{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:10:40Z","timestamp":1771632640764,"version":"3.50.1"},"reference-count":32,"publisher":"Cambridge University Press (CUP)","issue":"12","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"unspecified","delay-in-days":17,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotica"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Although deep reinforcement learning (DRL) techniques have been extensively studied in the field of robotic manipulators, there is limited research on directly mapping the output of policy functions to the joint space of manipulators. This paper proposes a motion planning scheme for redundant manipulators to avoid obstacles based on DRL, considering the actual shapes of obstacles in the environment. This scheme not only accomplishes the path planning task for the end-effector but also enables autonomous obstacle avoidance while obtaining the joint trajectories of the manipulator. First, a reinforcement learning framework based on the joint space is proposed. This framework uses the joint accelerations of the manipulator to calculate the Cartesian coordinates of the end-effector through forward kinematics, thereby performing end-to-end path planning for the end-effector. Second, the distance between all the linkages of the manipulator and irregular obstacles is calculated in real time based on the Gilbert\u2013Johnson\u2013Keerthi distance algorithm. The reward function containing joint acceleration is constructed with this distance to realize the obstacle avoidance task of the redundant manipulator. Finally, simulations and physical experiments were conducted on a 7-degree-of-freedom manipulator, demonstrating that the proposed scheme can generate efficient and collision-free trajectories in environments with irregular obstacles, effectively avoiding collisions.<\/jats:p>","DOI":"10.1017\/s0263574725102993","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:35:06Z","timestamp":1766054106000},"page":"4519-4537","source":"Crossref","is-referenced-by-count":1,"title":["Deep reinforcement learning-based obstacle avoidance motion planning for redundant manipulator considering the actual shape of obstacles"],"prefix":"10.1017","volume":"43","author":[{"given":"Qing","family":"Yang","sequence":"first","affiliation":[{"name":"Southwest Petroleum University"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7908-3985","authenticated-orcid":false,"given":"Ju","family":"Chen","sequence":"additional","affiliation":[{"name":"Southwest Petroleum University"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southwest Petroleum University"}]},{"given":"Liang","family":"Ge","sequence":"additional","affiliation":[{"name":"Southwest Petroleum University"}]},{"given":"Yun Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Southwest Petroleum University"}]}],"member":"56","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"S0263574725102993_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3175484"},{"key":"S0263574725102993_ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-015-0455-7"},{"key":"S0263574725102993_ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.2999847"},{"key":"S0263574725102993_ref10","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211042730"},{"key":"S0263574725102993_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3283266"},{"key":"S0263574725102993_ref17","first-page":"1556","article-title":"Manipulator trajectory planning based on clustering curve discretization and B-spline","author":"Peng","year":"2024","journal-title":"J. Field Robot."},{"key":"S0263574725102993_ref12","first-page":"1","article-title":"Bio-inspired BAS: Run-time path-planning and the control of differential mobile robot","author":"Khan","year":"2022","journal-title":"EAI Endors. Trans. AI Robot."},{"key":"S0263574725102993_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990555"},{"key":"S0263574725102993_ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s23104642"},{"key":"S0263574725102993_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3258186"},{"key":"S0263574725102993_ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124281"},{"key":"S0263574725102993_ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108488"},{"key":"S0263574725102993_ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3083724"},{"key":"S0263574725102993_ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2024.3377002"},{"key":"S0263574725102993_ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3173404"},{"key":"S0263574725102993_ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2841-y"},{"key":"S0263574725102993_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3269462"},{"key":"S0263574725102993_ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.01.008"},{"key":"S0263574725102993_ref24","doi-asserted-by":"publisher","DOI":"10.1115\/1.4065814"},{"key":"S0263574725102993_ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"S0263574725102993_ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3507208"},{"key":"S0263574725102993_ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919890396"},{"key":"S0263574725102993_ref19","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574723000607"},{"key":"S0263574725102993_ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2916932"},{"key":"S0263574725102993_ref30","doi-asserted-by":"publisher","DOI":"10.1109\/56.2083"},{"key":"S0263574725102993_ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3160605"},{"key":"S0263574725102993_ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9816-8"},{"key":"S0263574725102993_ref23","unstructured":"[23] Cao, Y. X. , Wang, S. J. , Zheng, X. and Liu, L. , \u201cPlanning and Control of Space Robot in Capture Operation Based on Reinforcement Learning,\u201d In: Chinese Control Conference, Shanghai, July 26\u201328 2021)."},{"key":"S0263574725102993_ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2024.3413833"},{"key":"S0263574725102993_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2941916"},{"key":"S0263574725102993_ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3379361"},{"key":"S0263574725102993_ref18","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574723001613"}],"container-title":["Robotica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0263574725102993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T12:25:26Z","timestamp":1771590326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0263574725102993\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":32,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["S0263574725102993"],"URL":"https:\/\/doi.org\/10.1017\/s0263574725102993","relation":{},"ISSN":["0263-5747","1469-8668"],"issn-type":[{"value":"0263-5747","type":"print"},{"value":"1469-8668","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}