{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:30:48Z","timestamp":1760711448402,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781124"},{"type":"electronic","value":"9783031781131"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78113-1_10","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:02:33Z","timestamp":1733245353000},"page":"135-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reliable Semantic Understanding for\u00a0Real World Zero-Shot Object Goal Navigation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4368-5172","authenticated-orcid":false,"given":"Halil Utku","family":"Unlu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-7966","authenticated-orcid":false,"given":"Shuaihang","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6448-003X","authenticated-orcid":false,"given":"Congcong","family":"Wen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9131-5854","authenticated-orcid":false,"given":"Hao","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3709-2810","authenticated-orcid":false,"given":"Anthony","family":"Tzes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-3883","authenticated-orcid":false,"given":"Yi","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Al-Halah, Z., Ramakrishnan, S.K., Grauman, K.: Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17031\u201317041 (2022)","key":"10_CR1","DOI":"10.1109\/CVPR52688.2022.01652"},{"unstructured":"Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to Explore using Active Neural SLAM. arXiv preprint arXiv:2004.05155 (2020)","key":"10_CR2"},{"key":"10_CR3","first-page":"4247","volume":"33","author":"DS Chaplot","year":"2020","unstructured":"Chaplot, D.S., Gandhi, D.P., Gupta, A., Salakhutdinov, R.R.: Object Goal Navigation using Goal-Oriented Semantic Exploration. Adv. Neural. Inf. Process. Syst. 33, 4247\u20134258 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR4","first-page":"38149","volume":"35","author":"P Chen","year":"2022","unstructured":"Chen, P., Ji, D., Lin, K., Zeng, R., Li, T., Tan, M., Gan, C.: Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation. Adv. Neural. Inf. Process. Syst. 35, 38149\u201338161 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Deitke, M., Han, W., Herrasti, A., Kembhavi, A., Kolve, E., Mottaghi, R., Salvador, J., Schwenk, D., VanderBilt, E., Wallingford, M., et\u00a0al.: RoboTHOR: An Open Simulation-to-Real Embodied AI Platform. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3164\u20133174 (2020)","key":"10_CR5","DOI":"10.1109\/CVPR42600.2020.00323"},{"doi-asserted-by":"crossref","unstructured":"Dorbala, V.S., Mullen\u00a0Jr, J.F., Manocha, D.: Can an Embodied Agent Find Your \u201cCat-shaped Mug\u201d? LLM-Guided Exploration for Zero-Shot Object Navigation. arXiv preprint arXiv:2303.03480 (2023)","key":"10_CR6","DOI":"10.1109\/LRA.2023.3346800"},{"unstructured":"Gadre, S.Y., Wortsman, M., Ilharco, G., Schmidt, L., Song, S.: CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration. arXiv preprint arXiv:2203.104213(4), 7 (2022)","key":"10_CR7"},{"doi-asserted-by":"crossref","unstructured":"Gadre, S.Y., Wortsman, M., Ilharco, G., Schmidt, L., Song, S.: CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 23171\u201323181 (2023)","key":"10_CR8","DOI":"10.1109\/CVPR52729.2023.02219"},{"doi-asserted-by":"crossref","unstructured":"Huang, C., Mees, O., Zeng, A., Burgard, W.: Visual Language Maps for Robot Navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 10608\u201310615. IEEE (2023)","key":"10_CR9","DOI":"10.1109\/ICRA48891.2023.10160969"},{"doi-asserted-by":"crossref","unstructured":"Kahn, G., Villaflor, A., Ding, B., Abbeel, P., Levine, S.: Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation. In: 2018 IEEE international conference on robotics and automation (ICRA). pp. 5129\u20135136. IEEE (2018)","key":"10_CR10","DOI":"10.1109\/ICRA.2018.8460655"},{"doi-asserted-by":"crossref","unstructured":"Karnan, H., Warnell, G., Xiao, X., Stone, P.: VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation. In: 2022 International Conference on Robotics and Automation (ICRA). pp. 2497\u20132503. IEEE (2022)","key":"10_CR11","DOI":"10.1109\/ICRA46639.2022.9812316"},{"doi-asserted-by":"crossref","unstructured":"Khandelwal, A., Weihs, L., Mottaghi, R., Kembhavi, A.: Simple but Effective: CLIP Embeddings for Embodied AI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14829\u201314838 (2022)","key":"10_CR12","DOI":"10.1109\/CVPR52688.2022.01441"},{"doi-asserted-by":"crossref","unstructured":"Komorowski, J.: MinkLoc3D: Point Cloud Based Large-Scale Place Recognition . In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1790\u20131799 (2021)","key":"10_CR13","DOI":"10.1109\/WACV48630.2021.00183"},{"issue":"2","key":"10_CR14","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1002\/rob.21831","volume":"36","author":"M Labb\u00e9","year":"2019","unstructured":"Labb\u00e9, M., Michaud, F.: RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation. Journal of field robotics 36(2), 416\u2013446 (2019)","journal-title":"Journal of field robotics"},{"doi-asserted-by":"crossref","unstructured":"Li*, L.H., Zhang*, P., Zhang*, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J.N., Chang, K.W., Gao, J.: Grounded Language-Image Pre-training. In: CVPR (2022)","key":"10_CR15","DOI":"10.1109\/CVPR52688.2022.01069"},{"doi-asserted-by":"crossref","unstructured":"Macenski, S., Martin, F., White, R., Gin\u00e9s\u00a0Clavero, J.: The Marathon 2: A Navigation System. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","key":"10_CR16","DOI":"10.1109\/IROS45743.2020.9341207"},{"key":"10_CR17","first-page":"32340","volume":"35","author":"A Majumdar","year":"2022","unstructured":"Majumdar, A., Aggarwal, G., Devnani, B., Hoffman, J., Batra, D.: ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings. Adv. Neural. Inf. Process. Syst. 35, 32340\u201332352 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Chaplot, D.S., Al-Halah, Z., Malik, J., Grauman, K.: PONI: Potential Functions for ObjectGoal Navigation With Interaction-Free Learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18890\u201318900 (2022)","key":"10_CR18","DOI":"10.1109\/CVPR52688.2022.01832"},{"unstructured":"Shah, D., Equi, M.R., Osi\u0144ski, B., Xia, F., Ichter, B., Levine, S.: Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning. In: Conference on Robot Learning. pp. 2683\u20132699. PMLR (2023)","key":"10_CR19"},{"doi-asserted-by":"crossref","unstructured":"Silver, D., Bagnell, J., Stentz, A.: High Performance Outdoor Navigation from Overhead Data using Imitation Learning. Robotics: Science and Systems IV, Zurich, Switzerland 1 (2008)","key":"10_CR20","DOI":"10.15607\/RSS.2008.IV.034"},{"issue":"3","key":"10_CR21","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s10846-023-01835-0","volume":"108","author":"HU Unlu","year":"2023","unstructured":"Unlu, H.U., Chaikalis, D., Tsoukalas, A., Tzes, A.: UAV Indoor Exploration for Fire-Target Detection and Extinguishing. Journal of Intelligent & Robotic Systems 108(3), 54 (2023)","journal-title":"Journal of Intelligent & Robotic Systems"},{"doi-asserted-by":"crossref","unstructured":"W\u00f6hlke, J., Schmitt, F., van Hoof, H.: Hierarchies of Planning and Reinforcement Learning for Robot Navigation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA). pp. 10682\u201310688. IEEE (2021)","key":"10_CR22","DOI":"10.1109\/ICRA48506.2021.9561151"},{"doi-asserted-by":"crossref","unstructured":"Xia, Y., Shi, L., Ding, Z., Henriques, J.F., Cremers, D.: Text2Loc: 3D Point Cloud Localization from Natural Language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14958\u201314967 (2024)","key":"10_CR23","DOI":"10.1109\/CVPR52733.2024.01417"},{"unstructured":"Yamauchi, B.: A Frontier-Based Approach for Autonomous Exploration. In: Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA\u201997.\u2019Towards New Computational Principles for Robotics and Automation\u2019. pp. 146\u2013151. IEEE (1997)","key":"10_CR24"},{"unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., Cao, Y.: ReAct: Synergizing Reasoning and Acting in Language Models. arXiv preprint arXiv:2210.03629 (2022)","key":"10_CR25"},{"issue":"3","key":"10_CR26","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1145\/357994.358023","volume":"27","author":"TY Zhang","year":"1984","unstructured":"Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27(3), 236\u2013239 (1984)","journal-title":"Commun. ACM"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zhang, L., He, B., Liu, Z.: Semantic Policy Network for Zero-Shot Object Goal Visual Navigation. IEEE Robotics and Automation Letters (2023)","key":"10_CR27","DOI":"10.1109\/ICRA48891.2023.10161289"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zhang, L., He, B., Qiao, H., Liu, Z.: Zero-Shot Object Goal Visual Navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 2025\u20132031. IEEE (2023)","key":"10_CR28","DOI":"10.1109\/ICRA48891.2023.10161289"},{"unstructured":"Zheng, K., Zhou, K., Gu, J., Fan, Y., Wang, J., Di, Z., He, X., Wang, X.E.: JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents. arXiv preprint arXiv:2208.13266 (2022)","key":"10_CR29"},{"doi-asserted-by":"crossref","unstructured":"Zhou, G., Hong, Y., Wu, Q.: NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models. arXiv preprint arXiv:2305.16986 (2023)","key":"10_CR30","DOI":"10.1609\/aaai.v38i7.28597"},{"unstructured":"Zhou, K., Zheng, K., Pryor, C., Shen, Y., Jin, H., Getoor, L., Wang, X.E.: ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation. In: International Conference on Machine Learning. pp. 42829\u201342842. PMLR (2023)","key":"10_CR31"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:05:14Z","timestamp":1733245514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}