{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:05:21Z","timestamp":1774602321267,"version":"3.50.1"},"reference-count":29,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T00:00:00Z","timestamp":1627344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IR"],"published-print":{"date-parts":[[2022,1,3]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>As complex analysis of contact models is required in the traditional assembly strategy, it is still a challenge for a robot to complete the multiple peg-in-hole assembly tasks autonomously. This paper aims to enable the robot to complete the assembly tasks autonomously and more efficiently, with the strategies learned by reinforcement learning (RL), a learning-accelerated deep deterministic policy gradient (LADDPG) algorithm is proposed.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>The multiple peg-in-hole assembly strategy is designed in two modules: an advanced planning module and a bottom control module. The advanced module is completed by the LADDPG agent, which is used to derive advanced commands based on geometric and environmental constraints, that is, the desired contact force. The bottom-level control module will drive the robot to complete the compliant assembly task through the adaptive impedance algorithm according to the command set issued by the advanced module. In addition, a set of safety assurance mechanisms is developed to safely train a collaborative robot to complete autonomous learning.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>The method can complete the assembly tasks well through RL, and it can realize satisfactory compliance of the robot to the environment. Compared with the original DDPG algorithm, the average values of the instantaneous maximum contact force and contact torque during the assembly process are reduced by approximately 38% and 74%, respectively.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title>\n<jats:p>The entire algorithm can also be applied to other robots and the assembly strategy can be applied in the field of the automatic assembly.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>A compliant assembly strategy based on the LADDPG algorithm is proposed to complete the automated multiple peg-in-hole assembly tasks.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ir-01-2021-0003","type":"journal-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T06:25:00Z","timestamp":1627453500000},"page":"54-64","source":"Crossref","is-referenced-by-count":17,"title":["Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy"],"prefix":"10.1108","volume":"49","author":[{"given":"Xinwang","family":"Li","sequence":"first","affiliation":[]},{"given":"Juliang","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Haitao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Guodong","family":"Wang","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2021,7,27]]},"reference":[{"issue":"19","key":"key2021123108212363800_ref001","article-title":"Variable compliance control for robotic peg-in-hole assembly: a deep-reinforcement-learning approach","volume":"10","year":"2020","journal-title":"Applied Sciences"},{"issue":"4","key":"key2021123108212363800_ref002","doi-asserted-by":"crossref","first-page":"5709","DOI":"10.1109\/LRA.2020.3010739","article-title":"Learning force control for contact-rich manipulation tasks with rigid position-controlled robots","volume":"5","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"key":"key2021123108212363800_ref003","unstructured":"Brittain, M., Bertram, J., Yang, X. and Wei, P. (2019), \u201cPrioritized sequence experience replay\u201d, available at: https:\/\/arxiv.org\/abs\/1905.12726"},{"issue":"7","key":"key2021123108212363800_ref004","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1177\/0278364911402527","article-title":"Learning variable impedance control","volume":"30","year":"2011","journal-title":"The International Journal of Robotics Research"},{"key":"key2021123108212363800_ref005","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1109\/ICRA.2019.8793659","article-title":"A learning framework for high precision industrial assembly","volume-title":"2019 International Conference on Robotics and Automation (ICRA)","year":"2019"},{"issue":"5","key":"key2021123108212363800_ref006","first-page":"125","article-title":"Deep reinforcement learning with double Q-learning","volume":"2","year":"2015","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"key2021123108212363800_ref007","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/ROBIO.2018.8665255","article-title":"Knowledge-driven deep deterministic policy gradient for robotic multiple peg-in-hole assembly tasks","volume-title":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","year":"2018"},{"key":"key2021123108212363800_ref008","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1109\/IROS.2017.8202244","article-title":"Deep reinforcement learning for high precision assembly tasks","volume-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","year":"2017"},{"key":"key2021123108212363800_ref009","doi-asserted-by":"publisher","first-page":"101863","DOI":"10.1016\/j.rcim.2019.101863","article-title":"Reinforcement learning based on movement primitives for contact tasks","volume":"62","year":"2020","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"issue":"11","key":"key2021123108212363800_ref010","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: a survey","volume":"32","year":"2013","journal-title":"The International Journal of Robotics Research"},{"key":"key2021123108212363800_ref011","doi-asserted-by":"crossref","first-page":"6282","DOI":"10.1109\/ACCESS.2019.2934174","article-title":"Manipulation skill acquisition for robotic assembly based on multi-modal information description","volume":"8","year":"2020","journal-title":"IEEE Access"},{"issue":"6","key":"key2021123108212363800_ref012","first-page":"A187","article-title":"Continuous control with deep reinforcement learning","volume":"8","year":"2015","journal-title":"Computer Science"},{"key":"key2021123108212363800_ref013","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/AIM.2019.8868579","article-title":"Manipulation skill acquisition for robotic assembly using deep reinforcement learning","volume-title":"2019 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","year":"2019"},{"key":"key2021123108212363800_ref014","volume-title":"Modern Robotics: Mechanics, Planning, and Control","year":"2017"},{"issue":"7540","key":"key2021123108212363800_ref015","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","year":"2015","journal-title":"Nature"},{"issue":"6","key":"key2021123108212363800_ref016","article-title":"Learning-based variable compliance control for robotic assembly","volume":"10","year":"2018","journal-title":"Journal of Mechanisms Robotics"},{"key":"key2021123108212363800_ref017","article-title":"Prioritized experience replay","year":"2016"},{"issue":"2","key":"key2021123108212363800_ref018","first-page":"264","article-title":"Autonomous robust skill generation using reinforcement learning with plant variation","volume":"6","year":"2014","journal-title":"Advances in Mechanical Engineering"},{"key":"key2021123108212363800_ref019","first-page":"I-387","article-title":"Deterministic policy gradient algorithms","year":"2014"},{"issue":"6","key":"key2021123108212363800_ref020","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1108\/IR-07-2016-0186","article-title":"Study on dual peg-in-hole insertion using of constraints formed in the environment","volume":"44","year":"2017","journal-title":"Industrial Robot: An International Journal"},{"key":"key2021123108212363800_ref021","volume-title":"Reinforcement Learning: An Introduction","year":"1998"},{"key":"key2021123108212363800_ref022","first-page":"V002T27A002","article-title":"A learning-based framework for robot peg-hole-insertion","year":"2015"},{"key":"key2021123108212363800_ref023","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1109\/RCAR47638.2019.9043958","article-title":"Actor-critic method-based search strategy for high precision peg-in-hole tasks","volume-title":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","year":"2019"},{"issue":"2","key":"key2021123108212363800_ref024","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1108\/IR-11-2017-0193","article-title":"Smooth transition adaptive hybrid impedance control for connector assembly","volume":"45","year":"2018","journal-title":"Industrial Robot: An International Journal"},{"key":"key2021123108212363800_ref025","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1109\/COASE.2019.8842940","article-title":"Deep reinforcement learning of robotic precision insertion skill accelerated by demonstrations","volume-title":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","year":"2019"},{"key":"key2021123108212363800_ref026","unstructured":"Xu, J., Hou, Z., Liu, Z. and Qiao, H. (2019), \u201cCompare contact model-based control and contact model-free learning: a survey of robotic peg-in-hole assembly strategies\u201d, available at: https:\/\/arxiv.org\/abs\/1904.05240"},{"key":"key2021123108212363800_ref027","doi-asserted-by":"crossref","first-page":"108795","DOI":"10.1109\/ACCESS.2019.2931515","article-title":"Force\/torque sensorless compliant control strategy for assembly tasks using a 6-DOF collaborative robot","volume":"7","year":"2019","journal-title":"IEEE Access"},{"issue":"2","key":"key2021123108212363800_ref028","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1108\/AA-09-2016-120","article-title":"Force control for a rigid dual peg-in-hole assembly","volume":"37","year":"2017","journal-title":"Assembly Automation"},{"issue":"2","key":"key2021123108212363800_ref029","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1007\/s41315-020-00138-z","article-title":"Model accelerated reinforcement learning for high precision robotic assembly","volume":"4","year":"2020","journal-title":"International Journal of Intelligent Robotics and Applications"}],"container-title":["Industrial Robot: the international journal of robotics research and application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-01-2021-0003\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-01-2021-0003\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:38:13Z","timestamp":1753393093000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ir\/article\/49\/1\/54-64\/183670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,27]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,7,27]]},"published-print":{"date-parts":[[2022,1,3]]}},"alternative-id":["10.1108\/IR-01-2021-0003"],"URL":"https:\/\/doi.org\/10.1108\/ir-01-2021-0003","relation":{},"ISSN":["0143-991X","0143-991X"],"issn-type":[{"value":"0143-991X","type":"print"},{"value":"0143-991X","type":"print"}],"subject":[],"published":{"date-parts":[[2021,7,27]]}}}