{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:38:56Z","timestamp":1760575136263,"version":"build-2065373602"},"reference-count":29,"publisher":"Emerald","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,16]]},"abstract":"<jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>In response to the complex external structure of high-precision aviation plugs, which makes it difficult to search outside the hole and adjust inside the hole during automated assembly. This paper aims to propose an assembly framework that combines multi-agent search and variable parameter compliant control to solve this problem.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design\/methodology\/approach<\/jats:title>\n                  <jats:p>First, a multi-agent search strategy (MAS) based on Gaussian Mixture Model and Deep Q-Network was proposed to optimize displacement direction and actions, thereby improving search speed and success rate. Then, a variable parameter admittance control method (RL-VPA) based on dual delay depth deterministic policy gradient (TD3) was proposed, which dynamically optimized the internal parameters of the admittance controller and adopted state space discretization to improve convergence speed and assembly efficiency.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>Compared to spiral search and single-agent search, the average search success rate has improved by approximately 10% and 6.6%. Compared to fixed admittance control and other RL-based methods, the average assembly success rate has increased by approximately 38.6%, 22% and 8.6%. Compared with the training results of the model without state discretization, it was found that state discretization helps the model converge quickly. To verify the generalization ability of the assembly framework, experiments were conducted on three different pin counts of aviation plugs, the assembly success rate reached 86.7%, all of which showed good assembly results. Finally, combining state space discretization to reduce the impact of environmental noise, improve training effectiveness and convergence speed.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Originality\/value<\/jats:title>\n                  <jats:p>MAS has been proposed to optimize displacement direction and action, improving search speed and success rate. RL-VPA is designed to dynamically optimize the internal parameters of the admittance controller, enhancing the robustness and generalization ability of the model. Additionally, state space discretization is combined to improve training effectiveness and convergence speed.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1108\/ir-09-2024-0436","type":"journal-article","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T23:09:47Z","timestamp":1737760187000},"page":"639-650","source":"Crossref","is-referenced-by-count":0,"title":["Compliant assembly of complex aviation plugs combining multi-agent search and variable parameters"],"prefix":"10.1108","volume":"52","author":[{"given":"Zhenghai","family":"Liu","sequence":"first","affiliation":[{"name":"Dalian University of Technology , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Tang","sequence":"additional","affiliation":[{"name":"China Airborne Missile Academy , Luoyang,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingji","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyue","family":"Zhu","sequence":"additional","affiliation":[{"name":"Dalian Jiaotong University , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Du","sequence":"additional","affiliation":[{"name":"Dalian Jiaotong University , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojing","family":"Tian","sequence":"additional","affiliation":[{"name":"Dalian Jiaotong University , Dalian,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Cong","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , Dalian, and Dalian University of Technology Ningbo Research Institute, NingBo, China","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"2025101507172803000_ref001","doi-asserted-by":"crossref","first-page":"104399","DOI":"10.1016\/j.robot.2023.104399","article-title":"Robotic assembly strategy via reinforcement learning based on force and visual information","volume":"164","author":"Ahn","year":"2023","journal-title":"Robotics and Autonomous Systems"},{"issue":"19","key":"2025101507172803000_ref002","doi-asserted-by":"crossref","first-page":"6923","DOI":"10.3390\/app10196923","article-title":"Variable compliance control for robotic peg-in-hole assembly a deep-reinforcement-learning approach","volume":"10","author":"Beltran-Hernandez","year":"2020","journal-title":"Applied Sciences"},{"key":"2025101507172803000_ref003","first-page":"589","article-title":"Single force-guided precision peg-in-hole search of cylindrical part with small lengthdiameter ratio","author":"BIN Zhou","year":"2018"},{"issue":"4","key":"2025101507172803000_ref004","doi-asserted-by":"crossref","first-page":"6129","DOI":"10.1109\/LRA.2020.3011379","article-title":"Learning variable impedance control for contact sensitive tasks","volume":"5","author":"Bogdanovic","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"2","key":"2025101507172803000_ref005","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s41315-020-00136-1","article-title":"Integrating combined task and motion planning with compliant control","volume":"4","author":"Chen","year":"2020","journal-title":"International Journal of Intelligent Robotics and Applications"},{"key":"2025101507172803000_ref006","doi-asserted-by":"crossref","DOI":"10.1016\/j.isatra.2024.09.008","article-title":"Adaptive impedance control for docking robot via stewart parallel mechanism","volume":"155","author":"Chen","year":"2024","journal-title":"ISA Transactions"},{"key":"2025101507172803000_ref007","article-title":"LiDAR depth cluster active detection and localization for a UAV with partial information loss in GNSS","author":"Deng","year":"2024","journal-title":"Unmanned Systems"},{"key":"2025101507172803000_ref008","first-page":"405","article-title":"Self-supervised deep visual servoing for high precision peg-in-hole insertion","author":"Haugaard","year":"2022"},{"issue":"1","key":"2025101507172803000_ref009","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/TASE.2020.3024725","article-title":"Fuzzy logic-driven variable time-scale prediction-based reinforcement learning for robotic multiple peg-in-hole assembly","volume":"19","author":"Hou","year":"2022","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"2025101507172803000_ref010","doi-asserted-by":"crossref","first-page":"102366","DOI":"10.1016\/j.rcim.2022.102366","article-title":"A review of robotic assembly strategies for the full operation procedure: planning, execution and evaluation","volume":"78","author":"Jiang","year":"2022","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"key":"2025101507172803000_ref011","first-page":"6023","article-title":"Residual reinforcement learning for robot control","author":"Johannink","year":"2019"},{"issue":"3","key":"2025101507172803000_ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LRA.2022.3176718","article-title":"Uncertainty-driven spiral trajectory for robotic peg-in-hole assembly","volume":"7","author":"Kang","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2025101507172803000_ref013","first-page":"833","article-title":"Reinforcement learning-based sim-to-real impedance parameter tuning for robotic assembly","author":"Kim","year":"2021"},{"issue":"4","key":"2025101507172803000_ref014","doi-asserted-by":"crossref","first-page":"10898","DOI":"10.1109\/LRA.2022.3191070","article-title":"Reinforcement learning of impedance policies for peg-in-hole tasks: role of asymmetric matrices","volume":"7","author":"Kozlovsky","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2025101507172803000_ref015","article-title":"Integrating force-based manipulation primitives with deep learning-based visual servoing for robotic assembly","volume-title":"ICRA 2022 Workshop: Reinforcement Learning for Contact-Rich Manipulation.","author":"Lee","year":"2022"},{"issue":"4","key":"2025101507172803000_ref016","doi-asserted-by":"crossref","first-page":"8566","DOI":"10.1109\/LRA.2022.3187497","article-title":"Peg-in-hole assembly with Dual-Arm robot and dexterous robot hands","volume":"7","author":"Lee","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"16","key":"2025101507172803000_ref017","doi-asserted-by":"crossref","first-page":"7394","DOI":"10.3390\/app11167394","article-title":"Robotic assembly for irregular shaped peg-in-hole with partial constraints","volume":"11","author":"Li","year":"2021","journal-title":"Applied Sciences"},{"issue":"12","key":"2025101507172803000_ref018","doi-asserted-by":"crossref","DOI":"10.3390\/s21124064","article-title":"A coarse-to-fine method for estimating the axis pose based on 3D point clouds in robotic cylindrical shaft-in-hole assembly","volume":"21","author":"Li","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"3","key":"2025101507172803000_ref019","doi-asserted-by":"crossref","first-page":"4447","DOI":"10.1109\/LRA.2020.3000428","article-title":"Compliant peg-in-hole assembly using partial spiral force trajectory with tilted peg posture","volume":"5","author":"Park","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2025101507172803000_ref020","first-page":"5548","article-title":"Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards","author":"Schoettler","year":"2020"},{"issue":"8","key":"2025101507172803000_ref021","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1080\/01691864.2015.1130172","article-title":"Guidance algorithm for complex-shape peg-in-hole strategy based on geometrical information and force control","volume":"30","author":"Song","year":"2016","journal-title":"Advanced Robotics"},{"issue":"3","key":"2025101507172803000_ref022","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.3390\/app10031157","article-title":"A robotic automatic assembly system based on vision","volume":"10","author":"Song","year":"2020","journal-title":"Applied Sciences"},{"key":"2025101507172803000_ref023","doi-asserted-by":"crossref","first-page":"103651","DOI":"10.1016\/j.robot.2020.103651","article-title":"Skill learning for robotic assembly based on visual perspectives and force sensing","volume":"135","author":"Song","year":"2021","journal-title":"Robotics and Autonomous Systems"},{"key":"2025101507172803000_ref024","article-title":"Autonomous assembly method of 3-Arm robot to fix the multipin and hole load plate on a space station","volume":"2021","author":"Sun","year":"2021","journal-title":"Space: science & Technology"},{"key":"2025101507172803000_ref025","doi-asserted-by":"crossref","first-page":"60175","DOI":"10.1109\/ACCESS.2021.3073711","article-title":"Hybrid trajectory and force learning of complex assembly tasks: a combined learning framework","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"issue":"16","key":"2025101507172803000_ref026","doi-asserted-by":"crossref","first-page":"26407","DOI":"10.1109\/JSEN.2024.3424218","article-title":"LCDL: toward dynamic localization for autonomous landing of unmanned aerial vehicle based on LiDAR-Camera fusion","volume":"24","author":"Xu","year":"2024","journal-title":"IEEE Sensors Journal"},{"issue":"3","key":"2025101507172803000_ref027","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1109\/TII.2018.2868859","article-title":"Feedback deep deterministic policy gradient with fuzzy reward for robotic multiple peg-in-hole assembly tasks","volume":"15","author":"Xu","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"2025101507172803000_ref028","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.jmsy.2023.11.008","article-title":"A residual reinforcement learning method for robotic assembly using visual and force information","volume":"72","author":"Zhang","year":"2024","journal-title":"Journal of Manufacturing Systems"},{"issue":"2","key":"2025101507172803000_ref029","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s10846-024-02079-2","article-title":"Deep visual-guided and deep reinforcement learning algorithm based for multip-peg-in-hole assembly task of power distribution live-line operation robot","volume":"110","author":"Zheng","year":"2024","journal-title":"Journal of Intelligent & Robotic Systems"}],"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-09-2024-0436\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/ir\/article-pdf\/52\/5\/639\/10355736\/ir-09-2024-0436en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ir\/article-pdf\/52\/5\/639\/10355736\/ir-09-2024-0436en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T11:17:40Z","timestamp":1760527060000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ir\/article\/52\/5\/639\/1254863\/Compliant-assembly-of-complex-aviation-plugs"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,28]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10,16]]}},"URL":"https:\/\/doi.org\/10.1108\/ir-09-2024-0436","relation":{},"ISSN":["0143-991X","1758-5791"],"issn-type":[{"type":"print","value":"0143-991X"},{"type":"electronic","value":"1758-5791"}],"subject":[],"published":{"date-parts":[[2025,1,28]]}}}