{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:16:05Z","timestamp":1770228965025,"version":"3.49.0"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127619","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13346-13355","source":"Crossref","is-referenced-by-count":4,"title":["Dynamem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation"],"prefix":"10.1109","author":[{"given":"Peiqi","family":"Liu","sequence":"first","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanqiu","family":"Guo","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohit","family":"Warke","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumith","family":"Chintala","sequence":"additional","affiliation":[{"name":"Meta Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Paxton","sequence":"additional","affiliation":[{"name":"Hello Robot Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nur Muhammad Mahi","family":"Shafiullah","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lerrel","family":"Pinto","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Yenamandra","year":"2023","journal-title":"Homerobot: Open-vocabulary mobile manipulation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01537"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref4","author":"Zeng","year":"2024","journal-title":"Poliformer: Scaling on-policy rl with transformers results in masterful navigators"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref7","volume-title":"Clio: Real-time task-driven openset 3d scene graphs","author":"Maggio","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"ref10","author":"Qiu","year":"2024","journal-title":"Learning generalizable feature fields for mobile manipulation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341737"},{"key":"ref12","volume-title":"Goat: Go to any thing","author":"Chang","year":"2023"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.077","volume-title":"Hierarchical open-vocabulary 3d scene graphs for language-grounded robot navigation","author":"Werby","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"ref15","volume-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","author":"Chen","year":"2020"},{"key":"ref16","volume-title":"Scannet: Richlyannotated 3d reconstructions of indoor scenes","author":"Dai","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref18","author":"Baruch","year":"2021","journal-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data"},{"key":"ref19","article-title":"The homerobot open vocab mobile manipulation challenge","volume-title":"Thirtyseventh Conference on Neural Information Processing Systems: Competition Track","author":"Yenamandra","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3336109\/mm7"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48891.2023.10160969","volume-title":"Visual language maps for robot navigation","author":"Huang","year":"2023"},{"key":"ref22","first-page":"259","article-title":"Improving vision-andlanguage navigation with image-text pairs from the web","author":"Majumdar","year":"2020","journal-title":"in ECCV. Springer"},{"key":"ref23","author":"Krantz","year":"2022","journal-title":"Instance-specific image goal navigation: Training embodied agents to find object instances"},{"key":"ref24","first-page":"26661","article-title":"No rl, no simulation: Learning to navigate without navigating","volume":"34","author":"Hahn","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Chaplot","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636743"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01582"},{"key":"ref28","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","volume-title":"CoRR","volume":"abs\/2006.13171","author":"Batra"},{"key":"ref29","author":"Melnik","year":"2023","journal-title":"Uniteam: Open vocabulary mobile manipulation challenge"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911434148"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2873617"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202213"},{"key":"ref34","first-page":"42474258","article-title":"Object goal navigation using goaloriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","author":"Ha","year":"2022","journal-title":"Semantic abstraction: Open-world 3d scene understanding from 2d vision-language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161534"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref41","author":"Ji","year":"2024","journal-title":"Graspsplats: Efficient manipulation with 3d feature splatting"},{"key":"ref42","article-title":"Splatmover: Multi-stage, open-vocabulary robotic manipulation via editable gaussian splatting","volume-title":"8th Annual Conference on Robot Learning","author":"Shorinwa","year":"2024"},{"issue":"4","key":"ref43","doi-asserted-by":"crossref","DOI":"10.1145\/3592433","article-title":"3d gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Transactions on Graphics"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341737"},{"key":"ref45","author":"Wang","year":"2023","journal-title":"D3 fields: Dynamic 3d descriptor fields for zero-shot generalizable robotic manipulation"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3547643"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3331893"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056726"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00015"},{"key":"ref51","author":"Krishna","year":"2023","journal-title":"3dsslam: A 3d object detection based semantic slam towards dynamic indoor environments"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981750"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160782"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341922"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01853"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811667"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952161"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593828"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593691"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3203231"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3489849.3489882"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2860039"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.081"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-023-02019-6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068640"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196895"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_38"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146554"},{"key":"ref70","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref71","first-page":"5531","article-title":"Bayesian imitation learning for end-to-end mobile manipulation","volume-title":"International Conference on Machine Learning","author":"Du","year":"2022"},{"key":"ref72","first-page":"1367","article-title":"Error-aware imitation learning from teleoperation data for mobile manipulation","volume-title":"Conference on Robot Learning","author":"Wong","year":"2022"},{"key":"ref73","volume-title":"Spin: Simultaneous perception, interaction and navigation","author":"Uppal","year":"2024"},{"key":"ref74","volume-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref75","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01100","volume-title":"Sigmoid loss for language image pre-training","author":"Zhai","year":"2023"},{"key":"ref76","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref77","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"Extract free dense labels from clip","author":"Zhou","year":"2022"},{"key":"ref78","volume-title":"Gpt-4 technical report","author":"Team","year":"2024"},{"key":"ref79","author":"Google","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref83","volume-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2024"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref85","volume-title":"Stretch ai","author":"Robot","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref87","author":"Etukuru","year":"2024","journal-title":"Robot utility models: General policies for zero-shot deployment in new environments"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127619.pdf?arnumber=11127619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:56Z","timestamp":1756880036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127619","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}