{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:16:42Z","timestamp":1783995402727,"version":"3.55.0"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91748106"],"award-info":[{"award-number":["91748106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Hubei Province Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2019CFB526"],"award-info":[{"award-number":["2019CFB526"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tsmc.2022.3228901","type":"journal-article","created":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T18:50:52Z","timestamp":1672426252000},"page":"3566-3573","source":"Crossref","is-referenced-by-count":31,"title":["Deep Reinforcement Learning With a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8801-0972","authenticated-orcid":false,"given":"Gang","family":"Peng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9625-7449","authenticated-orcid":false,"given":"Jin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1529-4537","authenticated-orcid":false,"given":"Xinde","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1988-2328","authenticated-orcid":false,"given":"Mohammad Omar","family":"Khyam","sequence":"additional","affiliation":[{"name":"School of Engineering and Technology, Central Queensland University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3002852"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665248"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CRV50864.2020.00032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3070642"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2966859"},{"key":"ref17","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2017.8023674"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2018.8539438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932257"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025711"},{"key":"ref21","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"arXiv 2103 01955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2975232"},{"key":"ref7","first-page":"286","article-title":"Trajectory planning for seven-DOF robotic arm based on seventh degree polynomial","volume":"593","author":"fang","year":"2019","journal-title":"Proc Chin Intell Syst Conf (CISC)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.71"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2019.8768792"},{"key":"ref3","first-page":"740","article-title":"Robotic arm path planning based on three-dimensional artificial potential field","author":"lin","year":"2018","journal-title":"Proc 18th Int Conf Control Autom Syst (ICCAS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IHMSC.2019.10142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2784828"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10128819\/10004017.pdf?arnumber=10004017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:17:15Z","timestamp":1686593835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10004017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":25,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2022.3228901","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}