{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:03:38Z","timestamp":1781366618994,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127714","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13683-13689","source":"Crossref","is-referenced-by-count":8,"title":["ProxFly: Robust Control for Close Proximity Quadcopter Flight Via Residual Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ruiqi","family":"Zhang","sequence":"first","affiliation":[{"name":"University of California,High Performance Robotics Lab,Department of Mechanical Engineering,Berkeley,CA,United States,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California,High Performance Robotics Lab,Department of Mechanical Engineering,Berkeley,CA,United States,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark W.","family":"Mueller","sequence":"additional","affiliation":[{"name":"University of California,High Performance Robotics Lab,Department of Mechanical Engineering,Berkeley,CA,United States,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989376"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat3536"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304189"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197580"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3337701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2019.8798116"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383632"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3098436"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160836"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611665"},{"key":"ref20","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref22","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2636810"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968488"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref26","article-title":"Residual policy learning","author":"Silver","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3003277"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192770"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MFI55806.2022.9913862"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127714.pdf?arnumber=11127714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:34:53Z","timestamp":1760636093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127714","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}