{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T19:01:31Z","timestamp":1758394891112,"version":"3.37.3"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing University of Posts and Telecommunications China Mobile Research Institute Joint Innovation Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/lra.2023.3327672","type":"journal-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T18:01:52Z","timestamp":1698256912000},"page":"963-970","source":"Crossref","is-referenced-by-count":1,"title":["PoSE: Suppressing Perceptual Noise in Embodied Agents for Enhanced Semantic Navigation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5062-2460","authenticated-orcid":false,"given":"Benhui","family":"Zhuang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3008-1887","authenticated-orcid":false,"given":"Chunhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8874-5466","authenticated-orcid":false,"given":"Zheng","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FILM: Following instructions in language with modular methods","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Min","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981261"},{"key":"ref3","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chaplot","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178804"},{"key":"ref5","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","volume-title":"Proc. Conf. Robot Learn.","author":"Blukis","year":"2021"},{"key":"ref6","article-title":"Learning exploration policies for navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref7","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaplot","year":"2020"},{"article-title":"Prompter: Utilizing large language model prompting for a data efficient embodied instruction following","year":"2022","author":"Inoue","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"article-title":"AI2-THOR: An interactive 3D environment for visual AI","year":"2017","author":"Kolve","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref12","article-title":"Large-scale study of curiosity-driven learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00190"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01504"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/128"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.81"},{"key":"ref20","first-page":"1743","article-title":"Embodied concept learner: Self-supervised learning of concepts and mapping through instruction following","volume-title":"Proc. Conf. Robot Learn.","author":"Ding","year":"2022"},{"article-title":"LaMPP: Language models as probabilistic priors for perception and action","year":"2023","author":"Li","key":"ref21"},{"article-title":"Translating natural language to planning goals with large-language models","year":"2023","author":"Xie","key":"ref22"},{"article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref26","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Am Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref29","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"author":"Sanh","key":"ref30","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter"},{"key":"ref31","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10360389\/10295972.pdf?arnumber=10295972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T04:30:11Z","timestamp":1705033811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10295972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3327672","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}