{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:39:11Z","timestamp":1773376751899,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universidad de Guadalajara"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>This work introduces a unified Artificial Intelligence-based framework for the optimal tuning of gains in a neural discrete-time sliding mode controller (SMC) applied to a two-degree-of-freedom robotic manipulator. The novelty lies in combining surrogate-assisted optimization with normalized search spaces to enable a fair comparative analysis of three metaheuristic strategies: Bayesian Optimization (BO), Particle Swarm Optimization (PSO), and Genetic Algorithms (GAs). The manipulator dynamics are identified via a discrete-time recurrent high-order neural network (NN) trained online using an Extended Kalman Filter with adaptive noise covariance updates, allowing the model to accurately capture unmodeled dynamics, nonlinearities, parametric variations, and process\/measurement noise. This neural representation serves as the predictive plant for the discrete-time SMC, enabling precise control of joint angular positions under sinusoidal phase-shifted references. To construct the optimization dataset, MATLAB\u00ae simulations sweep the controller gains (k0*,k1*) over a bounded physical domain, logging steady-state tracking errors. These are normalized to mitigate scaling effects and improve convergence stability. Optimization is executed in Python\u00ae using integrated scikit-learn, DEAP, and scikit-optimize routines. Simulation results reveal that all three algorithms reach high-performance gain configurations. Here, the combined cost is the normalized aggregate objective J\u02dc constructed from the steady-state tracking errors of both joints. Under identical experimental conditions (shared data loading\/normalization and a single Python pipeline), PSO attains the lowest error in Joint 1 (7.36\u00d710\u22125 rad) with the shortest runtime (23.44 s); GA yields the lowest error in Joint 2 (8.18\u00d710\u22123 rad) at higher computational expense (\u224869.7 s including refinement); and BO is competitive in both joints (7.81\u00d710\u22125 rad, 8.39\u00d710\u22123 rad) with a runtime comparable to PSO (23.65 s) while using only 50 evaluations.<\/jats:p>","DOI":"10.3390\/robotics14090128","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T12:33:32Z","timestamp":1758285212000},"page":"128","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AI-Based Optimization of a Neural Discrete-Time Sliding Mode Controller via Bayesian, Particle Swarm, and Genetic Algorithms"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0781-0490","authenticated-orcid":false,"given":"Carlos E.","family":"Casta\u00f1eda","sequence":"first","affiliation":[{"name":"Centro Universitario de los Lagos, Universidad de Guadalajara, Lagos de Moreno 47460, Jalisco, Mexico"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Silaa, M.Y., Barambones, O., and Bencherif, A. (2024). Robust adaptive sliding mode control using stochastic gradient descent for robot arm manipulator trajectory tracking. Electronics, 13.","DOI":"10.3390\/electronics13193903"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sosa M\u00e9ndez, D., Bedolla-Mart\u00ednez, D., Saad, M., Kali, Y., Garc\u00eda Cena, C.E., and \u00c1lvarez, \u00c1.L. (2025). Upper-limb robotic rehabilitation: Online sliding mode controller gain tuning using particle swarm optimization. Robotics, 14.","DOI":"10.3390\/robotics14040051"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3146","DOI":"10.1109\/LRA.2022.3145957","article-title":"Computational model of robot trust in human co-worker for physical human-robot collaboration","volume":"7","author":"Wang","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Martinez-Cantin, R. (June, January 29). Bayesian optimization with adaptive kernels for robot control. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore.","DOI":"10.1109\/ICRA.2017.7989380"},{"key":"ref_5","first-page":"119","article-title":"Genetic Algorithm Optimization of sliding Mode Controller Parameters for Robot Manipulator","volume":"12","author":"Saidi","year":"2021","journal-title":"Int. J. Emerg. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1049\/ell2.12300","article-title":"Intelligent control of a single-link flexible manipulator using sliding modes and artificial neural networks","volume":"57","author":"Lima","year":"2021","journal-title":"Electron. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mosharafian, S., Afzali, S., Bao, Y., and Velni, J.M. (2022, January 12\u201315). A deep reinforcement learning-based sliding mode control design for partially-known nonlinear systems. Proceedings of the 2022 European Control Conference (ECC), London, UK.","DOI":"10.23919\/ECC55457.2022.9838169"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6317","DOI":"10.1109\/TIE.2024.3488314","article-title":"Sampled-Data Admittance-Based Control for Physical Human\u2013Robot Interaction With Data-Driven Moving Horizon Velocity Estimation","volume":"72","author":"Duan","year":"2024","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_9","unstructured":"Spong, M.W., Hutchinson, S., and Vidyasagar, M. (2006). Robot Modeling and Control, John Wiley & Sons."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.ifacol.2018.07.299","article-title":"Fine-tuning of a fuzzy computed-torque control for a 2-DOF robot via genetic algorithms","volume":"51","year":"2018","journal-title":"IFAC- PapersOnLine"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/S0098-1354(99)00007-1","article-title":"Time-discretization of nonlinear control systems via Taylor methods","volume":"23","author":"Kazantzis","year":"1999","journal-title":"Comput. Chem. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neunet.2012.03.005","article-title":"Decentralized neural identifier and control for nonlinear systems based on extended Kalman filter","volume":"31","author":"Esquivel","year":"2012","journal-title":"Neural Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Siebert, J., Gro\u00df, J., and Schroth, C. (2021). A systematic review of python packages for time series analysis. arXiv.","DOI":"10.3390\/engproc2021005022"},{"key":"ref_14","unstructured":"Rayhan, R., Rayhan, A., and Kinzler, R. (2025, September 14). Exploring the Power of Data Manipulation and Analysis: A Comprehensive Study of NumPy, SciPy, and Pandas. Available online: https:\/\/www.researchgate.net\/publication\/373217405_Exploring_the_Power_of_Data_Manipulation_and_Analysis_A_Comprehensive_Study_of_NumPy_SciPy_and_Pandas."},{"key":"ref_15","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhao, K., Liu, X., and Xu, H. (2024). Design and optimization of haze prediction model based on particle swarm optimization algorithm and graphics processor. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-60486-9"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105570","DOI":"10.1016\/j.scs.2024.105570","article-title":"Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models","volume":"118","author":"Kim","year":"2025","journal-title":"Sustain. Cities Soc."},{"key":"ref_18","unstructured":"Jolly, K. (2018). Machine Learning with Scikit-Learn Quick Start Guide: Classification, Regression, and Clustering Techniques in Python, Packt Publishing Ltd."},{"key":"ref_19","unstructured":"Head, T., Cherti, M., Pedregosa, F., Zhdanov, M., Louppe, G., Raffel, C., Mueller, A., Fauchere, N., McInnes, L., and Grisel, O. (2025, September 14). Scikit-Optimize: Sequential Model-Based Optimization with Scikit-Learn. Available online: https:\/\/scikit-optimize.github.io\/stable\/."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Greif, L., H\u00fcbschle, N., Kimmig, A., Kreuzwieser, S., Martenne, A., and Ovtcharova, J. (2025). Structured sampling strategies in Bayesian optimization: Evaluation in mathematical and real-world scenarios. J. Intell. Manuf., 1\u201331.","DOI":"10.1007\/s10845-025-02597-2"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1007\/s11831-021-09694-4","article-title":"Particle swarm optimization algorithm and its applications: A systematic review","volume":"29","author":"Gad","year":"2022","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Malashin, I., Masich, I., Tynchenko, V., Nelyub, V., Borodulin, A., and Gantimurov, A. (2024). Application of natural language processing and genetic algorithm to fine-tune hyperparameters of classifiers for economic activities analysis. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8060068"},{"key":"ref_23","unstructured":"Hackeling, G. (2017). Mastering Machine Learning with Scikit-Learn, Packt Publishing Ltd."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Roeva, O., Zoteva, D., Roeva, G., Ignatova, M., and Lyubenova, V. (2024). An Effective Hybrid Metaheuristic Approach Based on the Genetic Algorithm. Mathematics, 12.","DOI":"10.3390\/math12233815"},{"key":"ref_25","first-page":"174","article-title":"New Approach of Self-Adaptive Simulated Binary Crossover-Elitism in Genetic Algorithms for Numerical Function Optimization","volume":"12","author":"Fanggidae","year":"2024","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hamamatsu, Y., Rebane, J., Kruusmaa, M., and Ristolainen, A. (2024, January 18\u201320). Bayesian Optimization Based Self-Improving Sliding Mode Controller For a Bio-Inspired Marine Robot. Proceedings of the 2024 IEEE\/OES Autonomous Underwater Vehicles Symposium (AUV), Boston, MA, USA.","DOI":"10.1109\/AUV61864.2024.11030775"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1515\/auto-2023-0181","article-title":"Local Bayesian optimization for controller tuning with crash constraints","volume":"72","author":"Stenger","year":"2024","journal-title":"at-Automatisierungstechnik"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"168","DOI":"10.11591\/ijra.v11i2.pp168-180","article-title":"Modified power rate sliding mode control for robot manipulator based on particle swarm optimization","volume":"11","author":"Sinan","year":"2022","journal-title":"IAES Int. J. Robot. Autom."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lopez-Franco, C., Diaz, D., Hernandez-Barragan, J., Arana-Daniel, N., and Lopez-Franco, M. (2022). A metaheuristic optimization approach for trajectory tracking of robot manipulators. Mathematics, 10.","DOI":"10.3390\/math10071051"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2968","DOI":"10.1016\/j.ifacol.2022.10.183","article-title":"Genetic Algorithm-Based Sliding Mode Control of a Human Arm Model","volume":"55","author":"Kheshti","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"ref_31","unstructured":"(1998). Manipulating Industrial Robots\u2014Performance Criteria and Related Test Methods; Technical Report (Standard No. ISO 9283:1998)."},{"key":"ref_32","unstructured":"Nise, N.S. (2019). Control Systems Engineering, John Wiley & Sons."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/9\/128\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:49:09Z","timestamp":1760035749000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/9\/128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":32,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["robotics14090128"],"URL":"https:\/\/doi.org\/10.3390\/robotics14090128","relation":{},"ISSN":["2218-6581"],"issn-type":[{"value":"2218-6581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]}}}