ANFIS Adaptive Neuro-fuzzy Inference System for six-degree-of-freedom kinematics with prismatic joint

This paper presents an application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) to solve the inverse kinematics problem of a 6-DOF robotic manipulator including a prismatic joint. The ANFIS model is trained using forward kinematics data, which are used to generate membership functions for each joint. These functions approximate the inverse kinematics solution, significantly reducing computational complexity compared to traditional approaches. The results show that the ANFIS-based model achieves a root mean square error (RMSE) of approximately 0.182, which is sufficiently accurate for practical applications such as lifting and transportation systems. Compared to Support Vector Machines (SVM, RMSE ≈ 0.428) and Deep Neural Networks (DNN, RMSE ≈ 0.145), ANFIS provides a balanced trade-off between accuracy, efficiency, and interpretability. Therefore, ANFIS can be considered a suitable and promising tool for real-time robotic control, especially in systems with limited computational resources.
EDN: JOHREI, https://elibrary/johrei

References

[1] Shah M.F., Khan N.A., Jamwal P.K. Inverse kinematics solution for a six-degree-of-freedom upper limb rehabilitation robot using deep learning models. Neural Comput. & Applic., 2025, doi: https://doi.org/10.1007/s00521-025-11222-5

[2] Huang H., Arogbonlo A., Yu S.et al. Adaptive neuro-fuzzy inference system based active force control with iterative learning for trajectory tracking of a biped robot. Int. J. Syst. Sci., 2025, vol. 56, no. 6, pp. 1171–1188, doi: https://doi.org/10.1080/00207721.2024.2420069

[3] Barhaghtalab M.H., Sepestanaki M.A., Mobayen S. et al. Design of an adaptive fuzzy-neural inference system-based control approach for robotic manipulators. Appl. Soft Comput., 2023, vol. 149-A, art. 110970, doi: https://doi.org/10.1016/j.asoc.2023.110970

[4] Sarhan R.A., Rashid Z.H., Hassan M.S. Motion control of 3-DoF delta robot using adaptive neuro fuzzy inference system. Int. J. Comput. Vis. Robot., 2025, vol. 15, no. 7, pp. 1–16, doi: https://dx.doi.org/10.1504/IJCVR.2025.143990

[5] Ben Hazem Z., Guler N., Altaif A.H. A study of advanced mathematical modeling and adaptive control strategies for trajectory tracking in the Mitsubishi RV-2AJ 5-DOF Robotic Arm. Discov. Robot., 2025, vol. 1, art. 2, doi: https://doi.org/10.1007/s44430-025-00001-5

[6] Monfared P., Fei X., Peng W. Computation of inverse kinematics of redundant manipulator using particle swarm optimization algorithm and its combination with artificial neural networks. Eng. Proc., 2024, vol. 76, no. 1, art. 58, doi: https://doi.org/10.3390/engproc2024076058

[7] Lu J., Zou T., Jiang X. A neural network based approach to inverse kinematics problem for general six-axis robots. Sensors, 2022, vol. 22, no. 22, art. 8909, doi: https://doi.org/10.3390/s22228909

[8] Zafar M.H., Moosavi S.K.R., Sanfilippo F. Inverse kinematic modelling of a 3-DOF robotic manipulator using hybrid deep learning models. Procedia CIRP, 2023, vol. 120, pp. 213–218, doi: https://doi.org/10.1016/j.procir.2023.08.038

[9] Alwardat M.Y., Alwan H.M. Forward and inverse kinematics of a 6-dof robotic manipulator with a prismatic joint using MATLAB robotics toolbox. IJATEE, 2024, vol. 11, no. 117, pp. 1097–1111, doi: https://doi.org/10.19101/IJATEE.2024.111100210

[10] Alvardat M.Y., Al-Aradzhi Kh.M., Mbolo O.E.L. et al. Geometric derivation of the Jacobian for six degrees of freedom with prismatic joint. Robototekhnika i tekhnicheskaya kibernetika [Robotics and Technical Cybernetics], 2024, vol. 12, no. 4, pp. 261–269, doi: https://doi.org/10.31776/RTCJ (in Russ.).

[11] Alwardat M.Y., Alwan H.M., Kochneva O.V. Comprehensive kinematic analysis for optimal performance of a 6-DOF robotic manipulator with prismatic joint (RRRRRP). Russ. Engin. Res., 2024, no. 11, pp. 1640–1647, doi: https://doi.org/10.3103/S1068798X24702691

[12] Alvardat M.Ya., Al-Arazhi Kh.M. Review of intelligent control methods for manipulators with rigid links. Avtomatizatsiya. Sovremennye tekhnologii [Automation. Modern Technologies], 2023, vol. 77, no. 10, pp. 466–474, doi: https://doi.org/10.36652/0869-4931-2023-77-10-466-474 (in Russ.).

[13] Alvardat M.Ya., Alvan Kh.M., M’bolo O.E. et al. Research of the robot-manipulators singularity. Avtomatizatsiya. Sovremennye tekhnologii [Automation. Modern Technologies], 2024, vol. 78, no. 4, pp. 173–179, doi: https://doi.org/10.36652/0869-4931-2024-78-4-173-179 (in Russ.).

[14] Saeedi B., Mohammadi Moghaddam M., Sadedel M. Inverse kinematics analysis of a wrist rehabilitation robot using artificial neural network and adaptive Neuro-Fuzzy inference system. Mech. Based Des. Struct. Mach., 2024, vol. 52, no. 12, pp. 10439–10487, doi: https://doi.org/10.1080/15397734.2024.2356066