{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:25:46Z","timestamp":1743085546898,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811623356"},{"type":"electronic","value":"9789811623363"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-981-16-2336-3_2","type":"book-chapter","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T16:17:17Z","timestamp":1620145037000},"page":"15-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hole-Peg Assembly Strategy Based on Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Xiaodong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengchao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Quillen, D., Jang, E., Nachum, O., et al.: Deep reinforcement learning for vision-based robotic grasping: a simulated comparative evaluation of off-policy methods (2018). arXiv Robot","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Zeng, A., Song, S., Welker, S., et al.: Learning synergies between pushing and grasping with self-supervised deep reinforcement learning. Intell. Robots Syst. 4238\u20134245 (2018)","DOI":"10.1109\/IROS.2018.8593986"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., et al.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: International Conference on Robotics and Automation, pp. 3389\u20133396 (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"2_CR4","unstructured":"De Andres, M.O., Ardakani, M.M., Robertsson, A., et al.: Reinforcement learning for 4-finger-gripper manipulation. In: International Conference on Robotics and Automation, pp. 1\u20136 (2018)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Yang, P., Huang, J.: TrackDQN: visual tracking via deep reinforcement learning. In: 2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT). IEEE (2019)","DOI":"10.1109\/ICCASIT48058.2019.8973189"},{"key":"2_CR6","unstructured":"Kenzo, LT., Francisco, L., Javier, R.D.S.: Visual navigation for biped humanoid robots using deep reinforcement learning. IEEE Robot. Autom. Lett. 3, 1\u20131 (2018)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Yang, Y., Bevan, M.A., Li, B.: Efficient navigation of colloidal robots in an unknown environment via deep reinforcement learning. Adv. Intell. Syst. (2019)","DOI":"10.1002\/aisy.201900106"},{"issue":"18","key":"2_CR8","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.3390\/s19183837","volume":"19","author":"J Zeng","year":"2019","unstructured":"Zeng, J., Ju, R., Qin, L., et al.: Navigation in unknown dynamic environments based on deep reinforcement learning. Sensors 19(18), 3837 (2019)","journal-title":"Sensors"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Y., Luo, J., Tomizuka, M., et al.: A learning framework for high precision industrial assembly. In: International Conference on Robotics and Automation, pp. 811\u2013817 (2019)","DOI":"10.1109\/ICRA.2019.8793659"},{"issue":"3","key":"2_CR10","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1109\/TII.2018.2868859","volume":"15","author":"J Xu","year":"2019","unstructured":"Xu, J., Hou, Z., Wang, W., et al.: Feedback deep deterministic policy gradient with fuzzy reward for robotic multiple peg-in-hole assembly tasks. IEEE Trans. Ind. Informat. 15(3), 1658\u20131667 (2019)","journal-title":"IEEE Trans. Ind. Informat."},{"issue":"4","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1109\/TII.2017.2748236","volume":"14","author":"L Roveda","year":"2018","unstructured":"Roveda, L., Pallucca, G., Pedrocchi, N., et al.: Iterative learning procedure with reinforcement for high-accuracy force tracking in robotized tasks. IEEE Trans Ind. Informat. 14(4), 1753\u20131763 (2018)","journal-title":"IEEE Trans Ind. Informat."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Chang, W., Andini, D.P., Pham, V., et al.: An implementation of reinforcement learning in assembly path planning based on 3D point clouds. In: International Automatic Control Conference (2018)","DOI":"10.1109\/CACS.2018.8606737"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Inoue, T., De Magistris, G., Munawar, A. et al.: Deep reinforcement learning for high precision assembly tasks. In: Intelligent Robots and Systems, pp. 819\u2013825 (2017)","DOI":"10.1109\/IROS.2017.8202244"},{"key":"2_CR14","unstructured":"Vecerik, M., Hester, T., Scholz, J., et al.: leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards (2017). arXiv: Artificial Intelligence"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Luo, J., Solowjow, E., Wen, C., et al.: Reinforcement learning on variable impedance controller for high-precision robotic assembly. In: International Conference on Robotics and Automation, pp. 3080\u20133087 (2019)","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"2_CR16","unstructured":"Lillicrap, T., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning (2015). arXiv Learning"},{"key":"2_CR17","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Playing Atari with deep reinforcement learning (2013). arXiv Learning"},{"key":"2_CR18","unstructured":"Fujimoto, S., Van Hoof, H., Meger, D. et al.: Addressing function approximation error in actor-critic methods (2018) . arXiv: Artificial Intelligence"}],"container-title":["Communications in Computer and Information Science","Cognitive Systems and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-2336-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T16:36:20Z","timestamp":1620146180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-2336-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811623356","9789811623363"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-2336-3_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Systems and Signal Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhuhai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccsip2020.caai.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"120","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}