Learning to estimate UAV created turbulence from scene structure observed by onboard cameras
Controlling UAV flights precisely requires a realistic dynamic model and accurate state estimates from onboard sensors like UAV, GPS and visual observations. Obtaining a precise dynamic model is extremely difficult, as important aerodynamic effects are hard to model, in particular ground effect and...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-03 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Possamaï, Quentin Steeven Janny Nadri, Madiha Bako, Laurent Wolf, Christian |
description | Controlling UAV flights precisely requires a realistic dynamic model and accurate state estimates from onboard sensors like UAV, GPS and visual observations. Obtaining a precise dynamic model is extremely difficult, as important aerodynamic effects are hard to model, in particular ground effect and other turbulences. While machine learning has been used in the past to estimate UAV created turbulence, this was restricted to flat grounds or diffuse in-flight air turbulences, both without taking into account obstacles. In this work we address the complex problem of estimating in-flight turbulences caused by obstacles, in particular the complex structures in cluttered environments. We learn a mapping from control input and images captured by onboard cameras to turbulence. In a large-scale setting, we train a model over a large number of different simulated photo-realistic environments loaded into the Habitat.AI simulator augmented with a dynamic UAV model and an analytic ground effect model. We transfer the model from simulation to a real environment and evaluate on real UAV flights from the EuRoC-MAV dataset, showing that the model is capable of good sim2real generalization performance. The dataset will be made publicly available upon acceptance. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2644592013</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2644592013</sourcerecordid><originalsourceid>FETCH-proquest_journals_26445920133</originalsourceid><addsrcrecordid>eNqNjbEKwjAURYMgWLT_8MC5UJO26iiiODiqk1CS9FVa2kRfEsG_N4Mf4HQPnAN3whIuxCrbFJzPWOpcn-c5r9a8LEXC7meUZDrzAG8Bne9G6RGuuxtowogN-EAqDGg0Qkt2BKfRIDhPQUeFYJVDesdQfcAaZSU1oOWIJN2CTVs5OEx_O2fL4-GyP2VPsq8Q3-reBjJR1bwqinLL85UQ_1Vf6JdDvg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2644592013</pqid></control><display><type>article</type><title>Learning to estimate UAV created turbulence from scene structure observed by onboard cameras</title><source>Free E- Journals</source><creator>Possamaï, Quentin ; Steeven Janny ; Nadri, Madiha ; Bako, Laurent ; Wolf, Christian</creator><creatorcontrib>Possamaï, Quentin ; Steeven Janny ; Nadri, Madiha ; Bako, Laurent ; Wolf, Christian</creatorcontrib><description>Controlling UAV flights precisely requires a realistic dynamic model and accurate state estimates from onboard sensors like UAV, GPS and visual observations. Obtaining a precise dynamic model is extremely difficult, as important aerodynamic effects are hard to model, in particular ground effect and other turbulences. While machine learning has been used in the past to estimate UAV created turbulence, this was restricted to flat grounds or diffuse in-flight air turbulences, both without taking into account obstacles. In this work we address the complex problem of estimating in-flight turbulences caused by obstacles, in particular the complex structures in cluttered environments. We learn a mapping from control input and images captured by onboard cameras to turbulence. In a large-scale setting, we train a model over a large number of different simulated photo-realistic environments loaded into the Habitat.AI simulator augmented with a dynamic UAV model and an analytic ground effect model. We transfer the model from simulation to a real environment and evaluate on real UAV flights from the EuRoC-MAV dataset, showing that the model is capable of good sim2real generalization performance. The dataset will be made publicly available upon acceptance.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Barriers ; Cameras ; Datasets ; Dynamic models ; Ground effect (aerodynamics) ; Machine learning ; Simulation ; Turbulence ; Visual observation</subject><ispartof>arXiv.org, 2022-03</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Possamaï, Quentin</creatorcontrib><creatorcontrib>Steeven Janny</creatorcontrib><creatorcontrib>Nadri, Madiha</creatorcontrib><creatorcontrib>Bako, Laurent</creatorcontrib><creatorcontrib>Wolf, Christian</creatorcontrib><title>Learning to estimate UAV created turbulence from scene structure observed by onboard cameras</title><title>arXiv.org</title><description>Controlling UAV flights precisely requires a realistic dynamic model and accurate state estimates from onboard sensors like UAV, GPS and visual observations. Obtaining a precise dynamic model is extremely difficult, as important aerodynamic effects are hard to model, in particular ground effect and other turbulences. While machine learning has been used in the past to estimate UAV created turbulence, this was restricted to flat grounds or diffuse in-flight air turbulences, both without taking into account obstacles. In this work we address the complex problem of estimating in-flight turbulences caused by obstacles, in particular the complex structures in cluttered environments. We learn a mapping from control input and images captured by onboard cameras to turbulence. In a large-scale setting, we train a model over a large number of different simulated photo-realistic environments loaded into the Habitat.AI simulator augmented with a dynamic UAV model and an analytic ground effect model. We transfer the model from simulation to a real environment and evaluate on real UAV flights from the EuRoC-MAV dataset, showing that the model is capable of good sim2real generalization performance. The dataset will be made publicly available upon acceptance.</description><subject>Barriers</subject><subject>Cameras</subject><subject>Datasets</subject><subject>Dynamic models</subject><subject>Ground effect (aerodynamics)</subject><subject>Machine learning</subject><subject>Simulation</subject><subject>Turbulence</subject><subject>Visual observation</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjbEKwjAURYMgWLT_8MC5UJO26iiiODiqk1CS9FVa2kRfEsG_N4Mf4HQPnAN3whIuxCrbFJzPWOpcn-c5r9a8LEXC7meUZDrzAG8Bne9G6RGuuxtowogN-EAqDGg0Qkt2BKfRIDhPQUeFYJVDesdQfcAaZSU1oOWIJN2CTVs5OEx_O2fL4-GyP2VPsq8Q3-reBjJR1bwqinLL85UQ_1Vf6JdDvg</recordid><startdate>20220328</startdate><enddate>20220328</enddate><creator>Possamaï, Quentin</creator><creator>Steeven Janny</creator><creator>Nadri, Madiha</creator><creator>Bako, Laurent</creator><creator>Wolf, Christian</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220328</creationdate><title>Learning to estimate UAV created turbulence from scene structure observed by onboard cameras</title><author>Possamaï, Quentin ; Steeven Janny ; Nadri, Madiha ; Bako, Laurent ; Wolf, Christian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26445920133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Barriers</topic><topic>Cameras</topic><topic>Datasets</topic><topic>Dynamic models</topic><topic>Ground effect (aerodynamics)</topic><topic>Machine learning</topic><topic>Simulation</topic><topic>Turbulence</topic><topic>Visual observation</topic><toplevel>online_resources</toplevel><creatorcontrib>Possamaï, Quentin</creatorcontrib><creatorcontrib>Steeven Janny</creatorcontrib><creatorcontrib>Nadri, Madiha</creatorcontrib><creatorcontrib>Bako, Laurent</creatorcontrib><creatorcontrib>Wolf, Christian</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Possamaï, Quentin</au><au>Steeven Janny</au><au>Nadri, Madiha</au><au>Bako, Laurent</au><au>Wolf, Christian</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Learning to estimate UAV created turbulence from scene structure observed by onboard cameras</atitle><jtitle>arXiv.org</jtitle><date>2022-03-28</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Controlling UAV flights precisely requires a realistic dynamic model and accurate state estimates from onboard sensors like UAV, GPS and visual observations. Obtaining a precise dynamic model is extremely difficult, as important aerodynamic effects are hard to model, in particular ground effect and other turbulences. While machine learning has been used in the past to estimate UAV created turbulence, this was restricted to flat grounds or diffuse in-flight air turbulences, both without taking into account obstacles. In this work we address the complex problem of estimating in-flight turbulences caused by obstacles, in particular the complex structures in cluttered environments. We learn a mapping from control input and images captured by onboard cameras to turbulence. In a large-scale setting, we train a model over a large number of different simulated photo-realistic environments loaded into the Habitat.AI simulator augmented with a dynamic UAV model and an analytic ground effect model. We transfer the model from simulation to a real environment and evaluate on real UAV flights from the EuRoC-MAV dataset, showing that the model is capable of good sim2real generalization performance. The dataset will be made publicly available upon acceptance.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-03 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2644592013 |
source | Free E- Journals |
subjects | Barriers Cameras Datasets Dynamic models Ground effect (aerodynamics) Machine learning Simulation Turbulence Visual observation |
title | Learning to estimate UAV created turbulence from scene structure observed by onboard cameras |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T16%3A51%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Learning%20to%20estimate%20UAV%20created%20turbulence%20from%20scene%20structure%20observed%20by%20onboard%20cameras&rft.jtitle=arXiv.org&rft.au=Possama%C3%AF,%20Quentin&rft.date=2022-03-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2644592013%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2644592013&rft_id=info:pmid/&rfr_iscdi=true |