{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T15:13:19Z","timestamp":1762096399816,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819983902"},{"type":"electronic","value":"9789819983919"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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\/978-981-99-8391-9_29","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T16:02:21Z","timestamp":1701014541000},"page":"363-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Toward a\u00a0Unified Framework for\u00a0RGB and\u00a0RGB-D Visual Navigation"],"prefix":"10.1007","author":[{"given":"Heming","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv preprint arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"29_CR2","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"issue":"8","key":"29_CR3","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"29_CR4","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ehsani, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Learning to learn how to learn: self-adaptive visual navigation using meta-learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6750\u20136759 (2019)","DOI":"10.1109\/CVPR.2019.00691"},{"key":"29_CR6","unstructured":"Kolve, E., et al.: AI2-THOR: an interactive 3D environment for visual AI. arXiv (2017)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Oriolo, G., Vendittelli, M., Ulivi, G.: On-line map building and navigation for autonomous mobile robots. In: Proceedings of 1995 IEEE International Conference on Robotics and Automation, vol. 3, pp. 2900\u20132906. IEEE (1995)","DOI":"10.1109\/ROBOT.1995.525695"},{"key":"29_CR8","unstructured":"Kortenkamp, D., Weymouth, T.: Topological mapping for mobile robots using a combination of sonar and vision sensing. In: AAAI, vol. 94, pp. 979\u2013984 (1994)"},{"issue":"5","key":"29_CR9","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/21.44033","volume":"19","author":"J Borenstein","year":"1989","unstructured":"Borenstein, J., Koren, Y.: Real-time obstacle avoidance for fast mobile robots. IEEE Trans. Syst. Man Cybern. 19(5), 1179\u20131187 (1989)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"3","key":"29_CR10","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1109\/70.88137","volume":"7","author":"J Borenstein","year":"1991","unstructured":"Borenstein, J., Koren, Y.: The vector field histogram-fast obstacle avoidance for mobile robots. IEEE Trans. Robot. Autom. 7(3), 278\u2013288 (1991)","journal-title":"IEEE Trans. Robot. Autom."},{"issue":"3","key":"29_CR11","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/70.938381","volume":"17","author":"MG Dissanayake","year":"2001","unstructured":"Dissanayake, M.G., Newman, P., Clark, S., Durrant-Whyte, H.F., Csorba, M.: A solution to the simultaneous localization and map building (SLAM) problem. IEEE Trans. Robot. Autom. 17(3), 229\u2013241 (2001)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2017)","DOI":"10.1109\/CVPR.2017.769"},{"key":"29_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"29_CR15","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673 (2016)"},{"key":"29_CR16","unstructured":"Chen, T., Gupta, S., Gupta, A.: Learning exploration policies for navigation. arXiv preprint arXiv:1903.01959 (2019)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Fang, K., Toshev, A., Fei-Fei, L., Savarese, S.: Scene memory transformer for embodied agents in long-horizon tasks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 538\u2013547 (2019)","DOI":"10.1109\/CVPR.2019.00063"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Sepulveda, G., Niebles, J.C., Soto, A.: A deep learning based behavioral approach to indoor autonomous navigation. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4646\u20134653. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460646"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: A behavioral approach to visual navigation with graph localization networks. arXiv preprint arXiv:1903.00445 (2019)","DOI":"10.15607\/RSS.2019.XV.010"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13137\u201313146 (2020)","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"29_CR21","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. 1\u20138. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wu, Y., Tamar, A., Russell, S., Gkioxari, G., Tian, Y.: Bayesian relational memory for semantic visual navigation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2769\u20132779 (2019)","DOI":"10.1109\/ICCV.2019.00286"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Shen, W.B., Xu, D., Zhu, Y., Guibas, L.J., Fei-Fei, L., Savarese, S.: Situational fusion of visual representation for visual navigation. arXiv preprint arXiv:1908.09073 (2019)","DOI":"10.1109\/ICCV.2019.00297"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 3357\u20133364. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"29_CR25","unstructured":"Yang, W., Wang, X., Farhadi, A., Gupta, A., Mottaghi, R.: Visual semantic navigation using scene priors. arXiv preprint arXiv:1810.06543 (2018)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Toshev, A., Fi\u0161er, M., Ko\u0161eck\u00e1, J., Wahid, A., Davidson, J.: Visual representations for semantic target driven navigation. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8846\u20138852. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Du, H., Yu, X., Zheng, L.: Learning object relation graph and tentative policy for visual navigation. arXiv preprint arXiv:2007.11018 (2020)","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, S., Song, X., Bai, Y., Li, W., Chu, Y., Jiang, S.: Hierarchical object-to-zone graph for object navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15130\u201315140 (2021)","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"29_CR29","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)","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"29_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. arXiv preprint arXiv:2101.01169 (2021)","DOI":"10.1145\/3505244"},{"key":"29_CR33","unstructured":"Song, H., et al.: ViDT: an efficient and effective fully transformer-based object detector. arXiv preprint arXiv:2110.03921 (2021)"},{"key":"29_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["Lecture Notes in Computer Science","AI 2023: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8391-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T10:43:15Z","timestamp":1730630595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8391-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819983902","9789819983919"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8391-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brisbane, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"213","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}