{"id":238,"date":"2025-02-17T05:16:35","date_gmt":"2025-02-17T05:16:35","guid":{"rendered":"https:\/\/chinaservicerobots.com\/?p=238"},"modified":"2025-02-17T05:16:35","modified_gmt":"2025-02-17T05:16:35","slug":"target-position-guided-in-hand-re-orientation-for-five-fingered-dexterous-hands","status":"publish","type":"post","link":"https:\/\/chinaservicerobots.com\/zh\/target-position-guided-in-hand-re-orientation-for-five-fingered-dexterous-hands\/","title":{"rendered":"Target Position-guided In-hand Re-orientation for Five-fingered Dexterous Hands"},"content":{"rendered":"<table class=\"article-tab\">\n<tbody>\n<tr>\n<td valign=\"top\" width=\"70\"><span class=\"\"><b>Citation:<\/b><\/span><\/td>\n<td><span id=\"infoEn\" class=\"info\">ZHANG Lingjun, TANG Liang, LIU Lei. Target Position-guided In-hand Re-orientation for Five-fingered Dexterous Hands[J].\u00a0<i>ROBOT<\/i>, 2025, 47(1): 10-21.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.240019\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.240019<\/a><\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<div class=\"article-left\">\n<div id=\"articleEnMeta\" class=\"articleEn loaded\">\n<div class=\"article-title\">\n<h1><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium\" src=\"https:\/\/robot.sia.cn\/fileJQR\/journal\/article\/jqr\/2025\/1\/3fc54037-a33b-47be-a4c9-0a7395d24176.jpg\" width=\"472\" height=\"354\" \/><\/h1>\n<h1>Target Position-guided In-hand Re-orientation for Five-fingered Dexterous Hands<\/h1>\n<\/div>\n<ul class=\"article-author clear\">\n<li><a class=\"mainColor \" data-relate=\"\">ZHANG Lingjun<\/a><sup class=\"authorTag\"><span class=\"com-num mainColor\" data-tagval=\"aff1\">1<\/span><\/sup>,<\/li>\n<li><a class=\"mainColor \" data-relate=\"tl614@sina.com\">TANG Liang<\/a><sup class=\"authorTag\"><span class=\"com-num mainColor\" data-tagval=\"aff1, aff2\">1, 2<\/span>,\u00a0,\u00a0<\/sup>,<\/li>\n<li><a class=\"mainColor \" data-relate=\"\">LIU Lei<\/a><sup class=\"authorTag\"><span class=\"com-num mainColor\" data-tagval=\"aff1, aff2\">1, 2<\/span><\/sup><\/li>\n<\/ul>\n<ul class=\"about-author addresswrap\">\n<li class=\"article-author-address\" data-afftagid=\"aff1\"><span class=\"\">1.<\/span>Beijing Institute of Control Engineering, Beijing 100094, China<\/li>\n<li class=\"article-author-address\" data-afftagid=\"aff2\"><span class=\"\">2.<\/span>Science and Technology on Space Intelligent Control Laboratory, Beijing 100094, China<\/li>\n<\/ul>\n<p><a class=\"togglebtn mainColor\"><i class=\"articleFont icon-jia\"><\/i>More Information<\/a><\/div>\n<\/div>\n<ul id=\"myTabContent\" class=\"article-tab-box tab-content article-box-content\">\n<li id=\"GraphicalAbstract\" class=\"articleListBox loaded\">\n<h3 id=\"Abstract-list\" class=\"navTitle visible-lg\">Abstract<\/h3>\n<div id=\"8e61d382-120b-400c-9962-357291e5f9f0_abs_div_0\" class=\"article-abstract \">Re-orientation involves rotating an object to a target configuration, with the most challenging case being the rotation from an arbitrary initial configuration to an arbitrary target configuration. To address the challenge of efficiently performing in-hand re-orientation tasks in a more human-like manner by guiding anthropomorphic five-fingered dexterous hands with different degrees of actuation (DoA), a target position-guided in-hand object re-orientation policy generation method is proposed. Firstly, a feasible principle for designing target positions is proposed, inspired by the operation characteristics of human hands during in-hand re-orientation and based on the distribution characteristics of DoA in anthropomorphic five-fingered dexterous hands. The difference between the actual and target positions of the object during re-orientation process is utilized as a component of the immediate reward to guide anthropomorphic five-fingered dexterous hands in maintaining the object near the target. Secondly, a method is developed inspired by the preparatory states of human hands before performing re-orientation tasks, to sample the joint positions of anthropomorphic five-fingered dexterous hands when resetting the state everytime, aiming to enhance manipulation capabilities. Finally, the re-orientation policy is trained using the proximal policy optimization (PPO) algorithm based on the long short-term memory (LSTM) network and asymmetric actor-critic architecture. Simulation results show that the proposed method enables the 9-DoA Schunk SVH dexterous hand, the 13-DoA BICE dexterous hand developed by Beijing Institute of Control Engineering (BICE), and the 18-DoA Shadow dexterous hand to approach the predefined maximum number of consecutive successes when performing re-orientation tasks. Moreover, compared with in-hand object re-orientation policy generation method without target position guidance, the proposed method significantly reduces the average number of steps required to perform re-orientation tasks. The proposed method enables anthropomorphic five-fingered dexterous hands with different DoA to efficiently perform object re-orientation tasks in a human-like manner through coordinated action of the palm and fingers, significantly enhancing operational efficiency.\u00a0<span id=\"icon_8e61d382-120b-400c-9962-357291e5f9f0_abs_div_0\" class=\"translate-icon\" title=\"Translate this paragraph\"><\/span><\/div>\n<p><b>Keywords:<\/b><\/p>\n<ul class=\"article-keyword article-info-en\">\n<li><a class=\"underHigh mainColor\">dexterous manipulation<\/a>,<\/li>\n<li><a class=\"underHigh mainColor\">in-hand manipulation<\/a>,<\/li>\n<li><a class=\"underHigh mainColor\">object re-orientation<\/a>,<\/li>\n<li><a class=\"underHigh mainColor\">five-fingered dexterous hand<\/a>,<\/li>\n<li><a class=\"underHigh mainColor\">reinforcement learning<\/a><\/li>\n<\/ul>\n<\/li>\n<li id=\"FullText\" class=\"articleListBox FullText-all html-text\">\n<div class=\"appendix-html\"><\/div>\n<div class=\"acks-html\"><\/div>\n<\/li>\n<li id=\"References\" class=\"articleListBox loaded\">\n<h3 id=\"References-list\" class=\"navTitle\">References<\/h3>\n<div class=\"References-wrap\">\n<table class=\"reference-tab\">\n<tbody>\n<tr id=\"b1\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[1]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">BICCHI A. Hands for dexterous manipulation and robust grasping: A difficult road toward simplicity[J]. IEEE Transactions on Robotics and Automation, 2000, 16(6): 652-662.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1109\/70.897777\" target=\"_blank\" rel=\"noopener\">10.1109\/70.897777<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b2\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[2]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">KUMAR V, TODOROV E, LEVINE S. Optimal control with learned local models: Application to dexterous manipulation[C]\/\/ IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2016: 378-383.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1109\/ICRA.2016.7487156\" target=\"_blank\" rel=\"noopener\">10.1109\/ICRA.2016.7487156<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b3\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[3]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">RAJESWARAN A, KUMAR V, GUPTA A, et al. Learning complex dexterous manipulation with deep reinforcement learning and demonstrations[C]\/\/Robotics: Science and Systems XIV. 2018.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.15607\/RSS.2018.XIV.049\" target=\"_blank\" rel=\"noopener\">10.15607\/RSS.2018.XIV.049<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b4\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[4]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">NAGABANDI A, KONOLIGE K, LEVINE S, et al. Deep dynamics models for learning dexterous manipulation[C]\/\/Proceedings of the Conference on Robot Learning. 2020: 1101-1112.\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/proceedings.mlr.press\/v100\/nagabandi20a.html\" target=\"_blank\" rel=\"noopener\">https:\/\/proceedings.mlr.press\/v100\/nagabandi20a.html<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b5\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[5]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">ANDRYCHOWICZ M, BAKER B, CHOCIEJ M, et al. Learning dexterous in-hand manipulation[J]. International Journal of Robotics Research, 2020, 39(1): 3-20.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1177\/0278364919887447\" target=\"_blank\" rel=\"noopener\">10.1177\/0278364919887447<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b6\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[6]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">CHEN T, XU J, AGRAWAL P. A system for general in-hand object re-orientation[C]\/\/Proceedings of the 5th Conference on Robot Learning. 2022: 297-307.\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/proceedings.mlr.press\/v164\/chen22a.html\" target=\"_blank\" rel=\"noopener\">https:\/\/proceedings.mlr.press\/v164\/chen22a.html<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b7\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[7]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">CHEN T, TIPPUR M, WU S, et al. Visual dexterity: In-hand re-orientation of novel and complex object shapes[J]. Science Robotics, 2023, 8(84).\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1126\/scirobotics.adc9244\" target=\"_blank\" rel=\"noopener\">10.1126\/scirobotics.adc9244<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b8\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[8]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">HUANG W, MORDATCH I, ABBEEL P, et al. Generalization in dexterous manipulation via geometry-aware multi-task learning[DB\/OL]. (2021-11-04) [2024-01-02].\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.48550\/arXiv.2111.03062\" target=\"_blank\" rel=\"noopener\">10.48550\/arXiv.2111.03062<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b9\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[9]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">PETRENKO A, ALLSHIRE A, STATE G, et al. DexPBT: Scaling up dexterous manipulation for hand-arm systems with population based training[C]\/\/Robotics: Science and Systems XIX. 2023.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.15607\/RSS.2023.XIX.037\" target=\"_blank\" rel=\"noopener\">10.15607\/RSS.2023.XIX.037<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b10\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[10]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">MA Y J, LIANG W, WANG G, et al. Eureka: Human-level reward design via coding large language models][DB\/OL]. (2023-10-06) [2024-03-28].\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/arxiv.org\/abs\/2310.12931\" target=\"_blank\" rel=\"noopener\">https:\/\/arxiv.org\/abs\/2310.12931<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b11\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[11]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">KHANDATE G, HAAS-HEGER M, CIOCARLIE M. On the feasibility of learning finger-gaiting in-hand manipulation with intrinsic sensing[C]\/\/International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2022: 2752-2758.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1109\/ICRA46639.2022.9812212\" target=\"_blank\" rel=\"noopener\">10.1109\/ICRA46639.2022.9812212<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b12\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[12]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">KHANDATE G, SHANG S, CHANG E T, et al. Sampling-based exploration for reinforcement learning of dexterous manipulation[DB\/OL]. (2023-05-23) [2024-01-20].\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/arxiv.org\/abs\/2303.03486\" target=\"_blank\" rel=\"noopener\">https:\/\/arxiv.org\/abs\/2303.03486<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b13\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[13]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">XU Y Z, WAN W K, ZHANG J L, et al. UniDexGrasp: Universal robotic dexterous grasping via learning diverse proposal generation and goal-conditioned policy[C]\/\/IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2023: 4737-4746.<\/div>\n<\/td>\n<\/tr>\n<tr id=\"b14\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[14]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">Shadow Robot Company. Shadow robot dexterous hand] [EB \/OL]. (2011-07-25) [2023-12-18].\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/www.shadowrobot.com\/dexterous-hand-series\/\" target=\"_blank\" rel=\"noopener\">https:\/\/www.shadowrobot.com\/dexterous-hand-series\/<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b15\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[15]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">Schunk SE &#038; Co. KG. SVH 5-finger hand][EB\/OL]. (2022-12-01) [2023-12-19].\u00a0<a class=\"mainColor ref-url \" href=\"http:\/\/wiki.ros.org\/schunk_svh_driver\" target=\"_blank\" rel=\"noopener\">http:\/\/wiki.ros.org\/schunk_svh_driver<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b16\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[16]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[DB\/OL]. (2017-08-28) [2023-12-19].\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.48550\/arXiv.1707.06347\" target=\"_blank\" rel=\"noopener\">10.48550\/arXiv.1707.06347<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b17\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[17]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">HOCHREITER S, SCHMIDHUBER J. Long short-term memory][J]. Neural Computation, 1997, 9(8): 1735-1780.\u00a0doi:\u00a0<a class=\"mainColor ref-doi \" href=\"https:\/\/dx.doi.org\/10.1162\/neco.1997.9.8.1735\" target=\"_blank\" rel=\"noopener\">10.1162\/neco.1997.9.8.1735<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b18\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[18]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">MAKOVIYCHUK V, WAWRZYNIAK L, GUO Y, et al. Isaac Gym: High performance GPU-based physics simulation for robot learning[DB\/OL]. (2021-08-24)[2023-12-19].\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/arxiv.org\/abs\/2108.10470\" target=\"_blank\" rel=\"noopener\">https:\/\/arxiv.org\/abs\/2108.10470<\/a><\/div>\n<\/td>\n<\/tr>\n<tr id=\"b19\" class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[19]<\/td>\n<td class=\"td2\">\n<div class=\"reference-en\">NAIR V, HINTON G E. Rectified linear units improve restricted Boltzmann machines][C]\/\/International Conference on Machine Learning. 2010: 807-814.\u00a0<a class=\"mainColor ref-url \" href=\"https:\/\/api.semanticscholar.org\/CorpusID:%2015539264\" target=\"_blank\" rel=\"noopener\">https:\/\/api.semanticscholar.org\/CorpusID: 15539264<\/a><\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/li>\n<li id=\"RelatedPages\" class=\"articleListBox\">\n<h3 id=\"relative-article\" class=\"navTitle\">Related Articles<\/h3>\n<table class=\"reference-tab\">\n<tbody>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[1]<\/td>\n<td class=\"td2\">FANG Baofu, YU Tingting, WANG Hao, WANG Zaijun.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.240021\" target=\"_blank\" rel=\"noopener\">Multi-agent Reinforcement Learning Based on Adaptive State Approximation in Sparse Reward Scenarios<\/a>[J]. ROBOT, 2024, 46(6): 663-671, 682.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.240021\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.240021<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[2]<\/td>\n<td class=\"td2\">ZHANG Zhenyi, HUANG Jie.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.230148\" target=\"_blank\" rel=\"noopener\">Reinforcement Learning Mission Supervisor Design for Behavior-based Differential Drive Robots<\/a>[J]. ROBOT, 2024, 46(4): 397-413, 424.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.230148\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.230148<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[3]<\/td>\n<td class=\"td2\">SHUANG Feng, LU Wanyu, LI Shaodong, YUAN Xiaogang.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.220011\" target=\"_blank\" rel=\"noopener\">Robotic Peg-in-hole Assembly Algorithm Based on Reinforcement Learning<\/a>[J]. ROBOT, 2023, 45(3): 321-332.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.220011\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.220011<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[4]<\/td>\n<td class=\"td2\">CHEN Jiapan, ZHENG Minhua.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.210008\" target=\"_blank\" rel=\"noopener\">A Survey of Robot Manipulation Behavior Research Based on Deep Reinforcement Learning<\/a>[J]. ROBOT, 2022, 44(2): 236-256.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.210008\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.210008<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[5]<\/td>\n<td class=\"td2\">DUO Nanxun, L&#220; Qiang, LIN Huican, WEI Heng.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.180336\" target=\"_blank\" rel=\"noopener\">Step into High-Dimensional and Continuous Action Space: A Survey on Applications of Deep Reinforcement Learning to Robotics<\/a>[J]. ROBOT, 2019, 41(2): 276-288.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.180336\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.180336<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[6]<\/td>\n<td class=\"td2\">DU Zhijiang, WANG Wei, YAN Zhiyuan, DONG Wei, WANG Weidong.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/doi\/10.13973\/j.cnki.robot.2017.0363\" target=\"_blank\" rel=\"noopener\">A Physical Human-Robot Interaction Algorithm Based on Fuzzy Reinforcement Learning for Minimally Invasive Surgery Manipulator<\/a>[J]. ROBOT, 2017, 39(3): 363-370.\u00a0DOI:\u00a0<a class=\"mainColor\" href=\"https:\/\/dx.doi.org\/10.13973\/j.cnki.robot.2017.0363\" target=\"_blank\" rel=\"noopener\">10.13973\/j.cnki.robot.2017.0363<\/a><\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[7]<\/td>\n<td class=\"td2\">LI Jun, PAN Qi-shu, HONG Bing-rong.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/id\/2846\" target=\"_blank\" rel=\"noopener\">A CBR-Based Multiagent Reinforcement Learning Approach<\/a>[J]. ROBOT, 2009, 31(4): 320-326.<\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[8]<\/td>\n<td class=\"td2\">DUAN Yong, YANG Huai-qing, CUI Bao-xia, XU Xin-he.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/id\/871\" target=\"_blank\" rel=\"noopener\">Application of Reinforcement Learning to Basic Action Learning of Soccer Robot<\/a>[J]. ROBOT, 2008, 30(5): 453-459.<\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[9]<\/td>\n<td class=\"td2\">CHEN Wei-dong, XI Yu-geng, GU Dong-lei.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/id\/323\" target=\"_blank\" rel=\"noopener\">A SURVEY OF REINFORCEMENT LEARNING IN AUTONOMOUS MOBILE ROBOTS<\/a>[J]. ROBOT, 2001, 23(4): 379-384.<\/td>\n<\/tr>\n<tr class=\"document-box\">\n<td class=\"td1\" valign=\"top\">[10]<\/td>\n<td class=\"td2\">ZHANG Rubo, ZHOU Ning, GU Guochang, ZHANG Guoyin.\u00a0<a class=\"\" href=\"https:\/\/robot.sia.cn\/en\/article\/id\/1110\" target=\"_blank\" rel=\"noopener\">REINFORCEMENT-LEARNING-BASED OBSTACLE AVOIDANCE LEARNING FOR INTELLIGENT ROBOT<\/a>[J]. ROBOT, 1999, 21(3): 204-209.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Target Position-guided In-hand Re-orientation for Five-fingered Dexterous Hands<br \/>\nRe-orientation involves rotating an object to a target configuration, with the most challenging case being the rotation from an arbitrary initial configuration to an arbitrary target configuration. To address the challenge of efficiently performing in-hand re-orientation tasks in a more human-like manner by guiding anthropomorphic five-fingered dexterous hands with different degrees of actuation (DoA),<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"zakra_page_container_layout":"customizer","zakra_page_sidebar_layout":"customizer","zakra_remove_content_margin":false,"zakra_sidebar":"customizer","zakra_transparent_header":"customizer","zakra_logo":0,"zakra_main_header_style":"default","zakra_menu_item_color":"","zakra_menu_item_hover_color":"","zakra_menu_item_active_color":"","zakra_menu_active_style":"","zakra_page_header":true,"footnotes":""},"categories":[72],"tags":[162],"class_list":["post-238","post","type-post","status-publish","format-standard","hentry","category-robot-new","tag-target-position-guided-in-hand-re-orientation-for-five-fingered-dexterous-hands"],"_links":{"self":[{"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/posts\/238","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/comments?post=238"}],"version-history":[{"count":0,"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/posts\/238\/revisions"}],"wp:attachment":[{"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/media?parent=238"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/categories?post=238"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/chinaservicerobots.com\/zh\/wp-json\/wp\/v2\/tags?post=238"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}