{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T09:09:33Z","timestamp":1779008973082,"version":"3.51.4"},"reference-count":44,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:p>Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional policy networks struggle to process full-resolution LIDAR inputs, forcing prior works to rely on simplified observations that reduce spatial awareness and navigation robustness. This paper presents a novel model-based RL framework built on top of the DreamerV3 algorithm, integrating a Multi-Layer Perceptron Variational Autoencoder (MLP-VAE) within a world model to encode high-dimensional LIDAR readings into compact latent representations. These latent features, combined with a learned dynamics predictor, enable efficient imagination-based policy optimization. Experiments on simulated TurtleBot3 navigation tasks demonstrate that the proposed architecture achieves faster convergence and higher success rate compared to model-free baselines such as SAC, DDPG, and TD3. It is worth emphasizing that the DreamerV3-based agent attains a 100% success rate across all evaluated environments when using the full dataset of the Turtlebot3 LIDAR (360 readings), while model-free methods plateaued below 85%. These findings demonstrate that integrating predictive world models with learned latent representations enables more efficient and robust navigation from high-dimensional sensory data.<\/jats:p>","DOI":"10.1177\/18758967251399741","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T16:44:11Z","timestamp":1764607451000},"page":"1998-2014","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations"],"prefix":"10.1177","volume":"50","author":[{"given":"Raul","family":"Steinmetz","sequence":"first","affiliation":[{"name":"Universidade Federal de Santa Maria"},{"name":"University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Demo Rosa","sequence":"additional","affiliation":[{"name":"Universidade Federal de Santa Maria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Augusto Kich","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jair","family":"Augusto Bottega","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricardo","family":"Bedin Grando","sequence":"additional","affiliation":[{"name":"Universidade Federal de Rio Grande"},{"name":"Universidad Tecnol\u00f3gica del Uruguay, Montevideo, Uruguay"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4714-7849","authenticated-orcid":false,"given":"Daniel Fernando","family":"Tello Gamarra","sequence":"additional","affiliation":[{"name":"Universidade Federal de Santa Maria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2025.3550137"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1556\/1848.2022.00420"},{"key":"e_1_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Anas H. Ong W. H. Malik O. A. (2021). Comparison of deep q-learning q-learning and sarsa reinforced learning for robot local navigation. In International conference on robot intelligence technology and applications (pp. 443\u2013454). Springer.","DOI":"10.1007\/978-3-030-97672-9_40"},{"key":"e_1_3_2_5_1","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp F.","year":"2017","unstructured":"Berkenkamp F., Turchetta M., Schoellig A., Krause A. (2017). Safe model-based reinforcement learning with stability guarantees. Advances in Neural Information Processing Systems, 30, 908\u2013918.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01367-5"},{"key":"e_1_3_2_7_1","doi-asserted-by":"crossref","unstructured":"de Moraes L. D. Kich V. A. Kolling A. H. Bottega J. A. Steinmetz R. da Silva E. C. Grando R. Cuckla A. R. Gamarra D.\u00a0F.\u00a0T. (2022). Double deep reinforcement learning techniques for low dimensional sensing mapless navigation of terrestrial mobile robots. In International conference on intelligent systems design and applications (pp. 156\u2013165). Springer.","DOI":"10.1007\/978-3-031-35507-3_16"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125204"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13127202"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008954632763"},{"key":"e_1_3_2_11_1","unstructured":"Fujimoto S. Hoof H. Meger D. (2018). Addressing function approximation error in actor-critic methods. In International conference on machine learning (pp. 1587\u20131596). PMLR."},{"key":"e_1_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Grando R. B. de Jesus J. C. Kich V. A. Kolling A. H. Pinheiro P. M. Guerra R. S. Drews P. L. (2022). Deterministic and stochastic analysis of deep reinforcement learning for low dimensional sensing-based navigation of mobile robots. In 2022 Latin american robotics symposium (LARS) 2022 Brazilian Symposium on Robotics (SBR) and 2022 workshop on robotics in education (WRE) (pp. 193\u2013198). IEEE.","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995792"},{"key":"e_1_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Grassi R. Rea P. Ottaviano E. Maggiore P. (2018). Application of an inspection robot composed by collaborative terrestrial and aerial modules for an operation in agriculture. In Advances in service and industrial robotics: Proceedings of the 26th International conference on robotics in alpe-adria-danube region RAAD 2017 (pp. 539\u2013546). Springer.","DOI":"10.1007\/978-3-319-61276-8_56"},{"key":"e_1_3_2_14_1","unstructured":"Ha D. Schmidhuber J. (2018). World models. arXiv preprint arXiv:1803.10122."},{"key":"e_1_3_2_15_1","unstructured":"Haarnoja T. Zhou A. Abbeel P. Levine S. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning (pp. 1861\u20131870). PMLR."},{"key":"e_1_3_2_16_1","unstructured":"Hafner D. Lillicrap T. Ba J. Norouzi M. (2019). Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603."},{"key":"e_1_3_2_17_1","unstructured":"Hafner D. Lillicrap T. Norouzi M. Ba J. (2020). Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193."},{"key":"e_1_3_2_18_1","unstructured":"Hafner D. Pasukonis J. Ba J. Lillicrap T. (2023). Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104."},{"key":"e_1_3_2_19_1","unstructured":"Hansen N. Su H. Wang X. (2023). Td-mpc2: Scalable robust world models for continuous control. arXiv preprint arXiv:2310.16828."},{"key":"e_1_3_2_20_1","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner M.","year":"2019","unstructured":"Janner M., Fu J., Zhang M., Levine S. (2019). When to trust your model: Model-based policy optimization. Advances in Neural Information Processing Systems, 32, 12519\u201312530.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.31436\/iiumej.v25i2.3188"},{"key":"e_1_3_2_22_1","unstructured":"Kaiser L. Babaeizadeh M. Milos P. Osinski B. Campbell R. H. Czechowski K. Erhan D. Finn C. Kozakowski P. Levine S. Mohiuddin A. Sepassi R. Tucker G. Michalewski H. (2019). Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374."},{"key":"e_1_3_2_23_1","unstructured":"Keith R. La H. M. (2024). Review of autonomous mobile robots for the warehouse environment. arXiv preprint arXiv:2406.08333."},{"issue":"4","key":"e_1_3_2_24_1","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.18280\/jesa.570408","article-title":"Improved trajectory planning of mobile robot based on pelican optimization algorithm","volume":"57","author":"Khaleel R. Z.","year":"2024","unstructured":"Khaleel R. Z., Khaleel H. Z., Abdullah Al-Hareeri A. A., Mahdi Al-Obaidi A. S., Humaidi A. J. (2024). Improved trajectory planning of mobile robot based on pelican optimization algorithm. Journal Europ\u00e9en des Syst\u00e8mes Automatis\u00e9s, 57(4), 1005\u20131013.","journal-title":"Journal Europ\u00e9en des Syst\u00e8mes Automatis\u00e9s"},{"key":"e_1_3_2_25_1","unstructured":"Kingma D. P. Welling M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114."},{"key":"e_1_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Li P. Wang Y. Gao Z. (2022). Path planning of mobile robot based on improved td3 algorithm. In 2022 IEEE International conference on mechatronics and automation (ICMA) (pp. 715\u2013720). IEEE.","DOI":"10.1109\/ICMA54519.2022.9856399"},{"key":"e_1_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Li X. Shang W. Cong S. (2020). Model-based reinforcement learning for robot control. In 2020 5th International conference on advanced robotics and mechatronics (ICARM) (pp. 300\u2013305). IEEE.","DOI":"10.1109\/ICARM49381.2020.9195341"},{"key":"e_1_3_2_28_1","unstructured":"Lillicrap T. P. Hunt J. J. Pritzel A. Heess N. Erez T. Tassa Y. Silver D. Wierstra D. (2016). Continuous control with deep reinforcement learning. In ICLR. PMLR."},{"key":"e_1_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Martinez C. J. M. Salguero R. C. Palomares R. Cornejo J. (2020). Mechatronics development of terrestrial mobile robot for exploring and monitoring environmental parameters at mine analogue sites using iot platform. In 2020 IEEE XXVII International conference on electronics electrical engineering and computing (INTERCON) (pp. 1\u20134). IEEE.","DOI":"10.1109\/INTERCON50315.2020.9220227"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-85810-9"},{"key":"e_1_3_2_32_1","unstructured":"NVIDIA Corporation (2025a) Nvidia jetson agx xavier. Retrieved October 13 2025 from https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-agx-xavier\/."},{"key":"e_1_3_2_33_1","unstructured":"NVIDIA Corporation (2025b) Nvidia jetson nano developer kit. Retrieved October 13 2025 from https:\/\/developer.nvidia.com\/embedded\/jetson-nano."},{"key":"e_1_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Prakash B. Horton M. Waytowich N. R. Hairston W. D. Oates T. Mohsenin T. (2019). On the use of deep autoencoders for efficient embedded reinforcement learning. In Proceedings of the 2019 on great lakes symposium on VLSI (pp. 507\u2013512).","DOI":"10.1145\/3299874.3319493"},{"key":"e_1_3_2_35_1","unstructured":"ROBOTIS (2017) TurtleBot3. Retrieved October 13 2025 from https:\/\/www.robotis.us\/turtlebot-3\/."},{"key":"e_1_3_2_36_1","first-page":"189","article-title":"Robot mobility systems for planetary surface exploration\u2013state-of-the-art and future outlook: A literature survey","volume":"492","author":"Seeni A.","year":"2010","unstructured":"Seeni A., Sch\u00e4fer B., Hirzinger G. (2010). Robot mobility systems for planetary surface exploration\u2013state-of-the-art and future outlook: A literature survey. Aerospace Technologies Advancements, 492, 189\u2013208.","journal-title":"Aerospace Technologies Advancements"},{"key":"e_1_3_2_37_1","unstructured":"Stooke A. Lee K. Abbeel P. Laskin M. (2021). Decoupling representation learning from reinforcement learning. In International conference on machine learning (pp. 9870\u20139879). PMLR."},{"key":"e_1_3_2_38_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"Sutton R. S., Barto A. G. (2018). Reinforcement Learning: An Introduction. MIT press."},{"key":"e_1_3_2_39_1","unstructured":"Thomas D. (2024). Changes between ros 1 and ros 2. Retrieved July 14 2025 from https:\/\/design.ros2.org\/articles\/changes.html."},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"key":"e_1_3_2_41_1","unstructured":"Wu P. Escontrela A. Hafner D. Abbeel P. Goldberg K. (2023). Daydreamer: World models for physical robot learning. In Conference on robot learning (pp. 2226\u20132240). PMLR."},{"key":"e_1_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1177\/14644193241243158"},{"key":"e_1_3_2_43_1","unstructured":"Zhang A. McAllister R. Calandra R. Gal Y. Levine S. (2020). Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742."},{"key":"e_1_3_2_44_1","first-page":"48203","article-title":"Taco: Temporal latent action-driven contrastive loss for visual reinforcement learning","volume":"36","author":"Zheng R.","year":"2024","unstructured":"Zheng R., Wang X., Sun Y., Ma S., Zhao J., Xu H., Daum\u00e9 I. I. I. H., Huang F. (2024). Taco: Temporal latent action-driven contrastive loss for visual reinforcement learning. Advances in Neural Information Processing Systems, 36, 48203\u201348225.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251399741","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18758967251399741","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251399741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T08:31:46Z","timestamp":1779006706000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18758967251399741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1177\/18758967251399741"],"URL":"https:\/\/doi.org\/10.1177\/18758967251399741","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}