{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:24:22Z","timestamp":1781972662695,"version":"3.54.5"},"reference-count":57,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"66","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2022,5,25]]},"abstract":"<jats:p>Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the relationship between various wind conditions and its effect on aircraft maneuverability is not well understood, it is challenging to design effective robot controllers using traditional control design methods. We present Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly builds on two key observations that aerodynamics in different wind conditions share a common representation and that the wind-specific part lies in a low-dimensional space. To that end, Neural-Fly uses a proposed learning algorithm, domain adversarially invariant meta-learning (DAIML), to learn the shared representation, only using 12 minutes of flight data. With the learned representation as a basis, Neural-Fly then uses a composite adaptation law to update a set of linear coefficients for mixing the basis elements. When evaluated under challenging wind conditions generated with the Caltech Real Weather Wind Tunnel, with wind speeds up to 43.6 kilometers\/hour (12.1 meters\/second), Neural-Fly achieves precise flight control with substantially smaller tracking error than stateof-the-art nonlinear and adaptive controllers. In addition to strong empirical performance, the exponential stability of Neural-Fly results in robustness guarantees. Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.<\/jats:p>","DOI":"10.1126\/scirobotics.abm6597","type":"journal-article","created":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T17:59:32Z","timestamp":1651687172000},"source":"Crossref","is-referenced-by-count":231,"title":["Neural-Fly enables rapid learning for agile flight in strong winds"],"prefix":"10.1126","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6681-8823","authenticated-orcid":true,"given":"Michael","family":"O\u2019Connell","sequence":"first","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9075-3705","authenticated-orcid":true,"given":"Guanya","family":"Shi","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5366-9256","authenticated-orcid":true,"given":"Xichen","family":"Shi","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamyar","family":"Azizzadenesheli","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-6797","authenticated-orcid":true,"given":"Anima","family":"Anandkumar","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9127-1989","authenticated-orcid":true,"given":"Yisong","family":"Yue","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-3907","authenticated-orcid":true,"given":"Soon-Jo","family":"Chung","sequence":"additional","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abh1221"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2776353"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"P. Ventura Diaz S. Yoon High-fidelity computational aerodynamics of multi-rotor unmanned aerial vehicles in 2018 AIAA Aerospace Sciences Meeting (2018) p. 1266.","DOI":"10.2514\/6.2018-1266"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2020.3001117"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"S. Mallikarjunan B. Nesbitt E. Kharisov E. Xargay N. Hovakimyan C. Cao L1 adaptive controller for attitude control of multirotors in A\/AA Guidance Navigation and Control Conference (American Institute of Aeronautics and Astronautics 2012).","DOI":"10.2514\/6.2012-4831"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"J. Pravitra K. A. Ackerman C. Cao N. Hovakimyan E. A. Theodorou LI-adaptive MPPI architecture for robust and agile control of multirotors in Proceedings of the 2020 IEEE\/RSI International Conference on Intelligent Robots and Systems (IROS) (2020) pp. 7661\u20137666. ISSN: 2153-0866.","DOI":"10.1109\/IROS45743.2020.9341154"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"D. Hanover P. Foehn S. Sun E. Kaufmann D. Scaramuzza Performance precision and payloads: Adaptive nonlinear MPC for quadrotors. IEEE Robot. Autom. Lett. 7 690-697 (2021).","DOI":"10.1109\/LRA.2021.3131690"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"G. Shi X. Shi M. O\u2019Connell R. Yu K. Azizzadenesheli A. Anandkumar Y. Yue S.-J. Chung Neural lander: Stable drone landing control using learned dynamics in Proceedings of the 2019 International Conference on Robotics and Automation (ICRA) (IEEE 2019) pp. 9784\u20139790.","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"G. Shi W. H\u00f6nig Y. Yue S.-J. Chung Neural-swarm: Decentralized close-proximity multirotor control using learned interactions in Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 3241\u20133247.","DOI":"10.1109\/ICRA40945.2020.9196800"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3098436"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061307"},{"key":"e_1_3_2_13_2","first-page":"6240","article-title":"Spectrally-normalized margin bounds for neural networks","volume":"30","author":"Bartlett P. L.","year":"2017","unstructured":"P. L. Bartlett, D. J. Foster, M. J. Telgarsky, Spectrally-normalized margin bounds for neural networks. Adv. Neural Inform. Process. Syst. 30, 6240 (2017).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9281-4"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"D. Mellinger V. Kumar Minimum snap trajectory generation and control for quadrotors in Proceedings of the 2011 IEEE International Conference on Robotics and Automation (IEEE 2011) pp. 2520\u20132525.","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"e_1_3_2_16_2","unstructured":"J.-J. E. Slotine W. Li Applied Nonlinear Control (Prentice Hall 1991)."},{"key":"e_1_3_2_17_2","unstructured":"P. A. Ioannou J. Sun Robust Adaptive Control (Prentice-Hall Upper Saddle River 1996) vol. 1."},{"key":"e_1_3_2_18_2","unstructured":"M. Krstic P. V. Kokotovic I. Kanellakopoulos Nonlinear and Adaptive Control Design (John Wiley & Sons Inc. 1995)."},{"key":"e_1_3_2_19_2","unstructured":"K. S. Narendra A. M. Annaswamy Stable Adaptive Systems (Courier Corporation 2012)."},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"J. A. Farrell M. M. Polycarpou Adaptive Approximation Based Control (John Wiley & Sons Ltd. 2006); https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/0471781819.fmatter.","DOI":"10.1002\/0471781819"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"K. A. Wise E. Lavretsky N. Hovakimyan Adaptive control of flight: theory applications and open problems in Proceedings of the 2006 American Control Conference (IEEE 2006).","DOI":"10.1109\/ACC.2006.1657677"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"X. Shi P. Spieler E. Tang E.-S. Lupu P. Tokumaru S.-J. Chung Adaptive Nonlinear Control of Fixed-Wing VTOL with Airflow Vector Sensing in 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 5321\u20135327.","DOI":"10.1109\/ICRA40945.2020.9197344"},{"key":"e_1_3_2_23_2","unstructured":"A. Rahimi B. Recht Random features for large-scale kernel machines in Proceedings of the 20th International Conference on Neural Information Processing Systems (Advances in neural information processing systems 2007) pp. 1177\u20131184."},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"S. Lale K. Azizzadenesheli B. Hassibi A. Anandkumar Model Learning Predictive Control in Nonlinear Dynamical Systems in Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC) (IEEE 2021) pp. 757\u2013762. ISSN: 2576-2370.","DOI":"10.1109\/CDC45484.2021.9683670"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"J. Nakanishi J. Farrell S. Schaal A locally weighted learning composite adaptive controller with structure adaptation in IEEE\/RSI International Conference on Intelligent Robots and Systems (IEEE 2002) vol. 1 pp. 882\u2013889.","DOI":"10.1109\/IRDS.2002.1041502"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/9.384214"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.2514\/2.6934"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.572089"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2020.3006184"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_31_2","unstructured":"C. Finn P. Abbeel S. Levine Model-agnostic meta-learning for fast adaptation of deep networks in Proceedings of the 34th International Conference on Machine Learning (PMLR 2017) pp. 1126\u20131135."},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"T. M. Hospedales A. Antoniou P. Micaelli A. J. Storkey Meta-learning in neural networks: A survey in IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE 2021) pp. 1.","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"e_1_3_2_33_2","unstructured":"A. Nagabandi I. Clavera S. Liu R. S. Fearing P. Abbeel S. Levine C. Finn Learning to adapt in dynamic real-world environments through meta-reinforcement learning. arXiv: 1.803.11347 [cs.LG] (2018)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"X. Song Y. Yang K. Choromanski K. Caluwaerts W. Gao C. Finn J. Tan Rapidly adaptable legged robots via evolutionary meta-learning in Proceedings of the 2020 IEEE\/RSI International Conference on Intelligent Robots and Systems (IROS) (IEEE 2020) pp. 3769\u20133776.","DOI":"10.1109\/IROS45743.2020.9341571"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063957"},{"key":"e_1_3_2_37_2","unstructured":"I. Clavera J. Rothfuss J. Schulman Y. Fujita T. Asfour P. Abbeel Model-based reinforcement learning via meta-policy optimization in Conference on Robot Learning (PMLR 2018) pp. 617\u2013629."},{"key":"e_1_3_2_38_2","unstructured":"M. O\u2019Connell G. Shi X. Shi S.-J. Chung Meta-learning-based robust adaptive flight control under uncertain wind conditions. arXiv: 2103.01932 [cs.RO] (2021)."},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"S. M. Richards N. Azizan J.-J. E. Slotine M. Pavone Adaptive-control-oriented meta-learning for nonlinear systems. arXiv:2103.04490 [cs.RO] (2021).","DOI":"10.15607\/RSS.2021.XVII.056"},{"key":"e_1_3_2_40_2","unstructured":"M. Peng B. Zhu J. Jiao Linear representation meta-reinforcement learning for instant adaptation. arXiv: 2101.04750 [cs.LG] (2021)."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"J. Tobin R. Fong A. Ray J. Schneider W. Zaremba P. Abbeel Domain randomization for transferring deep neural networks from simulation to the real world in Proceedings of the 2017 IEEE\/RS] International Conference on Intelligent Robots and Systems (IROS) (IEEE 2017) pp. 23\u201330.","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"F. Ramos R. C. Possas D. Fox Bayessim: Adaptive domain randomization via probabilistic inference for robotics simulators. arXiv: 1906.01728 [cs.RO] (2019).","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916632065"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"X. Shi K. Kim S. Rahili S.-J. Chung Nonlinear control of autonomous flying cars with wings and distributed electric propulsion in Proceedings of the 2018 IEEE Conference on Decision and Control (CDC) (IEEE 2018) pp. 5326\u20135333.","DOI":"10.1109\/CDC.2018.8619578"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3044033"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abf8136"},{"key":"e_1_3_2_49_2","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin Y.","year":"2017","unstructured":"Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, V. Lempitsky, Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 2096 (2017).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_50_2","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow I.","year":"2014","unstructured":"I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets. Adv. Neural Inform. Process. Syst. 27, (2014).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3658902"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"R. M. Murray Z. Li S. S. Sastry A Mathematical Introduction to Robotic Manipulation (CRC Press ed. 1 2017).","DOI":"10.1201\/9781315136370-1"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1090\/proc\/13623"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.07.002"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/s002110050030"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"e_1_3_2_57_2","unstructured":"H. K. Khalil Nonlinear Systems 3rd Edition (Prentice Hall 2002)."},{"key":"e_1_3_2_58_2","unstructured":"Multicopter PID Tuning Guide (Advanced\/Detailed) I PX4 User Guide."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.abm6597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T20:18:32Z","timestamp":1727122712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.abm6597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,25]]},"references-count":57,"journal-issue":{"issue":"66","published-print":{"date-parts":[[2022,5,25]]}},"alternative-id":["10.1126\/scirobotics.abm6597"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.abm6597","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,25]]},"article-number":"eabm6597"}}