{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:57:21Z","timestamp":1753887441237,"version":"3.41.2"},"reference-count":30,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T00:00:00Z","timestamp":1632268800000},"content-version":"vor","delay-in-days":264,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Sensors"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>The method of tactile perception can accurately reflect the contact state by collecting force and torque information, but it is not sensitive to the changes in position and posture between assembly objects. The method of visual perception is very sensitive to changes in pose and posture between assembled objects, but they cannot accurately reflect the contact state, especially since the objects are occluded from each other. The robot will perceive the environment more accurately if visual and tactile perception can be combined. Therefore, this paper proposes the alignment method of combined perception for the peg\u2010in\u2010hole assembly with self\u2010supervised deep reinforcement learning. The agent first observes the environment through visual sensors and then predicts the action of the alignment adjustment based on the visual feature of the contact state. Subsequently, the agent judges the contact state based on the force and torque information collected by the force\/torque sensor. And the action of the alignment adjustment is selected according to the contact state and used as a visual prediction label. Whereafter, the network of visual perception performs backpropagation to correct the network weights according to the visual prediction label. Finally, the agent will have learned the alignment skill of combined perception with the increase of iterative training. The robot system is built based on CoppeliaSim for simulation training and testing. The simulation results show that the method of combined perception has higher assembly efficiency than single perception.<\/jats:p>","DOI":"10.1155\/2021\/5073689","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T19:29:19Z","timestamp":1632338959000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Alignment Method of Combined Perception for Peg\u2010in\u2010Hole Assembly with Deep Reinforcement Learning"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1105-6275","authenticated-orcid":false,"given":"Yongzhi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ran","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Liping","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Junqiao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5762-7726","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"e_1_2_8_1_2","unstructured":"ZengA. Learning visual affordances for robotic manipulation[D] 2019 Princeton University."},{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2021.04.041"},{"key":"e_1_2_8_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/s17030476"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.02.001"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1080\/17517575.2019.1597388"},{"key":"e_1_2_8_6_2","doi-asserted-by":"publisher","DOI":"10.1108\/IR-07-2014-0363"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2015.1130172"},{"key":"e_1_2_8_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2508061"},{"key":"e_1_2_8_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0683-6"},{"key":"e_1_2_8_10_2","doi-asserted-by":"crossref","unstructured":"YuanJ. GuanR. DuL. andMaS. A robotic gripper design and integrated solution towards tunnel boring construction equipment 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS) Oct 2020 Las Vegas NV USA 2650\u20132655.","DOI":"10.1109\/IROS45743.2020.9341200"},{"key":"e_1_2_8_11_2","doi-asserted-by":"crossref","unstructured":"Te Tang LinH.-C. ZhaoY. ChenW. andTomizukaM. Autonomous alignment of peg and hole by force\/torque measurement for robotic assembly 2016 IEEE international conference on automation science and engineering (CASE) Aug 2016 Fort Worth TX USA 162\u2013167.","DOI":"10.1109\/COASE.2016.7743375"},{"key":"e_1_2_8_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946406"},{"key":"e_1_2_8_13_2","doi-asserted-by":"crossref","unstructured":"InoueT. De MagistrisG. MunawarA. YokoyaT. andTachibanaR. Deep reinforcement learning for high precision assembly tasks 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) Sept 2017 Vancouver BC Canada 819\u2013825.","DOI":"10.1109\/IROS.2017.8202244"},{"key":"e_1_2_8_14_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4041331"},{"key":"e_1_2_8_15_2","doi-asserted-by":"crossref","unstructured":"ZouP. ZhuQ. WuJ. andXiongR. Learning-based optimization algorithms combining force control strategies for peg-in-hole assembly 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS). 24 Oct.-24 Jan. 2021 Las Vegas NV USA 7403\u20137410.","DOI":"10.1109\/IROS45743.2020.9341678"},{"key":"e_1_2_8_16_2","unstructured":"XuJ. HouZ. LiuZ. andQiaoH. Compare contact model-based control and contact model-free learning: a survey of robotic peg-in-hole assembly strategies 2019 arXiv preprint arXiv: 1904.05240."},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3026802"},{"key":"e_1_2_8_18_2","doi-asserted-by":"crossref","unstructured":"LiaoY. ChenW. WangH. andWuR. A peg-in-hole assembly strategy using uncalibrated visual servoing 2019 IEEE international conference on robotics and biomimetics (ROBIO) Dec 2019 Dali China 1845\u20131850.","DOI":"10.1109\/ROBIO49542.2019.8961422"},{"key":"e_1_2_8_19_2","doi-asserted-by":"crossref","unstructured":"TriyonoputroJ. C. WanW. andHaradaK. Quickly inserting pegs into uncertain holes using multi-view images and deep network trained on synthetic data 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS) Nov 2019 Macau China 5792\u20135799.","DOI":"10.1109\/IROS40897.2019.8968072"},{"key":"e_1_2_8_20_2","unstructured":"HaugaardR. L. LangaaJ. SlothC. andBuchA. G. Fast robust peg-in-hole insertion with continuous visual servoing 2020 arXiv preprint arXiv: 2011.06399."},{"key":"e_1_2_8_21_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4004497"},{"key":"e_1_2_8_22_2","unstructured":"LiuY. RomeresD. JhaD. K. andNikovskiD. Understanding multi-modal perception using behavioral cloning for peg-in-a-hole insertion tasks 2020 ar Xiv preprint ar Xiv: 2007.11646."},{"key":"e_1_2_8_23_2","doi-asserted-by":"crossref","unstructured":"DingJ. WangC. andLuC. Transferable trial-minimizing progressive peg-in-hole model 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS) Nov 2019 Macau China 5862\u20135868.","DOI":"10.1109\/IROS40897.2019.8968282"},{"key":"e_1_2_8_24_2","doi-asserted-by":"crossref","unstructured":"OwensA.andEfrosA. A. Audio-visual scene analysis with self-supervised multisensory features[C] Proceedings of the European Conference on Computer Vision (ECCV) 2018 Munich Germany 631\u2013648.","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"e_1_2_8_25_2","doi-asserted-by":"crossref","unstructured":"FinnC.andLevineS. Deep visual foresight for planning robot motion 2017 IEEE international conference on robotics and automation (ICRA) 29 May-3 June 2017 Singapore 2786\u20132793.","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"e_1_2_8_26_2","doi-asserted-by":"crossref","unstructured":"SinapovJ. SchenckC. andStoytchevA. Learning relational object categories using behavioral exploration and multimodal perception 2014 IEEE international conference on robotics and automation (ICRA) 31 May-7 June 2014 Hongkong China 5691\u20135698.","DOI":"10.1109\/ICRA.2014.6907696"},{"key":"e_1_2_8_27_2","doi-asserted-by":"crossref","unstructured":"ZhengY. ZhangX. ChenY. andHuangY. Peg-in-hole assembly based on hybrid vision\/force guidance and dual-arm coordination 2017 IEEE international conference on robotics and biomimetics (ROBIO) Dec 2017 Macau Macao 418\u2013423.","DOI":"10.1109\/ROBIO.2017.8324453"},{"key":"e_1_2_8_28_2","doi-asserted-by":"crossref","unstructured":"LeeM. A. ZhuY. SrinivasanK. ShahP. SavareseS. Fei-FeiL. GargA. andBohgJ. Making sense of vision and touch: self-supervised learning of multimodal representations for contact-rich tasks 2019 international conference on robotics and automation (ICRA) May 2019 Montreal QC Canada 8943\u20138950.","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"e_1_2_8_29_2","article-title":"Peg-in-hole assembly based on two-phase scheme and f\/t sensor for dual-arm robot","volume":"17","author":"Zhang X.","year":"2017","journal-title":"Sensors"},{"key":"e_1_2_8_30_2","unstructured":"OlahC. Calculus on computational graphs: backpropagation 2015 http: \/\/colah. github.io\/posts\/2015-08-Backprop\/."}],"container-title":["Journal of Sensors"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2021\/5073689.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2021\/5073689.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5073689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:11:08Z","timestamp":1722903068000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5073689"}},"subtitle":[],"editor":[{"given":"Kelvin","family":"Wong","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5073689"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5073689","archive":["Portico"],"relation":{},"ISSN":["1687-725X","1687-7268"],"issn-type":[{"type":"print","value":"1687-725X"},{"type":"electronic","value":"1687-7268"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-07-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5073689"}}