{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T01:40:40Z","timestamp":1790646040007,"version":"4.1.0"},"reference-count":38,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51975587"],"award-info":[{"award-number":["51975587"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2013CB035504"],"award-info":[{"award-number":["2013CB035504"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities of Central South University","award":["2019zzts252"],"award-info":[{"award-number":["2019zzts252"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Autonomous planning robotic contact-rich manipulation has long been a challenging problem. Automatic peeling of glass substrates of LCD flat panel displays is a typical contact-rich manipulation task, which requires extremely high safe handling through the manipulation process. To this end of peeling glass substrates automatically, the system model is established from data and is used for the online planning of the robot motion in this paper. A simulation environment is designed to pretrain the process model with deep learning-based neural network structure to avoid expensive and time-consuming collection of real-time data. Then, an online learning algorithm is introduced to tune the pretrained model according to the real-time data from the peeling process experiments to cover the uncertainties of the real process. Finally, an Online Learning Model Predictive Path Integral (OL-MPPI) algorithm is proposed for the optimal trajectory planning of the robot. The performance of our algorithm was validated through glass substrate peeling tasks of experiments.<\/jats:p>","DOI":"10.3390\/s22031292","type":"journal-article","created":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T23:42:20Z","timestamp":1644363740000},"page":"1292","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Robotic Manipulation Planning for Automatic Peeling of Glass Substrate Based on Online Learning Model Predictive Path Integral"],"prefix":"10.3390","volume":"22","author":[{"given":"Liwei","family":"Hou","sequence":"first","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China"},{"name":"State Key Laboratory for High Performance Complex Manufacturing, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Zou","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yalin","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.jnoncrysol.2015.05.007","article-title":"Flat panel display glass: Current status and future","volume":"431","author":"Choi","year":"2016","journal-title":"J. Non-Cryst. Solids"},{"key":"ref_2","unstructured":"Wang, H., Zhang, Z., Yang, H., Liu, R., Qiu, W., Hou, L., and Liu, Y. (2018). Design and Use of the Glass Shoveling Device, Robotic Arm, Automatic Loading and Unloading Device. (CN108726174A), (In Chinese)."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/MRA.2007.339604","article-title":"Challenges for robot manipulation in human environments","volume":"14","author":"Kemp","year":"2007","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Qin, L., Wang, H., Yuan, Y., and Qin, S. (2021). Multi-Sensor Perception Strategy to Enhance Autonomy of Robotic Operation for Uncertain Peg-in-Hole Task. Sensors, 11.","DOI":"10.3390\/s21113818"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/S0736-5845(00)00052-1","article-title":"A robust trajectory tracking control of a polishing robot system based on CAM data","volume":"17","author":"Lee","year":"2011","journal-title":"Robot. Comput. -Integr. Manuf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Son, B., Kim, C.U., Kim, C., and Lee, D. (2020\u201324, January 25). Expert-emulating excavation trajectory planning for autonomous robotic industrial excavator. Proceedings of the 2020 International Conference on Intelligent Robots and Systems, Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9341036"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1108\/IR-01-2016-0020","article-title":"Experimental comparison of drag-wiper and roller-wiper glass-cleaning robots","volume":"43","author":"Zhou","year":"2016","journal-title":"Ind. Robot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"30","DOI":"10.3389\/fnbot.2020.00030","article-title":"An enhanced robot massage system in smart homes using force sensing and a dynamic movement primitive","volume":"14","author":"Li","year":"2020","journal-title":"Front. Neurorobot."},{"key":"ref_9","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103471","DOI":"10.1016\/j.compind.2021.103471","article-title":"Planning for automatic product assembly using reinforcement learning","volume":"130","author":"Zhang","year":"2021","journal-title":"Comput. Ind."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2737","DOI":"10.1109\/LRA.2021.3060389","article-title":"Reinforcement learning for robotic assembly using non-diagonal stiffness matrix","volume":"6","author":"Masahide","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1177\/0278364918755536","article-title":"A convex polynomial model for planar sliding mechanics: Theory, application, and experimental validation","volume":"37","author":"Zhou","year":"2018","journal-title":"Int. J. Robot. Res."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Bauza, M., and Alberto, R. (June, January 29). A probabilistic data-driven model for planar pushing. Proceedings of the 2017 IEEE International Conference on Robotics and Automation, Marina Bay Sands, Singapore.","DOI":"10.1109\/ICRA.2017.7989345"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1177\/0278364917698749","article-title":"Parameter and Contact Force Estimation of Planar Rigid-bodies Undergoing Frictional contact","volume":"36","author":"Fazeli","year":"2017","journal-title":"Int. J. Robot. Res."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ajay, A., Wu, J., Fazeli, N., Bauza, M., Kaelbling, L.P., Tenenbaum, J.B., and Rodriguez, A. (2018, January 1\u20135). Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing. Proceedings of the 2018 International Conference on Intelligent Robots and Systems, Madrid, Spain.","DOI":"10.1109\/IROS.2018.8593995"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/TIP.2019.2952032","article-title":"Unsupervised Single Image Dehazing Using Dark Channel Prior Loss","volume":"29","author":"Golts","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_17","unstructured":"Cranmer, M., Greydanus, S., Hoyer, S., Battaglia, P., Spergel, D., and Ho, S. (2020). Lagrangian Neural Networks. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Luo, J., Solowjow, E., Wen, C., Ojea, J.A., Agogino, A.M., Tamar, A., and Abbeel, P. (2019, January 20\u201324). Reinforcement learning on variable impedance controller for high-precision robotic assembly. Proceedings of the 2019 IEEE International Conference on Robotics and Automation, Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2586","DOI":"10.1109\/TAC.2014.2309282","article-title":"Optimal robust linear quadratic regulator for systems subject to uncertainties","volume":"59","author":"Terra","year":"2014","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hogan, F.R., Grau, E.R., and Rodriguez, A. (2018, January 21\u201326). Reactive planar manipulation with convex hybrid mpc. Proceedings of the 2018 IEEE International Conference on Robotics and Automation, Brisbane, Australia.","DOI":"10.1109\/ICRA.2018.8461175"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4688","DOI":"10.1109\/LRA.2021.3068908","article-title":"A unified mpc framework for whole-body dynamic locomotion and manipulation","volume":"6","author":"Sleiman","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"11011","DOI":"10.1088\/1742-5468\/2005\/11\/P11011","article-title":"Path integrals and symmetry breaking for optimal control theory","volume":"11","author":"Kappen","year":"2005","journal-title":"J. Stat. Mech. Theory Exp."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"344","DOI":"10.2514\/1.G001921","article-title":"Model predictive path integral control: From theory to parallel computation","volume":"40","author":"Williams","year":"2017","journal-title":"J. Guid. Control Dyn."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Arruda, E., Mathew, M.J., Kopicki, M., Mistry, M., Azad, M., and Wyatt, J.L. (2017, January 15\u201317). Uncertainty averse pushing with model predictive path integral control. Proceedings of the 2017 IEEE RAS International Conference on Humanoid Robotics, Birmingham, UK.","DOI":"10.1109\/HUMANOIDS.2017.8246918"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","article-title":"Catastrophic forgetting in connectionist networks","volume":"3","author":"French","year":"1999","journal-title":"Trends Cogn. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_27","first-page":"1827","article-title":"Research on Modeling and Experiment of Glass Substrate Peeling Based on Adhesion Theory","volume":"26","author":"Hou","year":"2019","journal-title":"Teh. Vjesn."},{"key":"ref_28","unstructured":"(2022, January 08). Pybullet, a Python Module for Physics Simulation in Robotics, Games and Machine Learning. Available online: https:\/\/github.com\/bulletphysics\/bullet3."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TSMCC.2011.2106494","article-title":"Experience replay for real-time reinforcement learning control","volume":"42","author":"Adam","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. Part C"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/0921-8890(95)00004-Y","article-title":"Lifelong robot learning","volume":"15","author":"Thrun","year":"1995","journal-title":"Robot. Auton. Syst."},{"key":"ref_32","unstructured":"Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., and Bengio, Y. (2013). An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv."},{"key":"ref_33","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 11\u201315). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Hou, L., Wang, H., Zou, H., and Wang, Q. (2021). Efficient Robot Skills Learning with Weighted Near-Optimal Experiences Policy Optimization. Appl. Sci., 11.","DOI":"10.3390\/app11031131"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Theodorou, E., and Todorov, E. (2012, January 10\u201313). Relative entropy and free energy dualities: Connections to Path Integral and KL control. Proceedings of the 51st IEEE Conference on Decision and Control, Maui, HI, USA.","DOI":"10.1109\/CDC.2012.6426381"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1214\/aoms\/1177706645","article-title":"A note on the Generation of Random Normal Deviates","volume":"29","author":"Box","year":"1958","journal-title":"Ann. Math. Stat."},{"key":"ref_37","unstructured":"Janner, M., Fu, J., Zhang, M., and Levine, S. (2019, January 8\u201314). When to trust your model: Model-based policy optimization. Proceedings of the 33rd Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Funabashi, S., Ogasa, S., Isobe, T., Ogata, T., Schmitz, A., Tomo, T.P., and Sugano, S. (2020\u201324, January 25). Variable In-Hand Manipulations for Tactile-Driven Robot Hand via CNN-LSTM. Proceedings of the 2020 International Conference on Intelligent Robots and Systems, Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9341484"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/3\/1292\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:16:15Z","timestamp":1760134575000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/3\/1292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,8]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["s22031292"],"URL":"https:\/\/doi.org\/10.3390\/s22031292","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,8]]}}}