{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:23:15Z","timestamp":1753885395014,"version":"3.41.2"},"reference-count":44,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,12,8]],"date-time":"2021-12-08T00:00:00Z","timestamp":1638921600000},"content-version":"vor","delay-in-days":341,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1700200"],"award-info":[{"award-number":["2018YFB1700200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803368","61533015","61972389","61903356"],"award-info":[{"award-number":["61803368","61533015","61972389","61903356"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M661156"],"award-info":[{"award-number":["2019M661156"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["20180540114","20180520029"],"award-info":[{"award-number":["20180540114","20180520029"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011259","name":"State Key Laboratory of Robotics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011259","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>As deep reinforcement learning methods have made great progress in the visual navigation field, metalearning\u2010based algorithms are gaining more attention since they greatly improve the expansibility of moving agents. According to metatraining mechanism, typically an initial model is trained as a metalearner by existing navigation tasks and becomes well performed in new scenes through relatively few recursive trials. However, if a metalearner is overtrained on the former tasks, it may hardly achieve generalization on navigating in unfamiliar environments as the initial model turns out to be quite biased towards former ambient configuration. In order to train an impartial navigation model and enhance its generalization capability, we propose an Unbiased Model\u2010Agnostic Metalearning (UMAML) algorithm towards target\u2010driven visual navigation. Inspired by entropy\u2010based methods, maximizing the uncertainty over output labels in classification tasks, we adopt inequality measures used in Economics as a concise metric to calculate the loss deviation across unfamiliar tasks. With succinctly minimizing the inequality of task losses, an unbiased navigation model without overperforming in particular scene types can be learnt based on Model\u2010Agnostic Metalearning mechanism. The exploring agent complies with a more balanced update rule, able to gather navigation experience from training environments. Several experiments have been conducted, and results demonstrate that our approach outperforms other state\u2010of\u2010the\u2010art metalearning navigation methods in generalization ability.<\/jats:p>","DOI":"10.1155\/2021\/5620751","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T05:35:21Z","timestamp":1639028121000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unbiased Model\u2010Agnostic Metalearning Algorithm for Learning Target\u2010Driven Visual Navigation Policy"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6383-1448","authenticated-orcid":false,"given":"Tianfang","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,12,8]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-017-0371-5"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-017-0646-z"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2015.2463671"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023014"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_2_9_6_2","unstructured":"MnihV. BadiaA. P. andMirzaM. Asynchronous methods for deep reinforcement learning Proceedings of the 33rd International Conference on Machine Learning June 2016 New York NY USA 2850\u20132869."},{"volume-title":"Introduction to Reinforcement Learning","year":"2017","author":"Sutton R. S.","key":"e_1_2_9_7_2"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"ZhuY. MottaghiR. KolveE. andLimJ. J. Target-driven visual navigation in indoor scenes using deep reinforcement learning Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) May 2017 Singapore 3357\u20133364 https:\/\/doi.org\/10.1109\/icra.2017.7989381 2-s2.0-85028006260.","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"e_1_2_9_9_2","unstructured":"WangZ. SchaulT. HesselM. Van HasseltH. LanctotM. andDe FreitasN. Dueling network architectures for deep reinforcement learning 48 Proceedings of the ICML 2016 IEEE New York NY USA 1995\u20132003."},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2020.2967677"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"TaalimiA. RahimpourA. LiuL. andQiH. Multiview task-driven recognition in visual sensor networks Proceedings of the ICIP September 2017 Beijing China IEEE 2099\u20132103 https:\/\/doi.org\/10.1109\/icip.2017.8296652 2-s2.0-85045320935.","DOI":"10.1109\/ICIP.2017.8296652"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2195922"},{"key":"e_1_2_9_13_2","unstructured":"FinnC. AbbeelP. andLevineS. Model-agnostic metalearning for fast adaptation of deep networks 2 Proceedings of the ICML August 2017 Sydney Australia IEEE."},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"BorensteinJ.andKorenY. Real-time obstacle avoidance for fast mobile robots in cluttered environments Proceedings of the IEEE International Conference on Robotics and Automation May 1990 Cincinnati OH USA 572\u2013577.","DOI":"10.1109\/ROBOT.1990.126042"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1023\/a:1008824626321"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"DavisonA. Real-time simultaneous localization and mapping with a single camera Proceedings of the IEEE International Conference on Computer Vision October 2003 Nice France 1403\u20131410.","DOI":"10.1109\/ICCV.2003.1238654"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"EngelJ. Sch\u00f6psT. andCremersD. LSD-SLAM: large-scale direct monocular SLAM Proceedings of the European Conference on Computer Vision September 2014 Zurich Switzerland 834\u2013849 https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54 2-s2.0-84906489259.","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"KimY.-H. JangJ.-I. andYunS. End-to-end deep learning for autonomous navigation of mobile robot Proceedings of the IEEE International Conference on Consumer Electronics June 2018 JeJu South Korea.","DOI":"10.1109\/ICCE.2018.8326229"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"GuptaS. DavidsonJ. LevineS. SukthankarR. andMalikJ. Cognitive mapping and planning for visual navigation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.769"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"MisraD. LangfordJ. andArtziY. Mapping instructions and visual observations to actions with reinforcement learning Proceedings of the Conference on Empirical Methods on Natural Language Processing September 2017 Copenhagen Denmark.","DOI":"10.18653\/v1\/D17-1106"},{"key":"e_1_2_9_22_2","unstructured":"WuY. WuY. GkioxariG. andTianY. Embodied question answering Proceedings of the CVPR June 2018 Salt Lake City UT USA."},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2018.2869640"},{"key":"e_1_2_9_24_2","unstructured":"SnellJ. KevinS. andZemelR. Prototypical networks for few-shot learning Proceedings of the Advances in Neural Information Processing Systems December 2017 Long Beach CA USA 4077\u20134087."},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"SungF. YangY. ZhangLi XiangT. TorrP. HS. andHospedalesT. M. Learning to compare: relation network for few-shot learning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 1199\u20131208 https:\/\/doi.org\/10.1109\/cvpr.2018.00131 2-s2.0-85061641334.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_2_9_26_2","unstructured":"MishraN. RohaninejadM. ChenX. andAbbeelP. A simple neural attentive meta-learner 2017 https:\/\/arxiv.org\/abs\/1707.03141."},{"key":"e_1_2_9_27_2","first-page":"2554","article-title":"Meta networks","volume":"70","author":"Munkhdalai T.","year":"2017","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_2_9_28_2","unstructured":"NicholA. AchiamJ. andSchulmanJ. On first-order meta-learning algorithms 2018 https:\/\/arxiv.org\/abs\/1803.02999."},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"HochreiterS. YoungerA. S. andConwellP. R. Learning to learn using gradient descent Proceedings of the International Conference on Artificial Neural Networks (ICANN 2001) August 2001 Vienna Austria 87\u201394 https:\/\/doi.org\/10.1007\/3-540-44668-0_13 2-s2.0-84958985283.","DOI":"10.1007\/3-540-44668-0_13"},{"key":"e_1_2_9_30_2","unstructured":"AndersonP. ChangA. ChaplotD. S. DosovitskiyA. GuptaS. KoltunV. KoseckaJ. andMalikJ. On evaluation of embodied navigation agents 2018 https:\/\/arxiv.org\/abs\/1807.06757."},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"LiuY. YangC. andSunG. Memory-based parameterized skills learning for mapless visual navigation Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP) September 2019 Taipei Taiwan.","DOI":"10.1109\/ICIP.2019.8803178"},{"key":"e_1_2_9_32_2","unstructured":"BhardwajM. ChoudhuryS. andSchererS. Learning heuristic search via imitation 2017 https:\/\/arxiv.org\/abs\/1707.03034."},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 770\u2013778 https:\/\/doi.org\/10.1109\/cvpr.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_34_2","doi-asserted-by":"crossref","unstructured":"LiY. QiH. DaiJ. JiX. andWeiY. Fully convolutional instance-aware semantic segmentation Proceedings of the CVPR July 2017 Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.472"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3023014"},{"key":"e_1_2_9_36_2","unstructured":"HermannK. M. HillF. GreenS. WangF. FaulknerR. SoyerH. SzepesvariD. CzarneckiW. M. JaderbergM. TeplyashinD. WainwrightM. AppsC. HassabisD. andBlunsomP. Grounded language learning in a simulated 3D world 2017 https:\/\/arxiv.org\/abs\/1706.06551."},{"key":"e_1_2_9_37_2","unstructured":"ArmandJ. GraveE. BojanowskiP. andMikolovT. Bag of tricks for efficient text classification 2016 https:\/\/arxiv.org\/abs\/1607.01759."},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2008.08.007"},{"key":"e_1_2_9_39_2","doi-asserted-by":"publisher","DOI":"10.2307\/2094626"},{"key":"e_1_2_9_40_2","unstructured":"EfeA. O.andFosterJ. Lorenz dominance and the variance of logarithms 1997 C. V. Starr Center for Applied Economics New York University New York NY USA Technical Report."},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"ChangA. DaiA. FunkhouserT. HalberM. NiessnerM. SavvaM. SongS. ZengA. andZhangY. Matterport3D: learning from RGB-D data in indoor environments Proceedings of the International Conference on 3D Vision October 2017 Qingdao China.","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_2_9_42_2","unstructured":"YangW. WangX. AliF. GuptaA. andMottaghiR. Visual semantic navigation using scene priors Proceedings of the Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA."},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/0014-2921(80)90051-3"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(70)90039-6"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5620751.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5620751.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5620751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T02:26:37Z","timestamp":1726280797000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5620751"}},"subtitle":[],"editor":[{"given":"Ahmed Mostafa","family":"Khalil","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5620751"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5620751","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-11-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5620751"}}