{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:41:09Z","timestamp":1762508469420,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"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_27","type":"book-chapter","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T16:17:17Z","timestamp":1620145037000},"page":"301-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Guided Deep Reinforcement Learning for Path Planning of Robotic Manipulators"],"prefix":"10.1007","author":[{"given":"Yue","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxuan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877","volume-title":"Planning Algorithms","author":"SM LaValle","year":"2006","unstructured":"LaValle, S.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)"},{"issue":"13","key":"27_CR2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.3901\/JME.2010.13.109","volume":"46","author":"Q Jia","year":"2010","unstructured":"Jia, Q., Chen, G., et al.: Path planning for space manipulator to avoid obstacle based on A* algorithm. J. Mech. Eng. 46(13), 109\u2013115 (2010)","journal-title":"J. Mech. Eng."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, Z., Ou, Y.: Obstacle avoidance of manipulators based on improved artificial potential field method. In: 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), Dali, China, pp. 564\u2013569. IEEE (2019)","DOI":"10.1109\/ROBIO49542.2019.8961506"},{"key":"27_CR4","unstructured":"Al-Hmouz, R., Gulrez, T., Al-Jumaily, A.: Probabilistic road maps with obstacle avoidance in cluttered dynamic environment. In: Proceedings of IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing Conference (ISSNIP), Melbourne, AUS, pp. 241\u2013245. IEEE (2004)"},{"key":"27_CR5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, MA (2018)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Katyal, K., Wang, I., Burlina, P.: Leveraging deep reinforcement learning for reaching robotic tasks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, pp. 490\u2013491. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.71"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Kamali, K., Bonev, I.A., Desrosiers, C.: Real-time motion planning for robotic teleoperation using dynamic-goal deep reinforcement learning. In: 2020 17th Conference on Computer and Robot Vision (CRV), Ottawa, Canada, pp. 182\u2013189. IEEE (2020)","DOI":"10.1109\/CRV50864.2020.00032"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Li, Z., Ma, H., et al.: Motion planning of six-dof arm robot based on improved DDPG algorithm. In: 2020 39th Chinese Control Conference (CCC), Shenyang, China, pp. 3954\u20133959. IEEE (2020)","DOI":"10.23919\/CCC50068.2020.9188521"},{"issue":"7540","key":"27_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"27_CR10","unstructured":"Gu, S., Lillicrap, T.P., et al.: Continuous deep q-learning with model-based acceleration. In: Proceedings of the 33rd International Conference on Machine Learning, New York, USA, pp. 2829\u20132838 (2016)"},{"key":"27_CR11","unstructured":"Lillicrap, T.P., Hunt, J.J., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"27_CR12","unstructured":"Mnih, V., Badia, A.P., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning, New York, USA, pp. 1928\u20131937 (2016)"},{"key":"27_CR13","unstructured":"Schulman, J., Wolski, F., et al.: Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"27_CR14","unstructured":"Schulman, J., Levine, S., et al.: Trust region policy optimization. In: Proceedings of the 31st International Conference on Machine Learning, Lille, France, pp. 1889\u20131897 (2015)"},{"key":"27_CR15","unstructured":"Fujimoto, S., Hoof, H.V., et al.: Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477 (2018)"},{"key":"27_CR16","unstructured":"Haarnoja, T., Zhou, A., et al.: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv preprint arXiv:1801.01290 (2018)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Sangiovanni, B., Rendiniello, A., et al.: Deep reinforcement learning for collision avoidance of robotic manipulators. In: 2018 European Control Conference (ECC), Limassol, Cyprus, pp. 2063\u20132068. IEEE (2018)","DOI":"10.23919\/ECC.2018.8550363"},{"issue":"7","key":"27_CR18","doi-asserted-by":"publisher","first-page":"105669","DOI":"10.1109\/ACCESS.2019.2932257","volume":"2019","author":"J Xie","year":"2019","unstructured":"Xie, J., Shao, Z., et al.: Deep reinforcement learning with optimized reward functions for robotic trajectory planning. IEEE Access 2019(7), 105669\u2013105679 (2019)","journal-title":"IEEE Access"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Zeng, R., Liu, M., et al.: Manipulator control method based on deep reinforcement learning. In: 2020 Chinese Control and Decision Conference (CCDC), Hefei, China, pp. 415\u2013420. IEEE (2020)","DOI":"10.1109\/CCDC49329.2020.9164440"},{"key":"27_CR20","unstructured":"James, S., Freese, M., Davison, A.J.: PyRep: Bringing V-REP to Deep Robot Learning. arXiv preprint arXiv:1906.11176 (2019)"}],"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_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T16:45:10Z","timestamp":1620146710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-2336-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811623356","9789811623363"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-2336-3_27","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)"}}]}}