Ayrıca klasik hız kontrolcüsünün sebep olduğu başlangıç hız süreksizliği yararlanılan sürekli hız kontrolcü ile giderilmiştir.  İkinci aşama olarak sabit kazanç yerine bulanık kayan kipten esinlenen ve her çevrimde hata ve hata türevinin değerine göre kazanç hesabı yapan bir bulanık mantık birimi kullanılmıştır. Bu uyarlanabilir kazanç yaklaşımıyla yüksek hız ihtiyacı olmadan hızlı yakınsama sağlanmıştır.

Anahtar Kelimeler

• Görüntü-tabanlı görsel servolama,Robot manipülatör,Sinir ağı,Bulanık mantık

An intelligent IBVS system for robot manipulators

Abstract

Image-Based Visual Servoing (IBVS) is one of the popular approaches in visual servoing (VS) for robot manipulators by not requiring pose estimation. Besides this popularity, IBVS has to deal with two common problems in realization: obtaining the inverse of the interaction matrix and finding an appropriate fixed gain value for the controller. Although the interaction matrix for IBVS is used with pseudoinverse, the control law is not applicable in the case of singularities. On the other hand, fixed gain value causes a trade-off between convergence speed and end-effector velocities. In this study, an intelligent IBVS scheme is proposed to solve these problems. As the first stage of the system, the interaction matrix is replaced with a trained neural network and the singularity problem has been solved. Furthermore, the discontinuity of the initial velocities caused by the classical velocity controller are resolved by the used continuous velocity controller. As the second stage, instead of a fixed gain, a fuzzy logic unit inspired by fuzzy sliding mode and computing a gain value according to error and error derivative values in each loop is considered. Fast convergence without high velocity demand is provided by this adaptive gain approach.

Keywords

• Image-based visual servoing,Robot manipulator,Neural network,Fuzzy logic

References

1. Hutchinson S, Hager G, Corke P. "A Tutorial On Visual Servo Control". IEEE Transactions on Robotics and Automation, 12 (5), 651-670, 1996.
2. Hill J, Park WT. "Real Time Control Of A Robot With A Mobile Camera". Proceedings of the 9th ISIR, 233-246, 1979.
3. Chaumette F, Hutchinson S. "Visual Servo Control, Part I: Basic Approaches". IEEE Robotics and Automation Magazine, 13 (4), 82-90, 2006.
4. Malis E, Chaumette F, Boudet S. "2-1/2 D Visual Servoing". IEEE Transactions on Robotics and Automation, 15, 238-250, 1999.
5. Corke P, Hutchinson S. "A New Partitioned Approach To Image-Based Visual Servo Control". IEEE Transactions on Robotics and Automation, 17, 507–515, 2001.
6. Kallem V, Swensen JP, Hager GD, Cowan NJ. "Kernel-Based Visual Servoing". IEEE/RSJ International Conference of Intelligent Robotic Systems, 1975–1980, 2007.
7. Collewet C, Marchand E, Chaumette F. “Visual Servoing Set Free From Image Processing”. IEEE International Conference of Robotics and Automation, 81–86, 2008.
8. Chaumette F. Potential Problems Of Stability And Convergence In Image-Based And Position-Based Visual Servoing. Lecture Notes on Control Information Science, 66–78, Berlin, Springer-Verlag, 1998.

9. Kumar PP, Behera L. "Visual Servoing Of Redundant Manipulator With Jacobian Matrix Estimation Using Self-Organizing Map". Robotics and Autonomous Systems, 58, 978–990, 2010.
10. Kosmopoulos DI. "Robust Jacobian Matrix Estimation For Image-Based Visual Servoing", Robotics and Computer-Integrated Manufacturing, 27, 82-87, 2011.
11. Sebastián JM, Pari L, Angel L, Traslosheros A. "Uncalibrated Visual Servoing Using The Fundamental Matrix", Robotics and Autonomous Systems, 57, 1-10, 2009.
12. Zhong X, Zhong X, Peng X. "Robust Kalman Filtering Cooperated Elman Neural Network Learning For Vision-Sensing-Based Robotic Manipulation With Global Stability", Sensors, 13(10), 13464-13486, 2013.
13. Zhong X, Zhong X, Peng X. "Robots Visual Servo Control With Features Constraint Employing Kalman-Neural-Network Filtering Scheme", Neurocomputing, 151, 268–277, 2015.
14. Gonçalves PJS, Mendonça LF, Sousa JMC, Pinto JRC, "Uncalibrated Eye-to-Hand Visual Servoing Using Inverse Fuzzy Models", IEEE Transactions on Fuzzy Systems, 16 (2), 341-353, 2008.
15. Mansard N, Chaumette F. "Task Sequencing For High-Level Sensor-Based Control", IEEE Transactions On Robotics, 23 (1), 60-72, 2007.
16. Kermorgant O, Chaumette F. "Dealing With Constraints In Sensor-Based Robot Control", IEEE Transactions on Robotics, 30, 244–257, 2014.
17. Slotine JJ, Weiping L., Applied Nonlinear Control, Upper Saddle River, Prentice Hall, 1991.
18. Kaynak O, Erbatur K, Ertuğrul M. "The Fusion Of Computationally Intelligent Methodologies And Sliding-Mode Control-A Survey". IEEE Transactions on Industrial Electronics, 48 (1), 4-17, 2001.
19. Tahri O, Chaumette F. “Point-Based And Region-Based Image Moments For Visual Servoing Of Planar Objects”, IEEE Transactions on Robotics, 21, 1116–1127, 2005.
20. Haykin S., Neural Networks: A Comprehensive Foundation, Upper Saddle River, Prentice-Hall,1998.
21. Jang SR, Sun CT., Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Upper Saddle River, Prentice-Hall, 1997.
22. Chesi G, Hung YS. "Global Path-Planning For Constrained And Optimal Visual Servoing", IEEE Transactions on Robotics, 23, 1050–1060, 2007.
23. Colley SJ., Vector Calculus, Upper Saddle River, Pearson, 2012.
24. Aström KJ, Hagglund T., Advanced PID Control, Research Triangle Park, ISA Publishing, 2006.
25. Corke P., Robotics, Vision & Control, Berlin, Springer, 2011.