{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:51:03Z","timestamp":1756993863868,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031222153"},{"type":"electronic","value":"9783031222160"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-22216-0_37","type":"book-chapter","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T04:39:26Z","timestamp":1673930366000},"page":"546-560","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Sensor-Based Navigation Using Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Christopher","family":"Gebauer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Dengler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maren","family":"Bennewitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,18]]},"reference":[{"key":"37_CR1","unstructured":"Anderson, P., Chang, A.X., Chaplot, D.S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., Savva, M., Zamir, A.R.: On Evaluation of Embodied Navigation Agents (2018)"},{"key":"37_CR2","unstructured":"Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B., Tobin, J., Pieter Abbeel, O., Zaremba, W.: Hindsight experience replay. In: Advances in Neural Information Processing Systems (2017)"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the International Conference on Machine Learning (ICML) (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"37_CR4","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: OpenAI Gym (2016)"},{"key":"37_CR5","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, A., Salakhutdinov, R.: Object goal navigation using goal-oriented semantic exploration. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2020)"},{"key":"37_CR6","unstructured":"Coumans, E., Bai, Y.: PyBullet, a Python module for physics simulation for games, robotics and machine learning (2016\u20132019). www.pybullet.org"},{"key":"37_CR7","unstructured":"Dhiman, V., Banerjee, S., Griffin, B., Siskind, J.M., Corso, J.J.: A Critical Investigation of Deep Reinforcement Learning for Navigation (2018)"},{"key":"37_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977","volume-title":"The Dynamic Window Approach to Collision Avoidance","author":"D Fox","year":"1997","unstructured":"Fox, D., Burgard, W., Thrun, S.: The Dynamic Window Approach to Collision Avoidance. Robot. Autom. Mag, IEEE (1997)"},{"key":"37_CR9","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Proceedings of the International Conference on Machine Learning (ICML) (2018)"},{"key":"37_CR10","unstructured":"Gebauer, C., Bennewitz, M.: The Pitfall of More Powerful Autoencoders in Lidar-Based Navigation (2021)"},{"key":"37_CR11","unstructured":"Jaderberg, M., Mnih, V., Czarnecki, W.M., Schaul, T., Leibo, J.Z., Silver, D., Kavukcuoglu, K.: Reinforcement Learning with Unsupervised Auxiliary Tasks. CoRR (2016)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. In: Artificial Intelligence (1998)","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"37_CR13","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (ICLR) (2013)"},{"key":"37_CR14","unstructured":"Kulkarni, T., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"37_CR15","unstructured":"Levy, A., Konidaris, G., Platt, R., Saenko, K.: Learning multi-level hierarchies with hindsight. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"37_CR16","unstructured":"Li, C., Xia, F., Mart\u00edn-Mart\u00edn, R., Savarese, S.: Hrl4in: hierarchical reinforcement learning for interactive navigation with mobile manipulators. In: Proceedings of the Conference on Robot Learning (CoRL) (2020)"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Liu, L., Dugas, D., Cesari, G., Siegwart, R., Dub\u00e9, R.: Robot navigation in crowded environments using deep reinforcement learning. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Macenski, S., Martin, F., White, R., Gin\u00e9s Clavero, J.: The marathon 2: a navigation system. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9341207"},{"key":"37_CR19","unstructured":"Mirowski, P., Pascanu, R., Viola, F., Soyer, H., Ballard, A.J., Banino, A., Denil, M., Goroshin, R., Sifre, L., Kavukcuoglu, K., Kumaran, D., Hadsell, R.: Learning to navigate in complex environments. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Pfeiffer, M., Schaeuble, M., Nieto, J.I., Siegwart, R., Cadena, C.: From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots. CoRR (2016)","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Regier, P., Gesing, L., Bennewitz, M.: Deep reinforcement learning for navigation in cluttered environments. Proceedings of the International Conference on Machine Learning and Applications (CMLA) (2020)","DOI":"10.5121\/csit.2020.101117"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Savitzky, A., Golay, M.J.E.: Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry (1964)","DOI":"10.1021\/ac60214a047"},{"key":"37_CR23","unstructured":"Sax, A., Zhang, J.O., Emi, B., Zamir, A.R., Guibas, L.J., Savarese, S., Malik, J.: Learning to navigate using mid-level visual priors. In: Proceedings of the Conference on Robot Learning (CoRL) (2019)"},{"key":"37_CR24","unstructured":"Stein, G.J., Bradley, C., Roy, N.: Learning over subgoals for efficient navigation of structured, unknown environments. In: Proceedings of the Conference on Robot Learning (CoRL) (2018)"},{"key":"37_CR25","unstructured":"Sutton, R.: The Bitter Lesson (2019). www.incompleteideas.net\/IncIdeas\/BitterLesson.html"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Tai, L., Paolo, G., Liu, M.: Virtual-to-real deep reinforcement learning: continuous control of mobile robots for mapless navigation. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017)","DOI":"10.1109\/IROS.2017.8202134"},{"key":"37_CR27","unstructured":"Vezhnevets, A.S., Osindero, S., Schaul, T., Heess, N., Jaderberg, M., Silver, D., Kavukcuoglu, K.: FeUdal networks for hierarchical reinforcement learning. In: Proceedings of the International Conference on Machine Learning (ICML) (2017)"},{"key":"37_CR28","unstructured":"Wahid, A., Stone, A., Chen, K., Ichter, B., Toshev, A.: Learning Object-Conditioned Exploration Using Distributed Soft Actor Critic (2020)"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Autonomous Systems 17"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22216-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T04:49:22Z","timestamp":1673930962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22216-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031222153","9783031222160"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22216-0_37","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Autonomous Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zagreb","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Croatia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ias2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ias-17.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}