{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:34:11Z","timestamp":1771893251070,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803084"],"award-info":[{"award-number":["61803084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10489-024-05323-2","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T07:02:38Z","timestamp":1719471758000},"page":"8442-8453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DGMem: learning visual navigation policy without any labels by dynamic graph memory"],"prefix":"10.1007","volume":"54","author":[{"given":"Wenzhe","family":"Cai","sequence":"first","affiliation":[]},{"given":"Teng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guangran","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Lele","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"5323_CR1","doi-asserted-by":"crossref","unstructured":"LaValle SM (2006) Planning algorithms","DOI":"10.1017\/CBO9780511546877"},{"key":"5323_CR2","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1145\/504729.504754","volume":"45","author":"S Thrun","year":"2002","unstructured":"Thrun S (2002) Probabilistic robotics. Commun ACM 45:52\u201357","journal-title":"Commun ACM"},{"key":"5323_CR3","first-page":"41","volume":"15","author":"BP Wrobel","year":"2001","unstructured":"Wrobel BP (2001) Multiple view geometry in computer vision. K\u00fcnstliche Intell 15:41","journal-title":"K\u00fcnstliche Intell"},{"key":"5323_CR4","unstructured":"Wijmans E, Kadian A, Morcos AS, Lee S, Essa I, Parikh D, Savva M, Batra D (2020) Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames. In: ICLR"},{"key":"5323_CR5","unstructured":"Datta S, Maksymets O, Hoffman J, Lee S, Batra D, Parikh D (2020) Integrating egocentric localization for more realistic point-goal navigation agents. In: Conference on Robot Learning"},{"key":"5323_CR6","unstructured":"Du H, Yu X, Zheng L (2021) {VTN}et: Visual transformer network for object goal navigation. In: International Conference on Learning Representations"},{"key":"5323_CR7","unstructured":"Pal A, Qiu Y, Christensen HI (2020) Learning hierarchical relationships for object-goal navigation. In: Conference on Robot Learning"},{"key":"5323_CR8","first-page":"2769","volume":"2019","author":"Y Wu","year":"2019","unstructured":"Wu Y, Wu Y, Tamar A, Russell SJ, Gkioxari G, Tian Y (2019) Bayesian relational memory for semantic visual navigation. IEEE\/CVF International Conference on Computer Vision (ICCV) 2019:2769\u20132779","journal-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"5323_CR9","first-page":"513","volume":"2020","author":"M Narasimhan","year":"2020","unstructured":"Narasimhan M, Wijmans E, Chen X, Darrell T, Batra D, Parikh D, Singh A (2020) Seeing the un-scene: Learning amodal semantic maps for room navigation. Computer Vision - ECCV 2020:513\u2013529","journal-title":"Computer Vision - ECCV"},{"key":"5323_CR10","first-page":"3357","volume":"2017","author":"Y Zhu","year":"2016","unstructured":"Zhu Y, Mottaghi R, Kolve E, Lim JJ, Gupta AK, Fei-Fei L, Farhadi A (2016) Target-driven visual navigation in indoor scenes using deep reinforcement learning. IEEE International Conference on Robotics and Automation (ICRA) 2017:3357\u20133364","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"5323_CR11","doi-asserted-by":"crossref","unstructured":"Choi Y, Oh S (2021) Image-goal navigation via keypoint-based reinforcement learning. 2021 18th International Conference on Ubiquitous Robots (UR), 18\u201321","DOI":"10.1109\/UR52253.2021.9494664"},{"key":"5323_CR12","first-page":"8451","volume":"2021","author":"H Wang","year":"2021","unstructured":"Wang H, Wang W, Liang W, Xiong C, Shen J (2021) Structured scene memory for vision-language navigation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021:8451\u20138460","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"5323_CR13","unstructured":"Chen C, Majumder S, Al-Halah Z, Gao R, Ramakrishnan SK, Grauman K (2021) Learning to set waypoints for audio-visual navigation. In: International Conference on Learning Representations"},{"key":"5323_CR14","first-page":"5163","volume":"2022","author":"R Ramrakhya","year":"2022","unstructured":"Ramrakhya R, Undersander E, Batra D, Das A (2022) Habitat-web: Learning embodied object-search strategies from human demonstrations at scale. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022:5163\u20135173","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"5323_CR15","unstructured":"Kolve E, Mottaghi R, Han W, VanderBilt E, Weihs L, Herrasti A, Deitke M, Ehsani K, Gordon D, Zhu Y, Kembhavi A, Gupta AK, Farhadi A (2017) Ai2-thor: An interactive 3d environment for visual ai. arXiv:1712.05474"},{"key":"5323_CR16","doi-asserted-by":"crossref","unstructured":"Savva M, Kadian A, Maksymets O, Zhao Y, Wijmans E, Jain B, Straub J, Liu J, Koltun V, Malik J, Parikh D, Batra D (2019) Habitat: A platform for embodied ai research. IEEE\/CVF International Conference on Computer Vision (ICCV) 2019:9338\u20139346","DOI":"10.1109\/ICCV.2019.00943"},{"key":"5323_CR17","unstructured":"Szot A, Clegg A, Undersander E, Wijmans E, Zhao Y, Turner JM, Maestre ND, Mukadam M, Chaplot DS, Maksymets O, Gokaslan A, Vondru\u0161 V, Dharur S, Meier F, Galuba W, Chang AX, Kira Z, Koltun V, Malik J, Savva M, Batra D (2021) Habitat 2.0: Training home assistants to rearrange their habitat. In: Beygelzimer A, Dauphin Y, Liang P, Vaughan JW (eds) Advances in Neural Information Processing Systems"},{"key":"5323_CR18","doi-asserted-by":"crossref","unstructured":"Shen B, Xia F, Li C, Mart\u2019in-Mart\u2019in R, Fan LJ, Wang G, Buch S, D\u2019Arpino CP, Srivastava S, Tchapmi LP, Tchapmi M, Vainio K, Fei-Fei L, Savarese S (2020) igibson 1.0: A simulation environment for interactive tasks in large realistic scenes. 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 7520\u20137527","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"5323_CR19","unstructured":"Li C, Xia F, Mart\u00edn-Mart\u00edn R, Lingelbach M, Srivastava S, Shen B, Vainio KE, Gokmen C, Dharan G, Jain T, Kurenkov A, Liu K, Gweon H, Wu J, Fei-Fei L, Savarese S (2021) igibson 2.0: Object-centric simulation for robot learning of everyday household tasks. In: 5th Annual Conference on Robot Learning"},{"key":"5323_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller MA, Fidjeland A, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533","journal-title":"Nature"},{"key":"5323_CR21","unstructured":"Jaderberg M, Mnih V, Czarnecki WM, Schaul T, Leibo JZ, Silver D, Kavukcuoglu K (2017) Reinforcement learning with unsupervised auxiliary tasks. In: International Conference on Learning Representations"},{"key":"5323_CR22","first-page":"538","volume":"2019","author":"K Fang","year":"2019","unstructured":"Fang K, Toshev A, Fei-Fei L, Savarese S (2019) Scene memory transformer for embodied agents in long-horizon tasks. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019:538\u2013547","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"5323_CR23","unstructured":"Chen T, Gupta S, Gupta A (2019) Learning exploration policies for navigation. In: International Conference on Learning Representations"},{"key":"5323_CR24","first-page":"4283","volume":"33","author":"M Chang","year":"2020","unstructured":"Chang M, Gupta A, Gupta S (2020) Semantic visual navigation by watching youtube videos. Advances in Neural Information Processing Systems 33:4283\u20134294","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5323_CR25","unstructured":"Hahn M, Chaplot DS, Tulsiani S, Mukadam M, Rehg JM, Gupta A (2021) No RL, no simulation: Learning to navigate without navigating. In: Beygelzimer A, Dauphin Y, Liang P, Vaughan JW (eds) Advances in Neural Information Processing Systems"},{"key":"5323_CR26","doi-asserted-by":"crossref","unstructured":"Shah D, Sridhar AK, Bhorkar A, Hirose N, Levine S (2022) Gnm: A general navigation model to drive any robot. IEEE International Conference on Robotics and Automation (ICRA) 2023:7226\u20137233","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"5323_CR27","doi-asserted-by":"crossref","unstructured":"Chen AS, Nair S, Finn C (2021) Learning generalizable robotic reward functions from \u201din-the-wild\u201d human videos. In: Self-Supervision for Reinforcement Learning Workshop - ICLR 2021","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"5323_CR28","unstructured":"Touati A, Ollivier Y (2021) Learning one representation to optimize all rewards. In: Beygelzimer A, Dauphin Y, Liang P, Vaughan JW (eds) Advances in Neural Information Processing Systems"},{"key":"5323_CR29","unstructured":"Schwarzer M, Rajkumar N, Noukhovitch M, Anand A, Charlin L, Hjelm D, Bachman P, Courville AC (2021) Pretraining representations for data-efficient reinforcement learning. In: Neural Information Processing Systems"},{"key":"5323_CR30","unstructured":"Eysenbach B, Gupta A, Ibarz J, Levine S (2019) Diversity is all you need: Learning skills without a reward function. In: International Conference on Learning Representations"},{"key":"5323_CR31","unstructured":"Sharma A, Gu S, Levine S, Kumar V, Hausman K (2020) Dynamics-aware unsupervised discovery of skills. In: International Conference on Learning Representations"},{"key":"5323_CR32","unstructured":"Chaplot DS, Gandhi D, Gupta S, Gupta A, Salakhutdinov R (2020) Learning to explore using active neural slam. In: International Conference on Learning Representations"},{"key":"5323_CR33","unstructured":"Chaplot DS, Gandhi D, Gupta A, Salakhutdinov R (2020) Object goal navigation using goal-oriented semantic exploration. In: In Neural Information Processing Systems (NeurIPS)"},{"key":"5323_CR34","unstructured":"Georgakis G, Bucher B, Schmeckpeper K, Singh S, Daniilidis K (2022) Learning to map for active semantic goal navigation. In: International Conference on Learning Representations"},{"key":"5323_CR35","first-page":"15870","volume":"2021","author":"O Kwon","year":"2021","unstructured":"Kwon O, Kim N, Choi Y, Yoo H, Park J, Oh S (2021) Visual graph memory with unsupervised representation for visual navigation. IEEE\/CVF International Conference on Computer Vision (ICCV) 2021:15870\u201315879","journal-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"5323_CR36","unstructured":"Kim N, Kwon O, Yoo H, Choi Y, Park J, Oh S (2022) Topological semantic graph memory for image goal navigation. In: CoRL"},{"key":"5323_CR37","first-page":"770","volume":"2016","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016:770\u2013778","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"5323_CR38","unstructured":"Ultralytics (2021) YOLOv5: A state-of-the-art real-time object detection system. https:\/\/docs.ultralytics.com"},{"key":"5323_CR39","unstructured":"Cobbe K, Hilton J, Klimov O, Schulman J (2020) Phasic policy gradient. In: International Conference on Machine Learning"},{"key":"5323_CR40","first-page":"488","volume":"2017","author":"D Pathak","year":"2017","unstructured":"Pathak D, Agrawal P, Efros AA, Darrell T (2017) Curiosity-driven exploration by self-supervised prediction. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2017:488\u2013489","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"5323_CR41","unstructured":"Burda Y, Edwards H, Storkey A, Klimov O (2019) Exploration by random network distillation. In: International Conference on Learning Representations"},{"key":"5323_CR42","volume-title":"Behavioral Cloning, pp 93\u201397","author":"C Sammut","year":"2010","unstructured":"Sammut C (2010). In: Sammut C, Webb GI (eds) Behavioral Cloning, pp 93\u201397. Springer, Boston, MA"},{"key":"5323_CR43","unstructured":"Ross S, Gordon GJ, Bagnell JA (2010) A reduction of imitation learning and structured prediction to no-regret online learning. In: International Conference on Artificial Intelligence and Statistics"},{"key":"5323_CR44","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv:1707.06347"},{"key":"5323_CR45","doi-asserted-by":"crossref","unstructured":"Khandelwal A, Weihs L, Mottaghi R, Kembhavi A (2022) Simple but effective: Clip embeddings for embodied ai. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"5323_CR46","unstructured":"Yadav K, Ramrakhya R, Majumdar A, Berges V-P, Kuhar S, Batra D, Baevski A, Maksymets O (2022) Offline visual representation learning for embodied navigation. arXiv:2204.13226"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05323-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05323-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05323-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T12:37:15Z","timestamp":1723034235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05323-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":46,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["5323"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05323-2","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]},"assertion":[{"value":"5 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No human subjects or animals are involved in this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}