RRR Robotik Kol için Çok Katmanlı Algılayıcı ve Ters Kinematik Karşılaştırması

Year 2024, , 121 - 131, 29.02.2024

Faruk Emre Aysal , İbrahim Çelik , Enes Cengiz , Yüksel Oğuz

https://doi.org/10.2339/politeknik.1092642

Cited By: 2

Abstract

Bu çalışmada 3 DOF bir robot kolunun pozisyon kontrol simülasyonu makine öğrenmesi ve ters kinematik analiz ile ayrı ayrı yapılarak karşılaştırılmıştır. Ele alınan robot kol, RRR düzeninde tasarlanmıştır. Robot kolun ters kinematik analizinde geometrik yaklaşım ve analitik yaklaşım birlikte kullanılmıştır. Makine öğrenmesi yöntemi olarak Multi-Layer Perceptron(MLP) kullanılmıştır. Robot kolun çalışma uzayında ulaşabileceği koordinat verilerinin bir kısmı seçilerek, bu verilerle MLP modeli eğitilmiştir. MLP makine öğrenmesi yöntemiyle eğitim yapıldığında korelasyon katsayısı(R2) 1 olarak elde edilmiştir. Çalışma uzayı içerisinde yer alabilecek olan 3 farklı geometrik modelin (helix, star ve daisy) koordinatları MLP modelinin test verisi olarak kullanılmıştır. Bu testler MATLAB ortamında 3d olarak simule edilmiştir. Simülasyon sonuçları test kinematik analiz verileri ile karşılaştırılmıştır. Sonuç olarak gerçekleştirilen testlerde helix, star ve daisy şekilleri için Mean Relative Error (MRE) değerleri sırasıyla 0.0007, 0.0033 ve 0.0011 olarak hesaplanmıştır. Mean Squared Error (MSE) değerleri ise sırasıyla 0.0034, 0.0065 ve 0.0040 olarak elde edilmiştir. Bu da önerilen MLP modelinin bu sistemi istenilen kararlılıkta çalıştırabileceğini doğrulamaktadır.

Keywords

ters kinematik, çok katmanlı algılayıcı, robot kolu

Supporting Institution

AFYON KOCATEPE ÜNİVERSİTESİ-BİLİMSEL ARAŞTIRMA PROJELERİ KOMİSYONU

Project Number

21.KARİYER.03

Thanks

Bu çalışma "AFYON KOCATEPE ÜNİVERSİTESİ-BİLİMSEL ARAŞTIRMA PROJELERİ KOMİSYONU" tarafından 21.KARİYER.03 nolu proje ile desteklenmiştir.

A Comparison of Multi-Layer Perceptron and Inverse Kinematic for RRR Robotic Arm

Abstract

In this study, the position control simulation of a 3 Degree of Freedom (3DOF) robot arm was compared with machine learning and inverse kinematic analysis separately. The considered robot arm is designed in RRR pattern. In the inverse kinematic analysis of the robot arm, the geometric approach and the analytical approach are used together. Multi-Layer Perceptron (MLP) was used as a machine learning method. Some of the coordinate data that the robot arm can reach in the working space are selected and the MLP model is trained with these data. When training was done with MLP machine learning method, the correlation coefficient (R2) was obtained as 1. Coordinates of 3 different geometric models (helix, star and daisy) that can be included in the working space are used as test data of the MLP model. These tests are simulated in 3D in MATLAB environment. The simulation results were compared with the inverse kinematics analysis data. As a result, Mean Relative Error (MRE) values for helix, star and daisy shapes were calculated as 0.0007, 0.0033 and 0.0011, respectively, in the tests performed. Mean Squared Error (MSE) values were obtained as 0.0034, 0.0065 and 0.0040, respectively. This confirms that the proposed MLP model can operate this system at the desired stability.

Keywords

inverse kinematic, MLP, Robot arm

Project Number

21.KARİYER.03

References

• [1] Wu W and Rao SS. “Uncertainty analysis and allocation of joint tolerances in robot manipulators based on interval analysis”, Reliab. Eng Syst Safety, 92 (1):54–64, (2007).
• [2] Hasan AT, Hamouda AMS, Ismail N, and Al-Assadi HMAA. “An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 D.O.F. serial robot manipulator”, Sciencedirect Adv Eng Software, 37(7):432–438, (2006).
• [3] Caccavale F, Natale C, Siciliano B, and Villani L. “Integration for the next generation: embedding force control into industrial robots”, IEEE Robot Autom Mag;12(3):53–64, (2006).
• [4] Gautam R., Gedam A., Zade A., and Mahawadiwar A., “Review on development of industrial robotic arm,” International Research Journal of Engineering and Technology (IRJET), 4(3): 1752-1755 (2017).
• [5] Becerra Y., Arbulu M., Soto S., and Martinez F., “A comparison among the Denavit-Hartenberg, the screw theory, and the iterative methods to solve inverse kinematics for assistant robot arm,” In International Conference on Swarm Intelligence, Springer, Cham, 447-457, (2019).
• [6] Patil A., Kulkarni M., and Aswale A., “Analysis of the inverse kinematics for 5 DOF robot arm using DH parameters,” In 2017 IEEE International Conference on Real-time Computing and Robotics (RCAR), 688-693 (2017).
• [7] Lopez-Franco C., Hernandez-Barragan J., AlaniA. Y. s, and Arana-Daniel N., “A soft computing approach for inverse kinematics of robot manipulators,” Engineering Applications of Artificial Intelligence, 74: 104-120, (2018).
• [8] Mahanta G. B., Deepak B. B. V. L., Dileep M., B. Biswal B., and Pattanayak S. K., “Prediction of inverse kinematics for a 6-DOF industrial robot arm using soft computing techniques,” In Soft computing for problem solving, Singapore, 519-530, (2019).
• [9] Myint K. M., Htun Z. M. M., and Tun H. M., “Position control method for pick and place robot arm for object sorting system,” International journal of scientific & technology research, 5(6): 57-61, (2016).
• [10] Han S. D., Feng S. W., and Yu J., “Toward Fast and Optimal Robotic Pick-and-Place on a Moving Conveyor,” IEEE Robotics and Automation Letters, 5(2): 446-453, (2019).
• [11] Nu'man H. S., Sofyan Y., and, Al Tahtawi A. R, “Pengendalian Robot Lengan Pemilah Benda Berdasarkan Bentuk Menggunakan Teknologi Computer Vision”, Seminar Nasional Teknologi dan Riset Terapan, 2: 42-48 (2020).
• [12] Zulfardi N. F., Saputra D. I., Ahkam A. D. A., “Aplikasi Deteksi Benda Menggunakan Metode Image Substraction Sebagai Masukan Koordinat Pada Robot Lengan 3 DOF,” Seminar Nasional Teknologi dan Riset Terapan, 1: 30-37 (2019).
• [13] Ishak I., Fisher J., and Larochelle P., “Robot arm platform for rapid prototyping: Concept,” Conference on Recent Advances in Robotics, Florida, (2015).
• [14] Tolani, D., Goswami, A., and Badler, N. I. “Real-time inverse kinematics techniques for anthropomorphic limbs”. Graphical Models, 62(5), 353-388, (2000).
• [15] Kim H. S. and Song J. B., “Low-cost robot arm with 3-DOF counterbalance mechanism,” IEEE International Conference on Robotics and Automation, 4183-4188, (2013).
• [16] Kato G., Onchi D. and Abarca M., “Low-cost flexible robot manipulator for pick and place tasks,” 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Jeju, 677-680, (2013).
• [17] Andrews N., Jacob S., Thomas S. Sukumar M., S. and Cherian R. K., “Low-Cost Robotic Arm for differently abled using Voice Recognition,” 3rd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 735-739, (2019).
• [18] Wu Y., Wang M. and Mayer N. M., “A new type of eye-on-hand robotic arm system based on a low-cost recognition system,” International Conference on Advanced Robotics and Intelligent Systems (ARIS), Taipei, 110-114 (2017).
• [19] Šuligoj F, Jerbić B., Švaco M., Šekoranja B., Mihalinec D and Vidaković J., “Medical applicability of a low-cost industrial robot arm guided with an optical tracking system,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, 3785-3790 (2015).
• [20] Kroeger O., Wollschläger F. and Krüger J., “Low-Cost Embedded Vision for Industrial Robots: A Modular End-of-Arm Concept,” 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 1301-1304, (2020)
• [21] Luu T. H. and Tran T. H., “3D vision for mobile robot manipulator on detecting and tracking target,” 15th International Conference on Control, Automation and Systems (ICCAS), Busan, 1560-1565, (2015).
• [22] Sarker P. P., Abedin F., and Shimim F. N., “R3Arm: Gesture controlled robotic arm for remote rescue operation,” IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, 428-431, (2017).
• [23] Mardiyanto R., Utomo M. F. R., Purwanto D. and Suryoatmojo H., “Development of hand gesture recognition sensor based on accelerometer and gyroscope for controlling arm of underwater remotely operated robot,” International Seminar on Intelligent Technology and Its Applications (ISITIA), Surabaya, 329-333, (2017).
• [24] Aggarwal L., Gaur V. and Verma P., “Design and implementation of a wireless gesture controlled robotic arm with vision,” International Journal of Computer Applications, 79(13): 39-43, (2013).
• [25] Khajone S. A., Mohod S. W. and Harne V. M., “Implementation of a wireless gesture controlled robotic arm,” International Journal of innovative research in computer and communication engineering, 3(1), 375-379, (2015).
• [26] Kadir W. M. H. W., Samin R. E., and Ibrahim B. S. K., “Internet controlled robotic arm,” Procedia Engineering, 41:1065-1071, (2012).
• [27] Atmoko R. A., and Yang D., “Online Monitoring & Controlling Industrial Arm Robot Using MQTT Protocol,” IEEE International Conference on Robotics, Biomimetics, and Intelligent Computational Systems (Robionetics), Bandung, Indonesia, 12-16 (2018).
• [28] Siagian P., and Shinoda K., “Web based monitoring and control of robotic arm using Raspberry Pi,” International Conference on Science in Information Technology (ICSITech), Yogyakarta, 192-196 (2015).
• [29] Zhang G., He Y., Dai B., Gu F., Han J. and Liu G., “Robust Control of an Aerial Manipulator Based on a Variable Inertia Parameters Model,” IEEE Transactions on Industrial Electronics, 67(11): 9515-9525, (2020).
• [30] Karlik B., and Aydin S., “An improved approach to the solution of inverse kinematics problems for robot manipulators”, Eng. Appl. Artif. Intell. 13 (2) :159–164, (2000).
• [31] Chiddarwar S.S., and Ramesh Babu N., “Comparison of RBF and MLP neural networks to solve inverse kinematic problem for 6R serial robot by a fusion approach”, Eng. Appl. Artif. Intell. 23 (7): 1083–1092, (2010).
• [32] Köker R., “A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization”, Information Sciences. 222: 528–543, (2013).
• [33] Duka A.-V., “Neural network based inverse kinematics solution for trajectory tracking of a robotic arm”, Procedia Technology, 12: 20–27, (2014).
• [34] Csiszar A., Eilers J., and Verl A., “On solving the inverse kinematics problem using neural networks”, 24th International Conference on Mechatronics and Machine Vision in Practice, IEEE, 1–6 (2017).
• [35] Toshani H., and Farrokhi M., “Real-time inverse kinematics of redundant manipulators using neural networks and quadratic programming: A Lyapunov-based approach”, Robotics and Autonomous Systems. 62 (6): 766–781, (2014).
• [36] Ren, H., and Pinhas B-T. "Learning inverse kinematics and dynamics of a robotic manipulator using generative adversarial networks." Robotics and Autonomous Systems, 124: 103386, (2020).
• [37] Karaboga, D., and Basturk, B. A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. Journal Of Global Optimization, 39: 459–471, (2007).
• [38] González J.R., Pelta D.A., Cruz C., Terrazas G., and Krasnogor N. (Eds.), “Nature Inspired Cooperative Strategies for Optimization (NICSO 2010)”, Springer Berlin Heidelberg, 65-74, (2010).
• [39] Hansen N., Lozano J.A., Larrañaga P., Inza I., and Bengoetxea E. (Eds.), “Towards a new evolutionary computation: advances in the estimation of distribution algorithms”, Springer Berlin Heidelberg, 75-102, (2006).
• [40] Yang X.S., and Deb S. “Nature Biologically Inspired Computing”, World Congress on Nature & Biologically Inspired Computing IEEE, 210-214, (2009).
• [41] Storn, R., and Price, K. “Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces”, Journal of Global Optimization, 11: 341–359 (1997).
• [42] Civicioglu, P., “Transforming geocentric cartesian coordinates to geodetic coordinates by using differential search algorithm.” Computers & Geosciences, 46:229-247, (2012).
• [43] Man, K. F., Tang, K. S., and Kwong, S., “Genetic algorithms: concepts and applications [in engineering design]”. IEEE Transactions on Industrial Electronics, 43(5): 519-534 (1996).
• [44] Kennedy J. and Eberhart R. “Particle Swarm Optimization”, IEEE International Conference on Neural Networks, Washington, DC, USA, 1942-1948, (1995).
• [45] Shi, J., Mao, Y., Li, P., Liu, G., Liu, P., Yang, X., and Wang, D. (2020). “Hybrid mutation fruit fly optimization algorithm for solving the inverse kinematics of a redundant robot manipulator”. Mathematical Problems in Engineering, 2020.
• [46] Dereli, S, and Köker R. "A meta-heuristic proposal for inverse kinematics solution of 7-DOF serial robotic manipulator: quantum behaved particle swarm algorithm." Artificial Intelligence Review 53(2): 949-964, (2020).
• [47] Zhou, D., Xie, M., Xuan, P., and Jia, R. “A teaching method for the theory and application of robot kinematics based on MATLAB and V‐REP”. Computer Applications in Engineering Education, 28(2): 239-253 (2020).
• [48] Al Tahtawi, A. R., Agni, M., and Hendrawati, T. D. "Small-scale Robot Arm Design with Pick and Place Mission Based on Inverse Kinematics." Journal of Robotics and Control (JRC) 2(6): 469-475, (2021).
• [49] Vasilyev, I. A., and A. M. Lyashin. "Analytical solution to inverse kinematic problem for 6-DOF robot-manipulator." Automation and Remote Control 71(10): 2195-2199, (2010).
• [50] Kucuk S., and Bingul Z., “The Inverse kinematics solutions of industrial robot manipulators”, IEEE Conferance on Mechatronics, 274-279, (2004).
• [51] Denavit J., and Hartenberg S., “A kinematic notation for lower-pair mechanisms based on matrices”, Journal of Applied Mechanics 1: 215-221, (1955).
• [52] Cengiz, E., Yılmaz, C., and Kahraman, H.T. “Classification of Human and Vehicles with The Deep Learning Based on Transfer Learning Method”, Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 9(3): 215-225 (2021).
• [53] Cengiz, E., Babagiray, M., Aysal, F. E., and Aksoy, F. “Kinematic viscosity estimation of fuel oil with comparison of machine learning methods” Fuel, 316: 123422, (2022).
• [54] Kelek, M. M., Cengiz, E., Oguz Y., and Yönetken, A. “RLBP Metodu ile Mamografi Görüntülerinin İncelenmesi ve Sınıflandırılması”, Afyon Kocatepe Üniversitesi Uluslararası Mühendislik Teknolojileri ve Uygulamalı Bilimler Dergisi, 4(2): 59-64, (2021).
• [55] Güvenç, U., Dursun, M., and Çimen, H., “Artificial Neural Network Based Modeling Of Cutting Time In The Marble Cutting Process”, International Journal of Technological Sciences, 3(2): 9-16 (2011).
• [56] Karadağ B., Arı A., and Karadağ M., “Derin öğrenme modellerinin sinirsel stil aktarımı performanslarının karşılaştırılması”, Politeknik Dergisi, 24(4): 1611-1622, (2021).
• [57] Yumurtaci M, and Yabanova İ. “Yapay Sinir Ağları ile Dinamik Ağırlık Tahmin Uygulaması”, Politeknik Dergisi, 20(1): 37-41, (2017).
• [58] Ngah, S., Bakar, R. A., Embong, A., and Razali, S., “Two-steps implementation of sigmoid function for artificial neural network in field programmable gate array”, ARPN journal of engineering and applied sciences, 11(7): 4882-4888 (2016).
• [59] Wanto, A., Windarto, A. P., Hartama, D., and Parlina, I., “Use of binary sigmoid function and linear identity in artificial neural networks for forecasting population density”, International Journal of Information System & Technology, 1(1): 43-54, (2017).