{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:06:33Z","timestamp":1775912793357,"version":"3.50.1"},"reference-count":39,"publisher":"Informa UK Limited","issue":"11","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2025,6,3]]},"DOI":"10.1080\/01691864.2025.2506091","type":"journal-article","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T05:14:16Z","timestamp":1748063656000},"page":"647-662","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["GenAerialNav: obstacle avoidance in real flight for generalized multirotors by reinforcement learning with variable Acc-Properties in dynamics"],"prefix":"10.1080","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4847-5497","authenticated-orcid":false,"given":"Haruki","family":"Kozuka","sequence":"first","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8361-5825","authenticated-orcid":false,"given":"Moju","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0212-5507","authenticated-orcid":false,"given":"Takuzumi","family":"Nishio","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4433-0013","authenticated-orcid":false,"given":"Iori","family":"Yanokura","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7464-7187","authenticated-orcid":false,"given":"Kento","family":"Kawaharazuka","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7937-3996","authenticated-orcid":false,"given":"Junichiro","family":"Sugihara","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6958-5176","authenticated-orcid":false,"given":"Kazuki","family":"Sugihara","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6606-6692","authenticated-orcid":false,"given":"Kei","family":"Okada","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1273-1567","authenticated-orcid":false,"given":"Masayuki","family":"Inaba","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1","unstructured":"Open X-Embodiment Collaboration et\u00a0al. Open X-embodiment: robotic learning datasets and RT-X models. 2023. arXiv:2310.08864."},{"key":"e_1_3_2_3_1","unstructured":"Brohan A Brown N Carbajal J et\u00a0al. Rt-2: vision-language-action models transfer web knowledge to robotic control. Preprint; 2023. arXiv:2307.15818."},{"key":"e_1_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Brohan A Brown N Carbajal J et\u00a0al. Rt-1: robotics transformer for real-world control at scale. Preprint; 2022. arXiv:2212.06817.","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_5_1","unstructured":"Feng G Zhang H Li Z et\u00a0al. Genloco: generalized locomotion controllers for quadrupedal robots. In: Conference on Robot Learning Atlanta GA. PMLR; 2023. p. 1893\u20131903."},{"key":"e_1_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Hirose N Shah D Sridhar A et\u00a0al. Exaug: robot-conditioned navigation policies via geometric experience augmentation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA) London. IEEE; 2023. p.\u00a04077\u20134084.","DOI":"10.1109\/ICRA48891.2023.10160761"},{"key":"e_1_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Shah D Sridhar A Bhorkar A et\u00a0al. GNM: a general navigation model to drive any robot. In: International Conference on Robotics and Automation (ICRA) London. 2023.","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3154013"},{"key":"e_1_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Song Y Steinweg M Kaufmann E et\u00a0al. Autonomous drone racing with deep reinforcement learning. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Prague Czech Republic. IEEE; 2021. p.\u00a01205\u20131212.","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3252342"},{"key":"e_1_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Devin C Gupta A Darrell T et\u00a0al. Learning modular neural network policies for multi-task and multi-robot transfer. In: 2017 IEEE International Conference on Robotics and Automation (ICRA) Marina Bay Sands Singapore. IEEE; 2017. p.\u00a02169\u20132176.","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"e_1_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Helwa MK Schoellig AP. Multi-robot transfer learning: a dynamical system perspective. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Vancouver Convention Centre Vancouver British Columbia Canada. IEEE; 2017. p.\u00a04702\u20134708.","DOI":"10.1109\/IROS.2017.8206342"},{"key":"e_1_3_2_15_1","first-page":"9355","article-title":"Hardware conditioned policies for multi-robot transfer learning","volume":"31","author":"Chen T","year":"2018","unstructured":"Chen T, Murali A, Gupta A. Hardware conditioned policies for multi-robot transfer learning. Adv Neural Inf Process Syst. 2018;31:9355\u20139366.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Molchanov A Chen T H\u00f6nig W et\u00a0al. Sim-to-(multi)-real: transfer of low-level robust control policies to multiple quadrotors. IEEE; 2019.","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"e_1_3_2_17_1","unstructured":"Shah D Osinski B Ichter B et\u00a0al. Lm-nav: robotic navigation with large pre-trained models of language vision and action. In: Conference on Robot Learning Atlanta GA. PMLR; 2023. p.\u00a0492\u2013504."},{"key":"e_1_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Xie Z Da X Van de Panne M et\u00a0al. Dynamics randomization revisited: a case study for quadrupedal locomotion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA) Xi'an China. IEEE; 2021. p.\u00a04955\u20134961.","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"e_1_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Patel U Kumar NKS Sathyamoorthy AJ et\u00a0al. Dwa-rl: dynamically feasible deep reinforcement learning policy for robot navigation among mobile obstacles. In: 2021 IEEE International Conference on Robotics and Automation (ICRA) Xi'an China. IEEE; 2021. p.\u00a06057\u20136063.","DOI":"10.1109\/ICRA48506.2021.9561462"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3257549"},{"key":"e_1_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Everett M Chen YF How JP. Motion planning among dynamic decision-making agents with deep reinforcement learning. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Madrid Spain. IEEE; 2018. p.\u00a03052\u20133059.","DOI":"10.1109\/IROS.2018.8593871"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068639"},{"key":"e_1_3_2_23_1","unstructured":"Wang D Fan T Han T et\u00a0al. A two-stage reinforcement learning approach for multi-UAV collision avoidance under imperfect sensing."},{"key":"e_1_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Chen YF Liu M Everett M et\u00a0al. Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: 2017 IEEE International Conference on Robotics and Automation (ICRA) Marina Bay Sands Singapore. IEEE; 2017. p.\u00a0285\u2013292.","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"e_1_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Tobin J Fong R Ray A et\u00a0al. Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Vancouver Convention Centre Vancouver British Columbia Canada. IEEE; 2017. p.\u00a023\u201330.","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068639"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abl6259"},{"key":"e_1_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Shi F Homberger T Lee J et\u00a0al. Circus anymal: a quadruped learning dexterous manipulation with its limbs. In: 2021 IEEE International Conference on Robotics and Automation (ICRA) Xi'an China. IEEE; 2021. p.\u00a02316\u20132323.","DOI":"10.1109\/ICRA48506.2021.9561926"},{"issue":"4","key":"e_1_3_2_29_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201311","article-title":"Deepmimic: example-guided deep reinforcement learning of physics-based character skills","volume":"37","author":"Peng XB","year":"2018","unstructured":"Peng XB, Abbeel P, Levine S, et\u00a0al. Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans Graph (TOG). 2018;37(4):1\u201314.","journal-title":"ACM Trans Graph (TOG)"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3251193"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00817-z"},{"key":"e_1_3_2_32_1","unstructured":"Schulman J Wolski F Dhariwal P et\u00a0al. Proximal policy optimization algorithms. Preprint; 2017. arXiv:1707.06347."},{"issue":"1","key":"e_1_3_2_33_1","first-page":"12348","article-title":"Stable-baselines3: reliable reinforcement learning implementations","volume":"22","author":"Raffin A","year":"2021","unstructured":"Raffin A, Hill A, Gleave A, et\u00a0al. Stable-baselines3: reliable reinforcement learning implementations. J\u00a0Mach Learn Res. 2021;22(1):12348\u201312355.","journal-title":"J\u00a0Mach Learn Res"},{"key":"e_1_3_2_34_1","unstructured":"Song Y Naji S Kaufmann E et\u00a0al. Flightmare: a flexible quadrotor simulator. In: Conference on Robot Learning London UK. PMLR; 2021. p.\u00a01147\u20131157."},{"key":"e_1_3_2_35_1","unstructured":"Anzai T Zhao M Shi F et\u00a0al. Sensing and navigation of aerial robot for measuring tree location and size in forest environment. In: International Workshop on Smart Info-Media Systems in Asia (SISA) Fukuoka Japan. 2017."},{"key":"e_1_3_2_36_1","unstructured":"Unity Technologies. Unity 2023. Game development platform."},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918801639"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2006.878967"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300191"},{"key":"e_1_3_2_40_1","unstructured":"Quigley M Gerkey B Conley K et\u00a0al. ROS: an open-source robot operating system. In: ICRA Workshop on Open Source Software. Vol. 3. Kobe Japan; 2009. p.\u00a05."}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2025.2506091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T13:59:34Z","timestamp":1751378374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2025.2506091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":39,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,6,3]]}},"alternative-id":["10.1080\/01691864.2025.2506091"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2025.2506091","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-10-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-13","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}