{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:22:35Z","timestamp":1767183755329,"version":"3.38.0"},"reference-count":37,"publisher":"SAGE Publications","issue":"16","license":[{"start":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T00:00:00Z","timestamp":1598572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Scientific Instruments Development Program of NSFC","award":["[615278010]"],"award-info":[{"award-number":["[615278010]"]}]},{"DOI":"10.13039\/501100012245","name":"science and technology planning project of guangdong province","doi-asserted-by":"publisher","award":["[2017B010116005]"],"award-info":[{"award-number":["[2017B010116005]"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Transactions of the Institute of Measurement and Control"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:p> Two common methods exist for solving indoor autonomous navigation and obstacle-avoidance problems using monocular vision: the traditional simultaneous localization and mapping (SLAM) method, which requires complex hardware, heavy calculations, and is prone to errors in low texture or dynamic environments; and deep-learning algorithms, which use the fully connected layer for classification or regression, resulting in more model parameters and easy over-fitting. Among the latter ones, the most advanced indoor navigation algorithm divides a single image frame into multiple parts for prediction, resulting in doubled reasoning time. To solve these problems, we propose a multi-task deep network based on feature map region division for monocular indoor autonomous navigation. We divide the feature map instead of the original image to avoid repeated information processing. To reduce model parameters, we use convolution instead of the fully connected layer to predict the navigable probability of the left, middle, and right parts. We propose that the linear velocity is determined by combining three prediction probabilities to reduce collision risk. Experimental evaluation shows that the proposed method is nine times smaller than the previous state-of-the-art methods; further, its processing speed and navigation capability increase more than five and 1.6 times, respectively. <\/jats:p>","DOI":"10.1177\/0142331220947507","type":"journal-article","created":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T12:04:37Z","timestamp":1598616277000},"page":"3243-3253","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":12,"title":["Part-based multi-task deep network for autonomous indoor drone navigation"],"prefix":"10.1177","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7277-5807","authenticated-orcid":false,"given":"Xiangzhu","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, China"}]},{"given":"Lijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, China"}]},{"given":"Hailong","family":"Pei","sequence":"additional","affiliation":[{"name":"Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, China"}]},{"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"UTA Research Institute, University of Texas at Arlington, USA"}]}],"member":"179","published-online":{"date-parts":[[2020,8,28]]},"reference":[{"key":"bibr1-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/5.736347"},{"key":"bibr2-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1117\/12.819082"},{"key":"bibr3-0142331220947507","doi-asserted-by":"publisher","DOI":"10.3390\/rs9020100"},{"key":"bibr4-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1586760"},{"key":"bibr5-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"bibr6-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21581"},{"key":"bibr7-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206247"},{"key":"bibr8-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2019.8798183"},{"key":"bibr9-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"bibr10-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"bibr11-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"bibr12-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"bibr13-0142331220947507","unstructured":"Howard AG, Zhu M, Chen B, et al. (2017) MobileNets: Efficient convolutional neural networks for mobile vision applications. Available at: https:\/\/arxiv.org\/abs\/1704.04861 (accessed 3 February 2020)."},{"key":"bibr14-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-29363-9_14"},{"key":"bibr15-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1177\/1729881419829941"},{"key":"bibr16-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2016.7838739"},{"key":"bibr17-0142331220947507","first-page":"448","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)","author":"Ioffe S","year":"2015"},{"key":"bibr18-0142331220947507","unstructured":"Kahn G, Villaflor A, Pong V, et al. (2017) Uncertainty-aware reinforcement learning for collision avoidance. arXiv preprint arXiv:1702.01182."},{"key":"bibr19-0142331220947507","unstructured":"Kim DK, Chen T (2015) Deep neural network for real-time autonomous indoor navigation. arXiv preprint arXiv:1511.04668."},{"volume-title":"3rd International Conference on Learning Representations (ICLR)","year":"2015","author":"Kingma DP","key":"bibr20-0142331220947507"},{"key":"bibr21-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594204"},{"key":"bibr22-0142331220947507","first-page":"1097","volume-title":"26th Annual Conference on Neural Information Processing Systems-Volume 1 (NIPS 2012)","author":"Krizhevsky A","year":"2012"},{"key":"bibr23-0142331220947507","first-page":"1","volume-title":"2nd International Conference on Learning Representations (ICLR 2014)","author":"Lin M","year":"2014"},{"key":"bibr24-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"bibr25-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2657002"},{"key":"bibr26-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2658940"},{"key":"bibr27-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21436"},{"key":"bibr28-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.099"},{"key":"bibr29-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2016.05.020"},{"key":"bibr30-0142331220947507","unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098."},{"key":"bibr31-0142331220947507","doi-asserted-by":"crossref","unstructured":"Sadeghi F, Levine S (2016) Cad2rl: Real single-image flight without a single real image. arXiv preprint arXiv:1611.04201.","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"bibr32-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9293-0"},{"key":"bibr33-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206285"},{"key":"bibr34-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"bibr35-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225002"},{"key":"bibr36-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1177\/0142331209342220"},{"key":"bibr37-0142331220947507","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Transactions of the Institute of Measurement and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0142331220947507","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0142331220947507","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0142331220947507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T12:28:16Z","timestamp":1741004896000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0142331220947507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,28]]},"references-count":37,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["10.1177\/0142331220947507"],"URL":"https:\/\/doi.org\/10.1177\/0142331220947507","relation":{},"ISSN":["0142-3312","1477-0369"],"issn-type":[{"type":"print","value":"0142-3312"},{"type":"electronic","value":"1477-0369"}],"subject":[],"published":{"date-parts":[[2020,8,28]]}}}