Abstract
The forward kinematics problem of parallel robots due to the resulting system of nonlinear equations has always been a challenge in the field of robotics. In this paper, an effective hybrid method is proposed based on the classification, neural networks, and particle swarm optimization algorithm for solving the forward kinematics problem of parallel robots. In order to increase the accuracy, the workspace of a parallel robot is divided into several subspaces. Then, the ECOC classifier is used to determine the subspace corresponding to the problem. Finally, the solutions of the forward kinematics problem are estimated using two evolutionary neural networks in each subspace. The proposed method is implemented on a 4-PUU parallel robot to estimate the pose of the moving platform through a path and its results compared with the results of the other neural network-based methods. The obtained results indicate that the proposed method provides a real-time solution with acceptable accuracy for the forward kinematics problem of the parallel robots.
Similar content being viewed by others
References
Chauhan DKS, Vundavilli PR (2022) Forward kinematics of the stewart parallel manipulator using machine learning. Int J Comput Methods. https://doi.org/10.1142/S0219876221420093
Duin R, Juszczak P, Paclik P, Pekalska E, DeRidder D, Tax D (2007) Prtools4.1, a matlab toolbox for pattern recognition, Tech Rep, Delft University of Technology, Netherlands
Gan D, Liao Q, Dai JS, Wei S, Seneviratne L (2009) Forward displacement analysis of the general 6–6 Stewart mechanism using Grobner bases. Mech Mach Theory 44:1640–1674
Gosselin CM, Merlet J-P (1994) The direct kinematics of planar parallel manipulators: special architectures and number of solutions. Mech Mach Theory 29:1083–1098
Karlik B, Aydin S (2000) An improved approach to the solution of inverse kinematics problems for robot manipulators. Eng Appl Artif Intell 13:159–164
Kong X, Gosselin CM (2007) Type synthesis of parallel mechanisms, vol 33. Springer, New York
Liu G, Wang Y, Zhang Y, Xie Z (2015) Real-time solution of the forward kinematics for a parallel haptic device using a numerical approach based on neural networks. J Mech Sci Technol 29(2487):2499
Liu C, Guohua C, Yongyin Q (2019) Safety analysis via forward kinematics of delta parallel robot using machine learning. Saf Sci 117:243–249
Masouleh MT, Gosselin C, Husty M, Walter DR (2011) Forward kinematic problem of 5-rpur parallel mechanisms (3t2r) with identical limb structures. Mech Mach Theory 46:945–959
Merlet J-P (2004) Solving the forward kinematics of a gough-type parallel manipulator with interval analysis. Int J Robot Res 23:221–235
Merlet JP (2006) Parallel robots, vol 128. Springer, New York
Mishra UA, Caro S (2022) Forward kinematics for suspended under-actuated cable-driven parallel robots with elastic cables: a neural network approach. J Mech Robotics 14(4):041008
Mohammed AM, Li S (2016) Dynamic neural networks for kinematic redundancy resolution of parallel Stewart platforms. IEEE Transactions Cybern 46:1538–1550
Naderi D, Masouleh MT, Varshovi-Jaghargh P (2016) Grobner basis and resultant method for the forward displacement of 3-dof planar parallel manipulators in seven-dimensional kinematic space. Robotica 34(11):2610–2628
Parikh PJ, Lam SS (2009) Solving the forward kinematics problem in parallel manipulators using an iterative artificial neural network strategy. Int J Adv Manuf Technol 40:595–606
Parsa SS, Daniali HM, Ghaderi R (2010) Optimization of parallel manipulator trajectory for obstacle and singularity avoidances based on neural network. Int J Adv Manuf Technol 51:811–816
Rahmani A, Ghanbari A, Mahboubkhah M (2014) Wavelet neural network application for kinematic solution of 2-(6ups) hybrid manipulator, Indian. J Sci Technol 7:2046–2054
Raj D, Muthuswamy S (2020) A forward, inverse kinematics and workspace analysis of 3rps and 3rps-r parallel manipulators. Iranian J Sci Technol Transactions Mech Eng 44:1–17
Sadjadian H, Taghirad H, Fatehi A (2005) Neural networks approaches for computing the forward kinematics of a redundant parallel manipulator. Int J Comput Intell 2:40–47
Siciliano B, Khatib O (2016) Springer handbook of robotics. Springer, New York
Tao M, Feng B, Li L, Li L (2021) Forward kinematics solution of cable robot based on neural network and lm algorithm, In: (2021) IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), IEEE Vol 5, 2519–2524
Varshovi-Jaghargh P, Naderi D, Tale-Masouleh M (2013) Forward kinematic problem of two 4-rrur with different geometric structures and one 4-ruu parallel robots. Modares Mech Eng 12(4):105–119
Varshovi-Jaghargh P, Naderi D, Tale-Masouleh M (2014) Forward kinematic problem of three 4-DOF parallel mechanisms (4-PRUR1, 4-PRUR2 and 4-PUU) with identical limb structures performing 3T1R motion pattern. Sci Iranica 21:1671–1682
Varshovi-Jaghargh P, Masouleh MT, Naderi D (2019) Forward kinematic analysis of parallel mechanisms in seven-dimensional kinematic space by considering limitation of passive joints motion. Iranian J Sci Technol Transactions Mech Eng 43(2):315–329
Wu X, Zhijiang X (2019) Forward kinematics analysis of a novel 3-dof parallel manipulator. Scientia Iranica 26(1):346–357
Wu J, Gao Y, Zhang B, Wang L (2017) Workspace and dynamic performance evaluation of the parallel manipulators in a spray-painting equipment. Robotics Computer Integr Manuf 44:199–207
Wu J, Zhang B, Wang L, Yu G (2021) An iterative learning method for realizing accurate dynamic feedforward control of an industrial hybrid robot. Sci China Technol Sci 64(6):1177–1188
Wu J, Ye H, Yu G, Huang T (2022) A novel dynamic evaluation method and its application to a 4-dof parallel manipulator. Mech Mach Theory 168:104627
Xue B, Zhang M, Browne WN (2013) Particle swarm optimization for feature selection in classification: a multi-objective approach. IEEE Transactions Cybern 43:1656–1671
Zare S, Haghighi MS, Yazdi MRH, Kalhor A, Masouleh MT (2020) Kinematic analysis of an under-constrained cable-driven robot using neural networks, In: 2020 28th Iranian Conference on Electrical Engineering (ICEE), IEEE, pp 1–6
Zhang HQ, Gao Q, Zhang M, Yao YA (2021) Forward kinematics of parallel robot based on neural network newton-raphson iterative algorithm, In: International Conference on Intelligent Equipment and Special Robots (ICIESR 2021), SPIE Vol 12127, 347–352
Zhang H, Fang H, Jiang B, Zhao F, Zhu T (2019) A newton-raphson and bp neural network hybrid algorithm for forward kinematics of parallel manipulator, In: WRC Symposium on Advanced Robotics and Automation, IEEE, pp 122–127
Zubizarreta A, Larrea M, Irigoyen E, Cabanes I, Portillo E (2018) Real time direct kinematic problem computation of the 3prs robot using neural networks. Neurocomputing 271:104–114
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tavassolian, F., Khotanlou, H. & Varshovi-Jaghargh, P. Forward Kinematic Analysis of Spatial Parallel Robots Using a Parallel Evolutionary Neural Networks. Iran J Sci Technol Trans Mech Eng 47, 1079–1092 (2023). https://doi.org/10.1007/s40997-022-00558-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40997-022-00558-1