{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T06:38:43Z","timestamp":1774507123451,"version":"3.50.1"},"reference-count":100,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"112","license":[{"start":{"date-parts":[[2027,3,25]],"date-time":"2027-03-25T00:00:00Z","timestamp":1805932800000},"content-version":"vor","delay-in-days":365,"URL":"https:\/\/www.science.org\/content\/page\/science-licenses-journal-article-reuse"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CMMI 2516439"],"award-info":[{"award-number":["CMMI 2516439"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2026,3,25]]},"abstract":"<jats:p>Tiny palm-sized aerial robots have exceptional agility and cost-effectiveness in navigating confined and cluttered environments. However, their limited payload capacity directly constrains the sensing suite onboard the robot, thereby limiting critical navigational tasks in Global Positioning System (GPS)\u2013denied wild scenes. Common methods for obstacle avoidance use cameras and light detection and ranging (LIDAR), which become ineffective under visually degraded conditions such as low visibility, dust, fog, or darkness. Other sensors, such as radio detection and ranging (RADAR), have high power consumption, making them unsuitable for tiny aerial robots. Inspired by bats, we propose Saranga, a low-power, ultrasound-based perception stack that localizes obstacles using a dual sonar array. We present two key solutions to combat the low peak signal-to-noise ratio of \u22124.9 decibels: physical noise reduction and a deep learning\u2013based denoising method. First, we present a practical way to block propeller-induced ultrasound noise on the weak echoes. The second solution is to train a neural network to use the long horizon of ultrasound echoes for finding signal patterns under high amounts of uncorrelated noise where classical methods were insufficient. We generalized to the real world by using a synthetic data generation pipeline augmented with limited real noise data for training. We enabled a palm-sized aerial robot to navigate under visually degraded conditions of dense fog, darkness, and snow in a cluttered environment with thin and transparent obstacles using only onboard sensing and computation. We provide extensive real-world results to demonstrate the efficacy of our approach.<\/jats:p>","DOI":"10.1126\/scirobotics.adz9609","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T17:58:51Z","timestamp":1774461531000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":1,"title":["Milliwatt ultrasound for navigation in visually degraded environments on palm-sized aerial robots"],"prefix":"10.1126","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4467-4683","authenticated-orcid":true,"given":"Manoj","family":"Velmurugan","sequence":"first","affiliation":[{"name":"Perception and Autonomous Robotics (PeAR) Group, Worcester Polytechnic Institute, Worcester, MA 01609, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phillip","family":"Brush","sequence":"additional","affiliation":[{"name":"Perception and Autonomous Robotics (PeAR) Group, Worcester Polytechnic Institute, Worcester, MA 01609, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5809-5165","authenticated-orcid":true,"given":"Colin","family":"Balfour","sequence":"additional","affiliation":[{"name":"Perception and Autonomous Robotics (PeAR) Group, Worcester Polytechnic Institute, Worcester, MA 01609, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3053-7127","authenticated-orcid":true,"given":"Richard J.","family":"Przybyla","sequence":"additional","affiliation":[{"name":"TDK InvenSense, Berkeley, CA 94710, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9681-7602","authenticated-orcid":true,"given":"Nitin J.","family":"Sanket","sequence":"additional","affiliation":[{"name":"Perception and Autonomous Robotics (PeAR) Group, Worcester Polytechnic Institute, Worcester, MA 01609, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.2307\/1539097"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ado6187"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"N. Wessendorp R. Dinaux J. Dupeyroux G. C. H. E. de Croon \u201cObstacle avoidance onboard MAVs using a FMCW radar \u201d in Proceedings of the 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2021) pp. 117\u2013122.","DOI":"10.1109\/IROS51168.2021.9635901"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3519888"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm5954"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3496336"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaz9712"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abl6334"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"K. Tong Y. Hu B. Dikic S. Solmaz F. Fraundorfer D. Watzenig \u201cRobots saving lives: A literature review about search and rescue (SAR) in harsh environments \u201d in Proceedings of the 2024 IEEE Intelligent Vehicles Symposium (IV) (IEEE 2024) pp. 953\u2013960.","DOI":"10.1109\/IV55156.2024.10588685"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2892497"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abp9742"},{"key":"e_1_3_2_13_2","unstructured":"Skydio Inc. Skydio X10 (2025); https:\/\/skydio.com\/x10."},{"key":"e_1_3_2_14_2","unstructured":"DJI Enterprise Matrice 4 Series (2025); https:\/\/enterprise.dji.com\/matrice-4-series."},{"key":"e_1_3_2_15_2","unstructured":"Autel Robotics EVO Max 4T (2025); https:\/\/shop.autelrobotics.com\/collections\/autel-evo-max-series-for-theme-2023\/products\/evo-max-4t-copy."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00359-010-0571-z"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23156810"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3334683"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.add5139"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2411"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"N. J. Sanket C. M. Parameshwara C. D. Singh A. V. Kuruttukulam C. Ferm\u00fcller D. Scaramuzza Y. Aloimonos \u201cEVDodgeNet: Deep dynamic obstacle dodging with event cameras \u201d in Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 10651\u201310657.","DOI":"10.1109\/ICRA40945.2020.9196877"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14542"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"M. Dharmadhikari H. Nguyen F. Mascarich N. Khedekar K. Alexis \u201cAutonomous cave exploration using aerial robots \u201d in Proceedings of the 2021 International Conference on Unmanned Aircraft Systems (ICUAS) (IEEE 2021) pp. 942\u2013949.","DOI":"10.1109\/ICUAS51884.2021.9476870"},{"key":"e_1_3_2_24_2","unstructured":"Infineon Technologies AG \u201cRadar wave propagation through materials\u201d (Infineon Technologies AG 2020)."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/0032-3861(85)90216-2"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21932"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"C. Papachristos S. Khattak K. Alexis \u201cAutonomous exploration of visually-degraded environments using aerial robots \u201d in Proceedings of the 2017 International Conference on Unmanned Aircraft Systems (ICUAS) (IEEE 2017) pp. 775\u2013780.","DOI":"10.1109\/ICUAS.2017.7991510"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"V. Pritzl P. Stepan M. Saska \u201cAutonomous flying into buildings in a firefighting scenario \u201d in Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2021) pp. 239\u2013245.","DOI":"10.1109\/ICRA48506.2021.9560789"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00520-5"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"C. Papachristos F. Mascarich K. Alexis \u201cThermal-inertial localization for autonomous navigation of aerial robots through obscurants \u201d in Proceedings of the 2018 International Conference on Unmanned Aircraft Systems (ICUAS) (IEEE 2018) pp. 394\u2013399.","DOI":"10.1109\/ICUAS.2018.8453447"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"H. M\u00fcller V. Kartsch M. Magno L. Benini \u201cBatDeck: Advancing nano-drone navigation with low-power ultrasound-based obstacle avoidance \u201d in Proceedings of the 2024 IEEE Sensors Applications Symposium (SAS) (IEEE 2024) pp. 1\u20136.","DOI":"10.1109\/SAS60918.2024.10636518"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"L. Schroeder H. M\u00fcller T. Polonelli M. Magno L. Benini \u201cSuperBat\u2014Advancing obstacle avoidance on nano-UAVs by fusing ultrasonic and laser-based time-of-flight sensors \u201d in Proceedings of the 2024 IEEE International Symposium on Systems Engineering (ISSE) (IEEE 2024) pp. 1\u20138.","DOI":"10.1109\/ISSE63315.2024.10741113"},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","unstructured":"J. M\u00fcller A. V. Ruiz I. Wieser \u201cSafe & sound: A robust collision avoidance layer for aerial robots based on acoustic sensors \u201d in Proceedings of the 2014 IEEE\/ION Position Location and Navigation Symposium (PLANS) (IEEE 2014) pp. 1197\u20131202.","DOI":"10.1109\/PLANS.2014.6851492"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3194669"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"J. Ahn S. Chen J. Feng H. Lee J. Park H. Kim J. Yoo \u201cReal-time ultrasound imaging system for drone and robotic applications \u201d in Proceedings of the 2024 21st International SoC Design Conference (ISOCC) (IEEE 2024) pp. 224\u2013225.","DOI":"10.1109\/ISOCC62682.2024.10762065"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060664"},{"key":"e_1_3_2_37_2","unstructured":"H. M\u00fcller V. Kartsch M. Magno L. Benini BatDeck\u2013Ultra low-power ultrasonic ego-velocity estimation and obstacle avoidance on nano-drones. arXiv 2412.10048 [cs.RO] (2024)."},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"C. Walter H. Schweinzer \u201cLocating of objects with discontinuities boundaries and intersections using a compact ultrasonic 3D sensor \u201d in Proceedings of the 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (IEEE 2014) pp. 591\u2013600.","DOI":"10.1109\/IPIN.2014.7275532"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Y. Nagashima S. Yuta \u201cUltrasonic sensing for a mobile robot to recognize an environment\u2014Measuring the normal direction of walls \u201d in Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE vol. 2 1992) pp. 805\u2013812.","DOI":"10.1109\/IROS.1992.594485"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"B. Kreczmer \u201cObjects localization and differentiation using ultrasonic sensors\u201d in Robot Localization and Map Building H. Yussof Ed. (IntechOpen 2010).","DOI":"10.5772\/9271"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2015.07.029"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.851375"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2005.856129"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20195511"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2221313"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2014.2384197"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"I. Dokmani\u0107 I. Tashev \u201cHardware and algorithms for ultrasonic depth imaging \u201d in Proceedings of the 2014 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (IEEE 2014) pp. 6702\u20136706.","DOI":"10.1109\/ICASSP.2014.6854897"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3385232"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TUFFC.2017.2769399"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics9110695"},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"H. Moravec A. Elfes \u201cHigh resolution maps from wide angle sonar \u201d in Proceedings of the 1985 IEEE International Conference on Robotics and Automation (ICRA) (IEEE vol. 2 1985) pp. 116\u2013121.","DOI":"10.1109\/ROBOT.1985.1087316"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"D.-W. Jung Z.-S. Lim B.-G. Kim N.-K. Kim \u201cMulti-channel ultrasonic sensor system for obstacle detection of the mobile robot \u201d in Proceedings of the 2007 International Conference on Control Automation and Systems (IEEE 2007) pp. 2347\u20132351.","DOI":"10.1109\/ICCAS.2007.4406722"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"A. De Almeida E. Freire C. Ronnow J. Vianna R. Rosi \u201cNeural network-based geometric references recognition applied to ultrasound echo signals \u201d in Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (IEEE vol. 3 2000) pp. 1344\u20131347.","DOI":"10.1109\/MWSCAS.2000.951463"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3094492"},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"J. H. Christensen S. Hornauer S. X. Yu \u201cBatVision: Learning to see 3D spatial layout with two ears \u201d in Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 1581\u20131587.","DOI":"10.1109\/ICRA40945.2020.9196934"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.04.002"},{"key":"e_1_3_2_57_2","first-page":"9633","article-title":"Listening to sounds of silence for speech denoising","volume":"33","author":"Xu R.","year":"2020","unstructured":"R. Xu, R. Wu, Y. Ishiwaka, C. Vondrick, C. Zheng, Listening to sounds of silence for speech denoising. Adv. Neural Inf. Proces. Syst. 33, 9633\u20139648 (2020).","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3572478"},{"key":"e_1_3_2_59_2","doi-asserted-by":"crossref","unstructured":"N. Garg Y. Bai N. Roy \u201cOwlet: Enabling spatial information in ubiquitous acoustic devices \u201d in Proceedings of the 19th Annual International Conference on Mobile Systems Applications and Services (MobiSys) (Association for Computing Machinery 2021) pp. 255\u2013268.","DOI":"10.1145\/3458864.3467880"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.snr.2025.100313"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","unstructured":"R. Mars V. G. Reju A. W. H. Khong Y. Hioka K. Niwa \u201cBeamforming techniques using microphone arrays\u201d in Academic Press Library in Signal Processing R. Chellappa S. Theodoridis Eds. (Academic Press vol. 7 2018) pp. 585\u2013612.","DOI":"10.1016\/B978-0-12-811887-0.00012-2"},{"key":"e_1_3_2_62_2","unstructured":"A. J. Barabell J. Capon D. F. DeLong J. R. Johnson K. D. Senne \u201cPerformance comparison of superresolution array processing algorithms\u201d (Tech. Rep. TST-72 Lincoln Laboratory Massachusetts Institute of Technology 1984)."},{"key":"e_1_3_2_63_2","unstructured":"A. Deleforge \u201cDrone audition for search and rescue: Datasets and challenges \u201d in QUIET DRONES International Symposium on UAV\/UAS Noise (Quiet Drones 2020)."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.3390\/drones5010009"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20071981"},{"key":"e_1_3_2_66_2","doi-asserted-by":"crossref","unstructured":"R. J. Przybyla S. E. Shelton C. Lee B. E. Eovino Q. Chau M. H. Kline O. I. Izyumin D. A. Horsley \u201cMass produced micromachined ultrasonic time-of-flight sensors operating in different frequency bands \u201d in Proceedings of the 2023 IEEE 36th International Conference on Micro Electro Mechanical Systems (MEMS) (IEEE 2023) pp. 961\u2013964.","DOI":"10.1109\/MEMS49605.2023.10052367"},{"key":"e_1_3_2_67_2","unstructured":"Google Coral Dev Board Mini (2005); https:\/\/gweb-coral-full.uc.r.appspot.com\/products\/dev-board-mini\/."},{"key":"e_1_3_2_68_2","unstructured":"MAVLink Developer Team MAVLink: Micro air vehicle communication protocol (2005); https:\/\/mavlink.io\/en\/."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12274"},{"key":"e_1_3_2_70_2","doi-asserted-by":"crossref","unstructured":"C. Nous R. Meertens C. De Wagter G. de Croon \u201cPerformance evaluation in obstacle avoidance \u201d in Proceedings of the 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2016) pp. 3614\u20133619.","DOI":"10.1109\/IROS.2016.7759532"},{"key":"e_1_3_2_71_2","doi-asserted-by":"crossref","unstructured":"J. L. Sch\u00f6nberger J.-M. Frahm \u201cStructure-from-motion revisited \u201d in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2016) pp. 4104\u20134113.","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_2_72_2","doi-asserted-by":"crossref","unstructured":"B. Pfrommer N. Sanket K. Daniilidis J. Cleveland \u201cPennCOSYVIO: A challenging visual inertial odometry benchmark \u201d in Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2017) pp. 3847\u20133854.","DOI":"10.1109\/ICRA.2017.7989443"},{"key":"e_1_3_2_73_2","doi-asserted-by":"crossref","unstructured":"R. Madaan D. Maturana S. Scherer \u201cWire detection using synthetic data and dilated convolutional networks for unmanned aerial vehicles \u201d in Proceedings of the 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2017) pp. 3487\u20133494.","DOI":"10.1109\/IROS.2017.8206190"},{"key":"e_1_3_2_74_2","unstructured":"M. Martinez G. Benet F. Blanes P. P\u00e9rez J. Simo \u201cUsing the amplitude of ultrasonic echoes to classify detected objects in a scene \u201d in Proceedings of the 11th International Conference on Advanced Robotics (ICAR\u201903) (IEEE 2003) pp. 1136\u20131142."},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:JMIV.0000011325.36760.1e"},{"key":"e_1_3_2_76_2","doi-asserted-by":"crossref","unstructured":"E. R. Davies \u201cChapter 3\u2014Basic image filtering operations\u201d in Computer & Machine Vision: Theory Algorithms and Practicalities (Academic Press ed. 4 2012) pp. 38\u201342.","DOI":"10.1016\/B978-0-12-386908-1.00003-3"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1021\/ac60214a047"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/31.1775"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1088\/0143-0807\/24\/5\/306"},{"key":"e_1_3_2_80_2","unstructured":"TDK InvenSense \u201cInvenSense ICU-30201 ultrasonic sensor datasheet\u201d (2025); https:\/\/invensense.tdk.com\/wp-content\/uploads\/documentation\/ds-000524_icu-30201-datasheet.pdf."},{"key":"e_1_3_2_81_2","doi-asserted-by":"crossref","unstructured":"C. Chen Q. Chen J. Xu V. Koltun \u201cLearning to see in the dark \u201d in Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2018) pp. 3291\u20133300.","DOI":"10.1109\/CVPR.2018.00347"},{"key":"e_1_3_2_82_2","unstructured":"C. Kumar H. U. R. Mohammed G. Peake \u201cmmWave radar radome design guide\u201d (SWRA705 Texas Instruments 2021); https:\/\/ti.com\/lit\/an\/swra705\/swra705.pdf."},{"key":"e_1_3_2_83_2","unstructured":"R. Przybyla \u201cUltrasonic 3D rangefinder on a chip \u201d thesis University of California Berkeley Berkeley CA (2015)."},{"key":"e_1_3_2_84_2","doi-asserted-by":"crossref","unstructured":"H. M\u00fcller V. Kartsch L. Benini \u201cGAP9Shield: A 150GOPS AI-capable ultra-low power module for vision and ranging applications on nano-drones\u201d in European Robotics Forum (Springer 2024) pp. 292\u2013297.","DOI":"10.1007\/978-3-031-76424-0_52"},{"key":"e_1_3_2_85_2","unstructured":"Google Coral Dev Board Micro (2025); https:\/\/gweb-coral-full.uc.r.appspot.com\/products\/dev-board-micro."},{"key":"e_1_3_2_86_2","unstructured":"STMicroelectronics STM32N6 series microcontrollers (2025); https:\/\/st.com\/en\/microcontrollers-microprocessors\/stm32n6-series.html."},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1093\/ehjci\/jeac111"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-097X.2004.00539.x"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"e_1_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Y. Wu V. Boominathan H. Chen A. Sankaranarayanan A. Veeraraghavan \u201cPhaseCam3D\u2014Learning phase masks for passive single view depth estimation \u201d in Proceedings of the 2019 IEEE International Conference on Computational Photography (ICCP) (IEEE 2019) pp. 1\u201312.","DOI":"10.1109\/ICCPHOT.2019.8747330"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/TUFFC.2006.1588392"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2010.01.015"},{"key":"e_1_3_2_93_2","doi-asserted-by":"crossref","unstructured":"O. Ronneberger P. Fischer T. Brox \u201cU-Net: Convolutional networks for biomedical image segmentation \u201d in Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015 (Springer International Publishing 2015) pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_94_2","unstructured":"Google TensorFlow Lite: Post-training dynamic range quantization (2025); https:\/\/ai.google.dev\/edge\/litert\/models\/post_training_quant."},{"key":"e_1_3_2_95_2","unstructured":"Google Coral Edge Tensor Processing Unit (TPU) Compiler (2025); https:\/\/coral.ai\/docs\/edgetpu\/compiler\/."},{"key":"e_1_3_2_96_2","unstructured":"D. W. Kurtz J. E. Marte \u201cA review of aerodynamic noise from propellers rotors and lift fans\u201d (Tech. Rep. 32-7462 NASA 1970)."},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-460X(91)90570-A"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995232"},{"key":"e_1_3_2_99_2","doi-asserted-by":"crossref","unstructured":"D. Scharstein R. Szeliski R. Zabih \u201cA taxonomy and evaluation of dense two-frame stereo correspondence algorithms \u201d in Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV) (IEEE 2001) pp. 131\u2013140.","DOI":"10.1109\/SMBV.2001.988771"},{"key":"e_1_3_2_100_2","doi-asserted-by":"crossref","unstructured":"R. Kala \u201cChapter 10\u2014Artificial potential field\u201d in Autonomous Mobile Robots (Academic Press 2024) pp. 465\u2013509.","DOI":"10.1016\/B978-0-443-18908-1.00009-1"},{"key":"e_1_3_2_101_2","doi-asserted-by":"crossref","unstructured":"K. Srivastava R. Kulkarni M. Velmurugan N. J. Sanket \u201cVizFlyt: Perception-centric pedagogical framework for autonomous aerial robots \u201d in Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2025) pp. 9920\u20139927.","DOI":"10.1109\/ICRA55743.2025.11128463"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adz9609","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adz9609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T17:59:07Z","timestamp":1774461547000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adz9609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":100,"journal-issue":{"issue":"112","published-print":{"date-parts":[[2026,3,25]]}},"alternative-id":["10.1126\/scirobotics.adz9609"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adz9609","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]},"assertion":[{"value":"2025-06-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadz9609"}}