{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T12:40:10Z","timestamp":1745152810684,"version":"3.40.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031858581","type":"print"},{"value":"9783031858598","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-85859-8_6","type":"book-chapter","created":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T12:09:16Z","timestamp":1745150956000},"page":"68-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Planning the\u00a0Path with\u00a0Reinforcement Learning: Optimal Robot Motion Planning in\u00a0RoboCup Small Size League Environments"],"prefix":"10.1007","author":[{"given":"Mateus G.","family":"Machado","sequence":"first","affiliation":[]},{"given":"Jo\u00e3o G.","family":"Melo","sequence":"additional","affiliation":[]},{"given":"Cleber","family":"Zanchettin","sequence":"additional","affiliation":[]},{"given":"Pedro H.","family":"Braga","sequence":"additional","affiliation":[]},{"given":"Pedro V.","family":"Cunha","sequence":"additional","affiliation":[]},{"given":"Edna N. S.","family":"Barros","sequence":"additional","affiliation":[]},{"given":"Hansenclever F.","family":"Bassani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"issue":"1","key":"6_CR1","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1109\/TSMC.2018.2834728","volume":"49","author":"RH Abiyev","year":"2018","unstructured":"Abiyev, R.H., Akkaya, N., Gunsel, I.: Control of omnidirectional robot using z-number-based fuzzy system. IEEE Trans. Syst. Man Cybern. Syst. 49(1), 238\u2013252 (2018)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1016\/j.procs.2017.11.286","volume":"120","author":"RH Abiyev","year":"2017","unstructured":"Abiyev, R.H., G\u00fcnsel, I.S., Akkaya, N., Aytac, E., \u00c7a\u011fman, A., Abizada, S.: Fuzzy control of omnidirectional robot. Procedia Comput. Sci. 120, 608\u2013616 (2017)","journal-title":"Procedia Comput. Sci."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Ara\u00fajo, V., et al.: Rob\u00f4cin ssl-unification: a modular software architecture for dynamic multi-robot systems. In: Robot World Cup, pp. 313\u2013324. Springer (2023)","DOI":"10.1007\/978-3-031-55015-7_26"},{"key":"6_CR4","unstructured":"Cruz, J.V.S.: Exploring reinforcement learning in path planning for omnidirectional robotsoccer (2023). https:\/\/repositorio.ufpe.br\/handle\/123456789\/51592"},{"key":"6_CR5","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. CoRR abs\/1604.06778 (2016). http:\/\/arxiv.org\/abs\/1604.06778"},{"key":"6_CR6","unstructured":"Eysenbach, B., Salakhutdinov, R., Levine, S.: Search on the replay buffer: bridging planning and reinforcement learning (2019)"},{"key":"6_CR7","unstructured":"Fang, M., Zhou, C., Shi, B., Gong, B., Xu, J., Zhang, T.: Dher: hindsight experience replay for dynamic goals. In: International Conference on Learning Representations (2018)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: Objectfolder 2.0: a multisensory object dataset for sim2real transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10598\u201310608 (2022)","DOI":"10.1109\/CVPR52688.2022.01034"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gasparetto, A., Boscariol, P., Lanzutti, A., Vidoni, R.: Path planning and trajectory planning algorithms: a general overview, pp. 3\u201327. Springer, Cham (2015)","DOI":"10.1007\/978-3-319-14705-5_1"},{"issue":"4","key":"6_CR10","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TITS.2015.2498841","volume":"17","author":"D Gonz\u00e1lez","year":"2016","unstructured":"Gonz\u00e1lez, D., P\u00e9rez, J., Milan\u00e9s, V., Nashashibi, F.: A review of motion planning techniques for automated vehicles. IEEE Trans. Intell. Transp. Syst. 17(4), 1135\u20131145 (2016). https:\/\/doi.org\/10.1109\/TITS.2015.2498841","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"6_CR11","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. CoRR abs\/1812.05905 (2018). http:\/\/arxiv.org\/abs\/1812.05905"},{"issue":"1","key":"6_CR12","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1109\/TIV.2023.3312777","volume":"9","author":"X Hu","year":"2024","unstructured":"Hu, X., Li, S., Huang, T., Tang, B., Huai, R., Chen, L.: How simulation helps autonomous driving: a survey of sim2real, digital twins, and parallel intelligence. IEEE Trans. Intell. Veh. 9(1), 593\u2013612 (2024). https:\/\/doi.org\/10.1109\/TIV.2023.3312777","journal-title":"IEEE Trans. Intell. Veh."},{"key":"6_CR13","unstructured":"Kaelbling, L.P.: Learning to achieve goals. In: IJCAI, vol.\u00a02, pp. 1094\u20131098. Citeseer (1993)"},{"key":"6_CR14","unstructured":"Kalyanakrishnan, S., et al.: An analysis of frame-skipping in reinforcement learning. CoRR abs\/2102.03718 (2021). https:\/\/arxiv.org\/abs\/2102.03718"},{"key":"6_CR15","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016, Conference Track Proceedings (2016). http:\/\/arxiv.org\/abs\/1509.02971"},{"key":"6_CR16","unstructured":"Mahmood, A.R., Korenkevych, D., Vasan, G., Ma, W., Bergstra, J.: Benchmarking reinforcement learning algorithms on real-world robots. CoRR abs\/1809.07731 (2018). http:\/\/arxiv.org\/abs\/1809.07731"},{"key":"6_CR17","unstructured":"Mankowitz, D.J., et al.: Robust reinforcement learning for continuous control with model misspecification. arXiv preprint arXiv:1906.07516 (2019)"},{"key":"6_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/978-3-030-98682-7_14","volume-title":"RoboCup 2021: Robot World Cup XXIV","author":"FB Martins","year":"2022","unstructured":"Martins, F.B., Machado, M.G., Bassani, H.F., Braga, P., Barros, E.S.: rSoccer: a framework for studying reinforcement learning in small and very small size robot soccer. In: Alami, R., Biswas, J., Cakmak, M., Obst, O. (eds.) RoboCup 2021. LNCS (LNAI), vol. 13132, pp. 165\u2013176. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98682-7_14"},{"key":"6_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR abs\/1312.5602 (2013). http:\/\/arxiv.org\/abs\/1312.5602"},{"key":"6_CR20","unstructured":"Mysore, S., Mabsout, B., Mancuso, R., Saenko, K.: Regularizing action policies for smooth control with reinforcement learning. CoRR abs\/2012.06644 (2020). https:\/\/arxiv.org\/abs\/2012.06644"},{"key":"6_CR21","unstructured":"Nair, A.V., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"6_CR22","unstructured":"Narasimhan, K., et al.: Feudal reinforcement learning. arXiv preprint arXiv:1811.03244 (2018)"},{"key":"6_CR23","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library (2019)"},{"issue":"4","key":"6_CR24","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1080\/00207721.2020.1839142","volume":"52","author":"A Perrusqu\u00eda","year":"2021","unstructured":"Perrusqu\u00eda, A., Yu, W.: Continuous-time reinforcement learning for robust control under worst-case uncertainty. Int. J. Syst. Sci. 52(4), 770\u2013784 (2021)","journal-title":"Int. J. Syst. Sci."},{"key":"6_CR25","unstructured":"Pong, V., Gu, S., Dalal, M., Levine, S.: Temporal difference models: model-free deep RL for model-based control. arXiv preprint arXiv:1802.09081 (2018)"},{"issue":"1","key":"6_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s10846-023-02030-x","volume":"110","author":"M Rahul","year":"2024","unstructured":"Rahul, M., Chiddarwar, S.S.: Deep reinforcement learning with inverse jacobian based model-free path planning for deburring in complex industrial environment. J. Intell. Robot. Syst. 110(1), 4 (2024)","journal-title":"J. Intell. Robot. Syst."},{"key":"6_CR27","unstructured":"Siegwart, R., Nourbakhsh, I.R., Scaramuzza, D.: Introduction to Autonomous Mobile Robots. MIT Press (2011)"},{"key":"6_CR28","unstructured":"Small Size League Technical Committee: Rules of the RoboCup Small Size League 2023. https:\/\/robocup-ssl.github.io\/ssl-rules\/sslrules.pdf"},{"key":"6_CR29","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press (2018)"},{"key":"6_CR30","unstructured":"Sutton, R.S., Precup, D.: Learning multi-level hierarchies with hindsight. In: International Conference on Machine Learning, pp. 861\u2013868 (1998)"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2024: Robot World Cup XXVII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85859-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T12:09:26Z","timestamp":1745150966000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85859-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031858581","9783031858598"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85859-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RoboCup","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Robot World Cup","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Eindhoven","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robocup2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.robocup.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}