A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control
The latest developments in the field of Machine Learning (ML), especially Reinforcement Learning (RL) techniques, reduce the need of having pre-existing data available. In this paper, we are presenting a Reinforcement Learning approach to Unmanned Aerial Vehicles (UAV) trajectory tracking and attitu...
Gespeichert in:
| Veröffentlicht in: | Land Forces Academy review 2022-12, Vol.27 (4), p.400-410 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 410 |
|---|---|
| container_issue | 4 |
| container_start_page | 400 |
| container_title | Land Forces Academy review |
| container_volume | 27 |
| creator | Bălaşa, Răzvan-Ionuț Bîlu, Marian Ciprian Iordache, Cătălin |
| description | The latest developments in the field of Machine Learning (ML), especially Reinforcement Learning (RL) techniques, reduce the need of having pre-existing data available. In this paper, we are presenting a Reinforcement Learning approach to Unmanned Aerial Vehicles (UAV) trajectory tracking and attitude control for an X configuration quadcopter. The proposed solution aims to tackle different maneuvers and to be able to withstand a wide variety of environmental disturbances, both while ensuring the success of the mission for which the Unmanned Aerial Vehicle has been designed. The Proximal Policy Optimization (PPO) solution has first been trained in a simulation environment. The model of the vehicle is designed to take into account various configurations, including changes of mass, while the model of the environment contains various disturbances sources. |
| doi_str_mv | 10.2478/raft-2022-0049 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3082682037</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3082682037</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1600-a893e9bc2b9b73e84e9182aeb17f41381b844111e3d5ece6920dcf9f5940c5823</originalsourceid><addsrcrecordid>eNptkM1Lw0AQxYMoWGqvnhc8p85-tNmAl1D8gkKLWPEWNptJuzXZjZstWv96UyrowdM8hvfeDL8ouqQwZiKR115VIWbAWAwg0pNowPp1LAW8nv7R59Go67YAQCHhU8YH0VtGlt59mkbVZOlqo_dk0QbTmC8VjLPkCY2tnNfYoA1kjspbY9cka1vvlN6Q4MjKNspaLEmG3vQ1L7gxusaOZCGYsCuRzJwN3tUX0Vml6g5HP3MYre5un2cP8Xxx_zjL5rGmU4BYyZRjWmhWpEXCUQpMqWQKC5pUgnJJCykEpRR5OUGN05RBqau0mqQC9EQyPoyujr39j-877EK-dTtv-5M5B8mmkgFPetf46NLedZ3HKm99j8Hvcwr5gWl-YJofmOYHpn3g5hj4UHVAX-La7_a9-G3_P8gSIQD4N4xnfts</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3082682037</pqid></control><display><type>article</type><title>A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control</title><source>De Gruyter Open Access Journals</source><source>Alma/SFX Local Collection</source><source>Sciendo</source><creator>Bălaşa, Răzvan-Ionuț ; Bîlu, Marian Ciprian ; Iordache, Cătălin</creator><creatorcontrib>Bălaşa, Răzvan-Ionuț ; Bîlu, Marian Ciprian ; Iordache, Cătălin</creatorcontrib><description>The latest developments in the field of Machine Learning (ML), especially Reinforcement Learning (RL) techniques, reduce the need of having pre-existing data available. In this paper, we are presenting a Reinforcement Learning approach to Unmanned Aerial Vehicles (UAV) trajectory tracking and attitude control for an X configuration quadcopter. The proposed solution aims to tackle different maneuvers and to be able to withstand a wide variety of environmental disturbances, both while ensuring the success of the mission for which the Unmanned Aerial Vehicle has been designed. The Proximal Policy Optimization (PPO) solution has first been trained in a simulation environment. The model of the vehicle is designed to take into account various configurations, including changes of mass, while the model of the environment contains various disturbances sources.</description><identifier>ISSN: 2247-840X</identifier><identifier>ISSN: 1582-6384</identifier><identifier>EISSN: 2247-840X</identifier><identifier>DOI: 10.2478/raft-2022-0049</identifier><language>eng</language><publisher>Sibiu: Sciendo</publisher><subject>Attitude control ; Configurations ; Control algorithms ; Disturbances ; Energy consumption ; Machine learning ; Optimization ; proximal policy optimization ; reinforcement learning ; Simulation ; Tracking control ; Trajectory control ; Unmanned aerial vehicles ; Vehicles ; Velocity</subject><ispartof>Land Forces Academy review, 2022-12, Vol.27 (4), p.400-410</ispartof><rights>Copyright Nicolae Balcescu 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1600-a893e9bc2b9b73e84e9182aeb17f41381b844111e3d5ece6920dcf9f5940c5823</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://sciendo.com/pdf/10.2478/raft-2022-0049$$EPDF$$P50$$Gwalterdegruyter$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://sciendo.com/article/10.2478/raft-2022-0049$$EHTML$$P50$$Gwalterdegruyter$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27923,27924,76035,76036</link.rule.ids></links><search><creatorcontrib>Bălaşa, Răzvan-Ionuț</creatorcontrib><creatorcontrib>Bîlu, Marian Ciprian</creatorcontrib><creatorcontrib>Iordache, Cătălin</creatorcontrib><title>A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control</title><title>Land Forces Academy review</title><description>The latest developments in the field of Machine Learning (ML), especially Reinforcement Learning (RL) techniques, reduce the need of having pre-existing data available. In this paper, we are presenting a Reinforcement Learning approach to Unmanned Aerial Vehicles (UAV) trajectory tracking and attitude control for an X configuration quadcopter. The proposed solution aims to tackle different maneuvers and to be able to withstand a wide variety of environmental disturbances, both while ensuring the success of the mission for which the Unmanned Aerial Vehicle has been designed. The Proximal Policy Optimization (PPO) solution has first been trained in a simulation environment. The model of the vehicle is designed to take into account various configurations, including changes of mass, while the model of the environment contains various disturbances sources.</description><subject>Attitude control</subject><subject>Configurations</subject><subject>Control algorithms</subject><subject>Disturbances</subject><subject>Energy consumption</subject><subject>Machine learning</subject><subject>Optimization</subject><subject>proximal policy optimization</subject><subject>reinforcement learning</subject><subject>Simulation</subject><subject>Tracking control</subject><subject>Trajectory control</subject><subject>Unmanned aerial vehicles</subject><subject>Vehicles</subject><subject>Velocity</subject><issn>2247-840X</issn><issn>1582-6384</issn><issn>2247-840X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNptkM1Lw0AQxYMoWGqvnhc8p85-tNmAl1D8gkKLWPEWNptJuzXZjZstWv96UyrowdM8hvfeDL8ouqQwZiKR115VIWbAWAwg0pNowPp1LAW8nv7R59Go67YAQCHhU8YH0VtGlt59mkbVZOlqo_dk0QbTmC8VjLPkCY2tnNfYoA1kjspbY9cka1vvlN6Q4MjKNspaLEmG3vQ1L7gxusaOZCGYsCuRzJwN3tUX0Vml6g5HP3MYre5un2cP8Xxx_zjL5rGmU4BYyZRjWmhWpEXCUQpMqWQKC5pUgnJJCykEpRR5OUGN05RBqau0mqQC9EQyPoyujr39j-877EK-dTtv-5M5B8mmkgFPetf46NLedZ3HKm99j8Hvcwr5gWl-YJofmOYHpn3g5hj4UHVAX-La7_a9-G3_P8gSIQD4N4xnfts</recordid><startdate>20221201</startdate><enddate>20221201</enddate><creator>Bălaşa, Răzvan-Ionuț</creator><creator>Bîlu, Marian Ciprian</creator><creator>Iordache, Cătălin</creator><general>Sciendo</general><general>Nicolae Balcescu</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7XB</scope><scope>88F</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BYOGL</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>M1Q</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope></search><sort><creationdate>20221201</creationdate><title>A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control</title><author>Bălaşa, Răzvan-Ionuț ; Bîlu, Marian Ciprian ; Iordache, Cătălin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1600-a893e9bc2b9b73e84e9182aeb17f41381b844111e3d5ece6920dcf9f5940c5823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Attitude control</topic><topic>Configurations</topic><topic>Control algorithms</topic><topic>Disturbances</topic><topic>Energy consumption</topic><topic>Machine learning</topic><topic>Optimization</topic><topic>proximal policy optimization</topic><topic>reinforcement learning</topic><topic>Simulation</topic><topic>Tracking control</topic><topic>Trajectory control</topic><topic>Unmanned aerial vehicles</topic><topic>Vehicles</topic><topic>Velocity</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bălaşa, Răzvan-Ionuț</creatorcontrib><creatorcontrib>Bîlu, Marian Ciprian</creatorcontrib><creatorcontrib>Iordache, Cătălin</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Military Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>East Europe, Central Europe Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Military Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</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>ProQuest Central Basic</collection><jtitle>Land Forces Academy review</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bălaşa, Răzvan-Ionuț</au><au>Bîlu, Marian Ciprian</au><au>Iordache, Cătălin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control</atitle><jtitle>Land Forces Academy review</jtitle><date>2022-12-01</date><risdate>2022</risdate><volume>27</volume><issue>4</issue><spage>400</spage><epage>410</epage><pages>400-410</pages><issn>2247-840X</issn><issn>1582-6384</issn><eissn>2247-840X</eissn><abstract>The latest developments in the field of Machine Learning (ML), especially Reinforcement Learning (RL) techniques, reduce the need of having pre-existing data available. In this paper, we are presenting a Reinforcement Learning approach to Unmanned Aerial Vehicles (UAV) trajectory tracking and attitude control for an X configuration quadcopter. The proposed solution aims to tackle different maneuvers and to be able to withstand a wide variety of environmental disturbances, both while ensuring the success of the mission for which the Unmanned Aerial Vehicle has been designed. The Proximal Policy Optimization (PPO) solution has first been trained in a simulation environment. The model of the vehicle is designed to take into account various configurations, including changes of mass, while the model of the environment contains various disturbances sources.</abstract><cop>Sibiu</cop><pub>Sciendo</pub><doi>10.2478/raft-2022-0049</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2247-840X |
| ispartof | Land Forces Academy review, 2022-12, Vol.27 (4), p.400-410 |
| issn | 2247-840X 1582-6384 2247-840X |
| language | eng |
| recordid | cdi_proquest_journals_3082682037 |
| source | De Gruyter Open Access Journals; Alma/SFX Local Collection; Sciendo |
| subjects | Attitude control Configurations Control algorithms Disturbances Energy consumption Machine learning Optimization proximal policy optimization reinforcement learning Simulation Tracking control Trajectory control Unmanned aerial vehicles Vehicles Velocity |
| title | A Proximal Policy Optimization Reinforcement Learning Approach to Unmanned Aerial Vehicles Attitude Control |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T22%3A17%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Proximal%20Policy%20Optimization%20Reinforcement%20Learning%20Approach%20to%20Unmanned%20Aerial%20Vehicles%20Attitude%20Control&rft.jtitle=Land%20Forces%20Academy%20review&rft.au=B%C4%83la%C5%9Fa,%20R%C4%83zvan-Ionu%C8%9B&rft.date=2022-12-01&rft.volume=27&rft.issue=4&rft.spage=400&rft.epage=410&rft.pages=400-410&rft.issn=2247-840X&rft.eissn=2247-840X&rft_id=info:doi/10.2478/raft-2022-0049&rft_dat=%3Cproquest_cross%3E3082682037%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3082682037&rft_id=info:pmid/&rfr_iscdi=true |