{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:58:06Z","timestamp":1772906286075,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s13042-025-02812-9","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T06:23:53Z","timestamp":1758522233000},"page":"10939-10957","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement learning-based friction compensation of an inverted pendulum on a cart"],"prefix":"10.1007","volume":"16","author":[{"given":"Jaehwan","family":"Jeong","sequence":"first","affiliation":[]},{"given":"Jaepil","family":"Ban","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"2812_CR1","doi-asserted-by":"publisher","unstructured":"Prasad LB, Tyagi B, Gupta HO (2011) Optimal control of nonlinear inverted pendulum dynamical system with disturbance input using PID controller & LQR. In: Proceedings of the 2011 IEEE international conference on control system, computing and engineering, Penang, Malaysia, pp 540-545. https:\/\/doi.org\/10.1109\/ICCSCE.2011.6190585","DOI":"10.1109\/ICCSCE.2011.6190585"},{"issue":"12","key":"2812_CR2","doi-asserted-by":"publisher","first-page":"12905","DOI":"10.1109\/TCYB.2021.3091531","volume":"52","author":"H Ma","year":"2022","unstructured":"Ma H, Zhou Q, Li H, Lu R (2022) Adaptive prescribed performance control of a flexible-joint robotic manipulator with dynamic uncertainties. IEEE Trans Cybern 52(12):12905\u201312915. https:\/\/doi.org\/10.1109\/TCYB.2021.3091531","journal-title":"IEEE Trans Cybern"},{"issue":"5","key":"2812_CR3","doi-asserted-by":"publisher","first-page":"4935","DOI":"10.1109\/TVT.2020.2980169","volume":"69","author":"N Guo","year":"2020","unstructured":"Guo N, Lenzo B, Zhang X, Zou Y, Zhai R, Zhang T (2020) A real-time nonlinear model predictive controller for yaw motion optimization of distributed drive electric vehicles. IEEE Trans Vehicular Technol 69(5):4935\u20134946. https:\/\/doi.org\/10.1109\/TVT.2020.2980169","journal-title":"IEEE Trans Vehicular Technol"},{"key":"2812_CR4","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1016\/j.ymssp.2017.05.036","volume":"98","author":"B Li","year":"2018","unstructured":"Li B, Rui X (2018) Vibration control of uncertain multiple launch rocket system using radial basis function neural network. Mech Syst Signal Process 98:702\u2013721. https:\/\/doi.org\/10.1016\/j.ymssp.2017.05.036","journal-title":"Mech Syst Signal Process"},{"key":"2812_CR5","doi-asserted-by":"publisher","unstructured":"Tijani I, Akmeliawati R, Salami M (2011). Artificial intelligent based friction modelling and compensation in motion control system. https:\/\/doi.org\/10.5772\/23432","DOI":"10.5772\/23432"},{"key":"2812_CR6","unstructured":"Lee DJ, Park Y, Park YS (2009) Adaptive friction compensation for asymmetric Coulomb and viscous friction. In: Asia-Pacific vibration conference"},{"key":"2812_CR7","doi-asserted-by":"publisher","first-page":"49066","DOI":"10.1109\/ACCESS.2020.2978025","volume":"8","author":"Z Ben Hazem","year":"2020","unstructured":"Ben Hazem Z, Fotuhi MJ, Bing\u00fcl Z (2020) A comparative study of the joint neuro-fuzzy friction models for a triple link rotary inverted pendulum. IEEE Access 8:49066\u201349078","journal-title":"IEEE Access"},{"issue":"1","key":"2812_CR8","first-page":"74","volume":"8","author":"Z Ben Hazem","year":"2019","unstructured":"Ben Hazem Z, Fotuhi MJ, Bing\u00fcl Z (2019) Comparison of friction estimation models for rotary triple inverted pendulum. Int J Mech Eng Robotics Res 8(1):74\u201378","journal-title":"Int J Mech Eng Robotics Res"},{"key":"2812_CR9","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.mechatronics.2015.06.011","volume":"30","author":"F Dai","year":"2015","unstructured":"Dai F, Gao X, Jiang S, Guo W, Liu Y (2015) A two-wheeled inverted pendulum robot with friction compensation. Mechatronics 30:116\u2013125","journal-title":"Mechatronics"},{"key":"2812_CR10","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.ins.2019.03.051","volume":"491","author":"J Wu","year":"2019","unstructured":"Wu J, Wang Y, Ye W, Su C-Y (2019) Control strategy based on fourier transformation and intelligent optimization for planar pendubot. Inf Sci 491:279\u2013288. https:\/\/doi.org\/10.1016\/j.ins.2019.03.051","journal-title":"Inf Sci"},{"issue":"2","key":"2812_CR11","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1109\/TIE.2011.2148678","volume":"59","author":"H Chaoui","year":"2012","unstructured":"Chaoui H, Sicard P (2012) Adaptive fuzzy logic control of permanent magnet synchronous machines with nonlinear friction. IEEE Trans Ind Electron 59(2):1123\u20131133. https:\/\/doi.org\/10.1109\/TIE.2011.2148678","journal-title":"IEEE Trans Ind Electron"},{"key":"2812_CR12","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1007\/s11071-014-1753-y","volume":"79","author":"MM Azimi","year":"2015","unstructured":"Azimi MM, Koofigar HR (2015) Adaptive fuzzy backstepping controller design for uncertain underactuated robotic systems. Nonlinear Dyn 79:1457\u20131468. https:\/\/doi.org\/10.1007\/s11071-014-1753-y","journal-title":"Nonlinear Dyn"},{"key":"2812_CR13","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1109\/TMECH.2009.2036994","volume":"16","author":"TH Lee","year":"2011","unstructured":"Lee TH, Tan KK, Huang S (2011) Adaptive friction compensation with a dynamical friction model. IEEE\/ASME Trans Mechatron 16:133\u2013140. https:\/\/doi.org\/10.1109\/TMECH.2009.2036994","journal-title":"IEEE\/ASME Trans Mechatron"},{"key":"2812_CR14","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.automatica.2017.12.003","volume":"89","author":"AG Loukianov","year":"2018","unstructured":"Loukianov AG, Rivera Dom\u00ednguez J, Castillo-Toledo B (2018) Robust sliding mode regulation of nonlinear systems. Automatica 89:241\u2013246. https:\/\/doi.org\/10.1016\/j.automatica.2017.12.003","journal-title":"Automatica"},{"key":"2812_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685","volume":"214","author":"A Heuillet","year":"2021","unstructured":"Heuillet A, Couthouis F, D\u00edaz-Rodr\u00edguez N (2021) Explainability in deep reinforcement learning. Knowl Based Syst 214:106685. https:\/\/doi.org\/10.1016\/j.knosys.2020.106685","journal-title":"Knowl Based Syst"},{"key":"2812_CR16","doi-asserted-by":"publisher","first-page":"9326","DOI":"10.1109\/TCYB.2021.3053414","volume":"52","author":"Q Wei","year":"2022","unstructured":"Wei Q, Ma H, Chen C, Dong D (2022) Deep reinforcement learning with quantum-inspired experience replay. IEEE Trans Cybern 52:9326\u20139338. https:\/\/doi.org\/10.1109\/TCYB.2021.3053414","journal-title":"IEEE Trans Cybern"},{"key":"2812_CR17","doi-asserted-by":"publisher","first-page":"7900","DOI":"10.1109\/TNNLS.2022.3146976","volume":"34","author":"R Zhang","year":"2023","unstructured":"Zhang R, Zong Q, Zhang X, Dou L, Tian B (2023) Game of drones: multi-uav pursuit-evasion game with online motion planning by deep reinforcement learning. IEEE Trans Neural Netw Learn Syst 34:7900\u20137909. https:\/\/doi.org\/10.1109\/TNNLS.2022.3146976","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2812_CR18","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.neucom.2022.05.006","volume":"497","author":"P Chen","year":"2022","unstructured":"Chen P, Pei J, Lu W, Li M (2022) A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidance. Neurocomputing 497:64\u201375. https:\/\/doi.org\/10.1016\/j.neucom.2022.05.006","journal-title":"Neurocomputing"},{"key":"2812_CR19","doi-asserted-by":"publisher","unstructured":"Aoki S, Higuchi T, Altintas O (2020) Cooperative perception with deep reinforcement learning for connected vehicles. In: 2020 IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA, pp 328\u2013334. https:\/\/doi.org\/10.1109\/IV47402.2020.9304570","DOI":"10.1109\/IV47402.2020.9304570"},{"key":"2812_CR20","doi-asserted-by":"publisher","first-page":"6584","DOI":"10.1109\/TNNLS.2021.3082568","volume":"33","author":"J Duan","year":"2022","unstructured":"Duan J, Guan Y, Li SE, Ren Y, Sun Q, Cheng B (2022) Distributional soft actor-critic: off-policy reinforcement learning for addressing value estimation errors. IEEE Trans Neural Netw Learn Syst 33:6584\u20136598. https:\/\/doi.org\/10.1109\/TNNLS.2021.3082568","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2812_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109450","volume":"128","author":"T Shuprajhaa","year":"2022","unstructured":"Shuprajhaa T, Sujit SK, Srinivasan K (2022) Reinforcement learning based adaptive pid controller design for control of linear\/nonlinear unstable processes. Appl Soft Comput 128:109450. https:\/\/doi.org\/10.1016\/j.asoc.2022.109450","journal-title":"Appl Soft Comput"},{"key":"2812_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118346","volume":"309","author":"J Arroyo","year":"2022","unstructured":"Arroyo J, Manna C, Spiessens F, Helsen L (2022) Reinforced model predictive control (rl-mpc) for building energy management. Appl Energy 309:118346. https:\/\/doi.org\/10.1016\/j.apenergy.2021.118346","journal-title":"Appl Energy"},{"issue":"7","key":"2812_CR23","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TCYB.2015.2417170","volume":"45","author":"D Liu","year":"2015","unstructured":"Liu D, Yang X, Wang D, Wei Q (2015) Reinforcement-learning-based robust controller design for continuous-time uncertain nonlinear systems subject to input constraints. IEEE Trans Cybern 45(7):1372\u20131385. https:\/\/doi.org\/10.1109\/TCYB.2015.2417170","journal-title":"IEEE Trans Cybern"},{"key":"2812_CR24","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/TSMCC.2011.2106494","volume":"42","author":"S Adam","year":"2012","unstructured":"Adam S, Busoniu L, Babuska R (2012) Experience replay for real-time reinforcement learning control. IEEE Trans Syst Man Cybern Part C Appl Rev 42:201\u2013212. https:\/\/doi.org\/10.1109\/TSMCC.2011.2106494","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"2812_CR25","doi-asserted-by":"publisher","unstructured":"Qin Y, Zhang W, Shi J, Liu J (2018) Improve PID controller through reinforcement learning. In: 2018 IEEE CSAA Guidance, Navigation and Control Conference (CGNCC), Xiamen, China, pp 1\u20136. https:\/\/doi.org\/10.1109\/GNCC42960.2018.9019095","DOI":"10.1109\/GNCC42960.2018.9019095"},{"key":"2812_CR26","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/TFUZZ.2010.2081994","volume":"19","author":"WM Hinojosa","year":"2011","unstructured":"Hinojosa WM, Nefti S, Kaymak U (2011) Systems control with generalized probabilistic fuzzy-reinforcement learning. IEEE Trans Fuzzy Syst 19:51\u201364. https:\/\/doi.org\/10.1109\/TFUZZ.2010.2081994","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"2812_CR27","doi-asserted-by":"publisher","unstructured":"Puriel-Gil G, Yu W, Sossa H (2018) Reinforcement learning compensation based PD control for inverted pendulum. In: 2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), Mexico City, Mexico, pp 1\u20136. https:\/\/doi.org\/10.1109\/ICEEE.2018.8533946","DOI":"10.1109\/ICEEE.2018.8533946"},{"key":"2812_CR28","doi-asserted-by":"publisher","unstructured":"Hernandez R, Garcia-Hernandez R, Jurado F (2023) Control of an underactuated mechanical system with reinforcement learning compensation. In: 2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), Mexico City, Mexico, pp 1\u20136. https:\/\/doi.org\/10.1109\/CCE60043.2023.10332903","DOI":"10.1109\/CCE60043.2023.10332903"},{"key":"2812_CR29","doi-asserted-by":"crossref","unstructured":"Prasad LB, Tyagi B, Gupta HO (2011) Optimal control of nonlinear inverted pendulum dynamical system with disturbance input using PID controller & LQR. In: Proceedings of the 2011 IEEE International Conference on Control System, Computing and Engineering, Penang, Malaysia, pp 540-545","DOI":"10.1109\/ICCSCE.2011.6190585"},{"key":"2812_CR30","doi-asserted-by":"crossref","unstructured":"Bugeja M (2003) Non-linear swing-up and stabilizing control of an inverted pendulum system. The IEEE Region 8 EUROCON 2003. Computer as a Tool, Ljubljana, Slovenia, 437-441 vol.2","DOI":"10.1109\/EURCON.2003.1248235"},{"key":"2812_CR31","doi-asserted-by":"publisher","unstructured":"Prasad LB, Tyagi B, Gupta HO (2012) Modelling and simulation for optimal control of nonlinear inverted pendulum dynamical system using PID controller and LQR. In: 2012 Sixth Asia Modelling Symposium, Bali, Indonesia, pp 138\u2013143. https:\/\/doi.org\/10.1109\/AMS.2012.21","DOI":"10.1109\/AMS.2012.21"},{"key":"2812_CR32","doi-asserted-by":"publisher","first-page":"95195","DOI":"10.1109\/ACCESS.2023.3310405","volume":"11","author":"MR Hong","year":"2023","unstructured":"Hong MR et al (2023) Optimizing reinforcement learning control model in furuta pendulum and transferring it to real-world. IEEE Access 11:95195\u201395200. https:\/\/doi.org\/10.1109\/ACCESS.2023.3310405","journal-title":"IEEE Access"},{"key":"2812_CR33","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.proeng.2013.09.088","volume":"64","author":"E Vinodh Kumar","year":"2013","unstructured":"Vinodh Kumar E, Jerome J (2013) Robust lqr controller design for stabilizing and trajectory tracking of inverted pendulum. Procedia Eng 64:169\u2013178. https:\/\/doi.org\/10.1016\/j.proeng.2013.09.088","journal-title":"Procedia Eng"},{"key":"2812_CR34","volume-title":"Nonlinear systems","author":"HK Khalil","year":"2002","unstructured":"Khalil HK, Grizzle JW (2002) Nonlinear systems. Prentice hall, NJ"},{"issue":"1","key":"2812_CR35","first-page":"351","volume":"21","author":"KAJ Verbert","year":"2016","unstructured":"Verbert KAJ, T\u00f3th R, Babu\u0161ka R (2016) Adaptive friction compensation: a globally stable approach. IEEE\/ASME Trans Mechatron 21(1):351\u2013363","journal-title":"IEEE\/ASME Trans Mechatron"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02812-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02812-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02812-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:41:39Z","timestamp":1765618899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02812-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2812"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02812-9","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"28 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}