{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:38:02Z","timestamp":1791913082187,"version":"4.3.4"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819670291","type":"print"},{"value":"9789819670307","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-7030-7_28","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:38:06Z","timestamp":1750682286000},"page":"403-418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Causality-Aware Transformer Networks for\u00a0Robotic Navigation"],"prefix":"10.1007","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanjiang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"28_CR2","unstructured":"Batra, D., et al.: ObjectNav revisited: on evaluation of embodied agents navigating to objects. arXiv preprint arXiv:2006.13171 (2020)"},{"key":"28_CR3","unstructured":"Blukis, V., Paxton, C., Fox, D., Garg, A., Artzi, Y.: A persistent spatial semantic representation for high-level natural language instruction execution. In: Conference on Robot Learning, pp. 706\u2013717. PMLR (2022)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Deitke, 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)","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"28_CR6","first-page":"5982","volume":"35","author":"M Deitke","year":"2022","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied AI using procedural generation. NeurIPS 35, 5982\u20135994 (2022)","journal-title":"NeurIPS"},{"issue":"2","key":"28_CR7","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: from simulators to research tasks. IEEE Trans. Emerg. Top. Comput. Intell. 6(2), 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"28_CR8","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1613\/jair.1.13646","volume":"74","author":"J Francis","year":"2022","unstructured":"Francis, J., Kitamura, N., Labelle, F., Lu, X., Navarro, I., Oh, J.: Core challenges in embodied vision-language planning. J. Artif. Intell. Res. 74, 459\u2013515 (2022)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR9","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"28_CR10","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)","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"28_CR11","unstructured":"Inoue, Y., Ohashi, H.: Prompter: utilizing large language model prompting for a data efficient embodied instruction following. arXiv preprint arXiv:2211.03267 (2022)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Kareer, S., Yokoyama, N., Batra, D., Ha, S., Truong, J.: ViNL: visual navigation and locomotion over obstacles. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2018\u20132024. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160612"},{"key":"28_CR13","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":"28_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Luo, H., Yue, A., Hong, Z.W., Agrawal, P.: Stubborn: a strong baseline for indoor object navigation. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3287\u20133293. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981646"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Maksymets, O., et al.: THDA: treasure hunt data augmentation for semantic navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15374\u201315383 (2021)","DOI":"10.1109\/ICCV48922.2021.01509"},{"key":"28_CR17","unstructured":"Min, S.Y., Chaplot, D.S., Ravikumar, P., Bisk, Y., Salakhutdinov, R.: Film: following instructions in language with modular methods. arXiv preprint arXiv:2110.07342 (2021)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Morin, S., Saavedra-Ruiz, M., Paull, L.: One-4-all: neural potential fields for embodied navigation. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342302"},{"key":"28_CR19","unstructured":"Moudgil, A., Majumdar, A., Agrawal, H., Lee, S., Batra, D.: SOAT: a scene-and object-aware transformer for vision-and-language navigation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 7357\u20137367 (2021)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Pashevich, A., Schmid, C., Sun, C.: Episodic transformer for vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15942\u201315952 (2021)","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"28_CR21","first-page":"331","volume":"2","author":"ML Puterman","year":"1990","unstructured":"Puterman, M.L.: Markov decision processes. Handb. Oper. Res. Manag. Sci. 2, 331\u2013434 (1990)","journal-title":"Handb. Oper. Res. Manag. Sci."},{"key":"28_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Ramrakhya, R., Batra, D., Wijmans, E., Das, A.: PirlNav: pretraining with imitation and RL finetuning for objectNav. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17896\u201317906 (2023)","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"28_CR24","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5173\u20135183 (2022)","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"28_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"28_CR26","unstructured":"Shah, D., et al.: Vint: a foundation model for visual navigation. arXiv preprint arXiv:2306.14846 (2023)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Shen, B., et\u00a0al.: igibson 1.0: A simulation environment for interactive tasks in large realistic scenes. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7520\u20137527. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Shridhar, M., et al.: Alfred: a benchmark for interpreting grounded instructions for everyday tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10740\u201310749 (2020)","DOI":"10.1109\/CVPR42600.2020.01075"},{"issue":"1\u20132","key":"28_CR29","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1162\/1064546053278973","volume":"11","author":"L Smith","year":"2005","unstructured":"Smith, L., Gasser, M.: The development of embodied cognition: six lessons from babies. Artif. Life 11(1\u20132), 13\u201329 (2005)","journal-title":"Artif. Life"},{"key":"28_CR30","unstructured":"Suglia, A., Gao, Q., Thomason, J., Thattai, G., Sukhatme, G.: Embodied BERT: a transformer model for embodied, language-guided visual task completion. arXiv preprint arXiv:2108.04927 (2021)"},{"key":"28_CR31","unstructured":"Szot, A., et\u00a0al.: Habitat 2.0: Training home assistants to rearrange their habitat. In: Advances in Neural Information Processing Systems, vol. 34, pp. 251\u2013266 (2021)"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. arXiv preprint arXiv:1904.04195 (2019)","DOI":"10.18653\/v1\/N19-1268"},{"key":"28_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Tan, A.H., Nejat, G.: NavFormer: a transformer architecture for robot target-driven navigation in unknown and dynamic environments. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3412638"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Weihs, L., Deitke, M., Kembhavi, A., Mottaghi, R.: Visual room rearrangement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5922\u20135931 (2021)","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"28_CR36","unstructured":"Weihs, L., et al.: Allenact: a framework for embodied AI research. arXiv preprint arXiv:2008.12760 (2020)"},{"key":"28_CR37","unstructured":"Wijmans, E., et al.: DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames. arXiv preprint arXiv:1911.00357 (2019)"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson ENV: real-world perception for embodied agents. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9068\u20139079 (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Ye, J., Batra, D., Das, A., Wijmans, E.: Auxiliary tasks and exploration enable objectgoal navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16117\u201316126 (2021)","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Yu, B., Kasaei, H., Cao, M.: Frontier semantic exploration for visual target navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161059"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chai, J.: Hierarchical task learning from language instructions with unified transformers and self-monitoring. arXiv preprint arXiv:2106.03427 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.368"},{"key":"28_CR42","unstructured":"Zheng, K., et al.: Jarvis: a neuro-symbolic commonsense reasoning framework for conversational embodied agents. arXiv preprint arXiv:2208.13266 (2022)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-7030-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:38:13Z","timestamp":1750682293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-7030-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819670291","9789819670307"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-7030-7_28","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}