{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T03:24:26Z","timestamp":1774236266748,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030976712","type":"print"},{"value":"9783030976729","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-97672-9_23","type":"book-chapter","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T04:03:10Z","timestamp":1648699390000},"page":"259-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards Autonomous Pipeline Inspection with\u00a0Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Nicol\u00f2","family":"Botteghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luuk","family":"Grefte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mannes","family":"Poel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beril","family":"Sirmacek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Brune","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edwin","family":"Dertien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Stramigioli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,1]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Abdellatif, M., et al.: Mechatronics design of an autonomous pipe-inspection robot. In: MATEC Web of Conferences, EDP Sciences (2018)","DOI":"10.1051\/matecconf\/201815302002"},{"key":"23_CR2","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"issue":"11","key":"23_CR3","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"23_CR4","unstructured":"Nachum, O., et al.: Data-efficient Hierarchical Reinforcement Learning. arXiv preprint arXiv:1805.08296 (2018)"},{"issue":"1\u20132","key":"23_CR5","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"23_CR6","unstructured":"Heess, N., et al.: Learning and transfer of modulated locomotor controllers. arXiv preprint arXiv:1610.05182 (2016)"},{"key":"23_CR7","unstructured":"Florensa, C., Duan, Y., Abbeel, P.: Stochastic neural networks for Hierarchical Reinforcement Learning. arXiv preprint arXiv:1704.03012 (2017)"},{"key":"23_CR8","unstructured":"Frans, K., et al.: Meta learning shared hierarchies. arXiv preprint arXiv:1710.09767 (2017)"},{"key":"23_CR9","unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: International Conference on Machine Learning. PMLR (2017)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Dertien, E., Stramigioli, S., Pulles, K.: Development of an inspection robot for small diameter gas distribution mains. In: 2011 IEEE International Conference on Robotics and Automation. IEEE (2011)","DOI":"10.1109\/ICRA.2011.5980077"},{"key":"23_CR12","unstructured":"Schulman, J., et al.: Proximal policy optimisation algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"23_CR13","unstructured":"Schulman, J., et al.: Trust region policy optimisation. In: International Conference on Machine Learning. PMLR (2015)"},{"key":"23_CR14","unstructured":"Howard, R.A.: Dynamic Probabilistic Systems:@ Semi-Markov and Decision Processes. Wiley, Hoboken (1971)"},{"key":"23_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/3-540-45622-8_16","volume-title":"Abstraction, Reformulation, and Approximation","author":"M Stolle","year":"2002","unstructured":"Stolle, M., Precup, D.: Learning options in reinforcement learning. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS (LNAI), vol. 2371, pp. 212\u2013223. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45622-8_16"},{"issue":"4","key":"23_CR16","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/robotics6040036","volume":"6","author":"GH Mills","year":"2017","unstructured":"Mills, G.H., Jackson, A.E., Richardson, R.C.: Advances in the inspection of unpiggable pipelines. Robotics 6(4), 36 (2017)","journal-title":"Robotics"},{"issue":"1","key":"23_CR17","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/S1462-0758(99)00012-6","volume":"1","author":"E Rome","year":"1999","unstructured":"Rome, E., et al.: Towards autonomous sewer robots: the MAKRO project. Urban Water 1(1), 57\u201370 (1999)","journal-title":"Urban Water"},{"issue":"5","key":"23_CR18","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1016\/S0957-4158(01)00022-8","volume":"12","author":"HR Choi","year":"2002","unstructured":"Choi, H.R., Ryew, S.M.: Robotic system with active steering capability for internal inspection of urban gas pipelines. Mechatronics 12(5), 713\u2013736 (2002)","journal-title":"Mechatronics"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Selvarajan, A., et al.: Design and development of a snake-robot for pipeline inspection. In: 2019 IEEE Student Conference on Research and Development (SCOReD). IEEE (2019)","DOI":"10.1109\/SCORED.2019.8896254"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Debenest, P., Guarnieri, M., Hirose, S.: PipeTron series-Robots for pipe inspection. In: Proceedings of the 2014 3rd International Conference on Applied Robotics for the Power Industry. IEEE (2014)","DOI":"10.1109\/CARPI.2014.7030052"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Nassiraei, A.A., et al.: Concept and design of a fully autonomous sewer pipe inspection mobile robot kantaro. In: Proceedings 2007 IEEE International Conference on Robotics and Automation. IEEE (2007)","DOI":"10.1109\/ROBOT.2007.363777"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Thrun, S.: Probabilistic robotics. In: Communications of the ACM (2002)","DOI":"10.1145\/504729.504754"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Rohmer, E., Singh, S.P., Freese, M.: V-REP: a versatile and scalable robot simulation framework. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696520"},{"key":"23_CR24","unstructured":"James, S., Davison, A.J., Johns, E.: Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task. In: Conference on Robot Learning. PMLR (2017)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Erickson, Z., et al.: Assistive gym: a physics simulation framework for assistive robotics. In: 2020 IEEE International Conference on Robotics and Automation. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"23_CR26","unstructured":"Moritz, P., et al.: Ray: a distributed framework for emerging AI applications. In: 13th USENIX Symposium on Operating Systems Design and Implementation (2018)"},{"key":"23_CR27","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"23_CR28","unstructured":"James, S., Freese, M., Davison, A.J.: Pyrep: bringing v-rep to deep robot learning. arXiv preprint arXiv:1906.11176 (2019)"},{"key":"23_CR29","unstructured":"Matas, J., James, S., Davison, A.J.: Sim-to-real reinforcement learning for deformable object manipulation. In: Conference on Robot Learning. PMLR (2018)"}],"container-title":["Lecture Notes in Networks and Systems","Robot Intelligence Technology and Applications 6"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-97672-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T06:07:49Z","timestamp":1663135669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-97672-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030976712","9783030976729"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-97672-9_23","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 April 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RiTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Robot Intelligence Technology and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rita2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}