{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:31:20Z","timestamp":1774449080128,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031632228","type":"print"},{"value":"9783031632235","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-63223-5_28","type":"book-chapter","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T15:02:36Z","timestamp":1718895756000},"page":"375-388","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["LFENav: LLM-Based Frontiers Exploration for\u00a0Visual Semantic Navigation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4065-6659","authenticated-orcid":false,"given":"Yuhong","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0321-4955","authenticated-orcid":false,"given":"Jianyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9898-5543","authenticated-orcid":false,"given":"Xinhu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"28_CR1","unstructured":"Ramakrishnan, S.K., et al.: Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3D environments for embodied AI (2021)"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Bloom, J., Paliwal, P., Mukherjee, A., Pinciroli, C.: Decentralized multi-agent reinforcement learning with global state prediction. In: The IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8854\u20138861. IEEE, Detroit (2023). https:\/\/doi.org\/10.1109\/IROS55552.2023.10341563","DOI":"10.1109\/IROS55552.2023.10341563"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Ramrakhya, R., Undersander, E., Batra, D., Das, A.: Habitat-web: learning embodied object-search strategies from human demonstrations at scale. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans. IEEE (2022). https:\/\/arxiv.org\/abs\/2204.03514","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Lu, Q., et al.: KEMP: keyframe-based hierarchical end-to-end deep model for long-term trajectory prediction. In: International Conference on Robotics and Automation (ICRA), Philadelphia, pp. 646\u2013652. IEEE (2022). https:\/\/doi.org\/10.1109\/ICRA46639.2022.9812337","DOI":"10.1109\/ICRA46639.2022.9812337"},{"key":"28_CR6","unstructured":"Yadav, K., et al.: OVRL-V2: a simple state-of-art baseline for imagenav and objectnav. CoRR abs\/2303.07798 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.07798"},{"key":"28_CR7","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"28_CR8","unstructured":"Rana, K., Haviland, J., Garg, S., Abou-Chakra, J., Reid, I., Suenderhauf, N.: Sayplan: grounding large language models using 3D scene graphs for scalable robot task planning. In: 7th Annual Conference on Robot Learning (CoRL). Atlanta (2023). https:\/\/openreview.net\/forum?id=wMpOMO0Ss7a"},{"key":"28_CR9","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, A., Salakhutdinov, R.: Object goal navigation using goal-oriented semantic exploration. In: Neural Information Processing Systems (NeurIPS), Virtual, vol.\u00a033, pp. 4247\u20134258. MIT Press (2020). https:\/\/arxiv.org\/pdf\/2007.00643.pdf"},{"key":"28_CR10","doi-asserted-by":"publisher","unstructured":"Zeng, A., Ichter, B., Xia, F., Xiao, T., Sindhwani, V.: Demonstrating large language models on robots. In: Proceedings of Robotics: Science and Systems (RSS). Daegu (2023). https:\/\/doi.org\/10.15607\/RSS.2023.XIX.024","DOI":"10.15607\/RSS.2023.XIX.024"},{"key":"28_CR11","unstructured":"Shah, D., et al.: ViNT: a foundation model for visual navigation. In: 7th Annual Conference on Robot Learning (CoRL), Atlanta (2023). https:\/\/arxiv.org\/abs\/2306.14846"},{"key":"28_CR12","doi-asserted-by":"publisher","unstructured":"Yu, B., Kasaei, H., Cao, M.: L3MVN: leveraging large language models for visual target navigation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, pp. 3554\u20133560. IEEE (2023). https:\/\/doi.org\/10.1109\/IROS55552.2023.10342512","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"28_CR13","doi-asserted-by":"publisher","unstructured":"Yamauchi, B.: A frontier-based approach for autonomous exploration. In: IEEE International Symposium on Computational Intelligence in Robotics and Automation (ICRA), Albuquerque, pp. 146\u2013151. IEEE (1997). https:\/\/doi.org\/10.1109\/CIRA.1997.613851","DOI":"10.1109\/CIRA.1997.613851"},{"key":"28_CR14","doi-asserted-by":"publisher","unstructured":"Xing, W., Song, A., Zhu, L.: Real-time robot path planning using rapid visible tree. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 11182\u201311188 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9560801","DOI":"10.1109\/ICRA48506.2021.9560801"},{"key":"28_CR15","doi-asserted-by":"publisher","unstructured":"Saha, A., Mendez, O., Russell, C., Bowden, R.: Translating images into maps. In: International Conference on Robotics and Automation (ICRA), Philadelphia, pp. 9200\u20139206. IEEE (2022). https:\/\/doi.org\/10.1109\/ICRA46639.2022.9811901","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Memory-based exploration-value evaluation model for visual navigation. In: IEEE International Conference on Robotics and Automation (ICRA), London, pp. 2011\u20132017. IEEE (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160665","DOI":"10.1109\/ICRA48891.2023.10160665"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Jain, K., Chhangani, V., Tiwari, A., Krishna, K.M., Gandhi, V.: Ground then navigate: language-guided navigation in dynamic scenes (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.11972","DOI":"10.1109\/ICRA48891.2023.10160614"},{"key":"28_CR18","doi-asserted-by":"publisher","unstructured":"Singh\u00a0Chaplot, D., Salakhutdinov, R., Gupta, A., Gupta, S.: Neural topological slam for visual navigation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, pp. 12872\u201312881. IEEE (2020).https:\/\/doi.org\/10.1109\/CVPR42600.2020.01289","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"28_CR19","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to explore using active neural slam (2020). https:\/\/doi.org\/10.48550\/arXiv.2004.05155"},{"key":"28_CR20","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans. IEEE (2022). https:\/\/arxiv.org\/pdf\/2201.10029.pdf","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Singh, I., et al.: Progprompt: generating situated robot task plans using large language models. In: IEEE International Conference on Robotics and Automation (ICRA), London, pp. 11523\u201311530. IEEE (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10161317","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"28_CR22","unstructured":"Zhang, J., et al.: Bootstrap your own skills: learning to solve new tasks with large language model guidance. In: 7th Annual Conference on Robot Learning (CoRL). Atlanta (2023). https:\/\/openreview.net\/forum?id=a0mFRgadGO"},{"key":"28_CR23","unstructured":"Shah, D., Equi, M., Osinski, B., Xia, F., Ichter, B., Levine, S.: Navigation with large language models: semantic guesswork as a heuristic for planning (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.10103"},{"key":"28_CR24","unstructured":"Yu, B., Kasaei, H., Cao, M.: Co-NAVGPT: Multi-robot cooperative visual semantic navigation using large language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.07937"},{"key":"28_CR25","unstructured":"Ren, A.Z., et al.: Robots that ask for help: Uncertainty alignment for large language model planners. In: 7th Annual Conference on Robot Learning (CoRL), Atlanta (2023). https:\/\/openreview.net\/forum?id=4ZK8ODNyFXx"},{"key":"28_CR26","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems (NeurIPS), New Orleans, vol.\u00a035, pp. 24824\u201324837. MIT Press (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.11903"},{"issue":"4","key":"28_CR27","first-page":"1591","volume":"93","author":"JA Sethian","year":"1996","unstructured":"Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Appl. Math. 93(4), 1591\u20131595 (1996)","journal-title":"Appl. Math."},{"key":"28_CR28","unstructured":"Chen, W., Hu, S., Talak, R., Carlone, L.: Leveraging large (visual) language models for robot 3d scene understanding (2023). https:\/\/doi.org\/10.48550\/arXiv.2209.05629"},{"key":"28_CR29","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), Venice, pp. 2980\u20132988. IEEE (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"28_CR30","unstructured":"Jiang, J., Zheng, L., Luo, F., Zhang, Z.: RedNet: residual encoder-decoder network for indoor RGB-D semantic segmentation. arXiv preprint arXiv:1806.01054 (2018). https:\/\/doi.org\/10.48550\/arXiv.1806.01054"},{"key":"28_CR31","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019). https:\/\/doi.org\/10.48550\/arXiv.1810.04805"},{"key":"28_CR32","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.11692"},{"key":"28_CR33","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https:\/\/api.semanticscholar.org\/CorpusID:160025533"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Black, S., et al.: Gpt-neox-20b: an open-source autoregressive language model (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06745","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"28_CR35","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-63223-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T15:07:11Z","timestamp":1718896031000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-63223-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031632228","9783031632235"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-63223-5_28","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 June 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Corfu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"27 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}