MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning
Achieving safe and precise landings for a swarm of drones poses a significant challenge, primarily attributed to conventional control and planning methods. This paper presents the implementation of multi-agent deep reinforcement learning (MADRL) techniques for the precise landing of a drone swarm at...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Aschu, Demetros Peter, Robinroy Karaf, Sausar Fedoseev, Aleksey Tsetserukou, Dzmitry |
| description | Achieving safe and precise landings for a swarm of drones poses a significant
challenge, primarily attributed to conventional control and planning methods.
This paper presents the implementation of multi-agent deep reinforcement
learning (MADRL) techniques for the precise landing of a drone swarm at
relocated target locations. The system is trained in a realistic simulated
environment with a maximum velocity of 3 m/s in training spaces of 4 x 4 x 4 m
and deployed utilizing Crazyflie drones with a Vicon indoor localization
system. The experimental results revealed that the proposed approach achieved a
landing accuracy of 2.26 cm on stationary and 3.93 cm on moving platforms
surpassing a baseline method used with a Proportional-integral-derivative (PID)
controller with an Artificial Potential Field (APF). This research highlights
drone landing technologies that eliminate the need for analytical centralized
systems, potentially offering scalability and revolutionizing applications in
logistics, safety, and rescue missions. |
| doi_str_mv | 10.48550/arxiv.2406.04159 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2406_04159</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2406_04159</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2406_041593</originalsourceid><addsrcrecordid>eNqFjs0KgkAURmfTIqoHaNV9gWwsjWonWbRQEGudXOxqAzrKVft5-xpp3-qDw_ngCDG1peVsXFcukF_qYS0dubakY7vbobiGXhygvhHvwIOgSrGACNs7RAVqrXQOWcXgc6UJzk_ksoGuMTjsilZhTroFn6iGmJT-qimVBgWEbN5jMciwaGjy25GYHQ-X_WnelyQ1qxL5nZiipC9a_Tc-HHlAyg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning</title><source>arXiv.org</source><creator>Aschu, Demetros ; Peter, Robinroy ; Karaf, Sausar ; Fedoseev, Aleksey ; Tsetserukou, Dzmitry</creator><creatorcontrib>Aschu, Demetros ; Peter, Robinroy ; Karaf, Sausar ; Fedoseev, Aleksey ; Tsetserukou, Dzmitry</creatorcontrib><description>Achieving safe and precise landings for a swarm of drones poses a significant
challenge, primarily attributed to conventional control and planning methods.
This paper presents the implementation of multi-agent deep reinforcement
learning (MADRL) techniques for the precise landing of a drone swarm at
relocated target locations. The system is trained in a realistic simulated
environment with a maximum velocity of 3 m/s in training spaces of 4 x 4 x 4 m
and deployed utilizing Crazyflie drones with a Vicon indoor localization
system. The experimental results revealed that the proposed approach achieved a
landing accuracy of 2.26 cm on stationary and 3.93 cm on moving platforms
surpassing a baseline method used with a Proportional-integral-derivative (PID)
controller with an Artificial Potential Field (APF). This research highlights
drone landing technologies that eliminate the need for analytical centralized
systems, potentially offering scalability and revolutionizing applications in
logistics, safety, and rescue missions.</description><identifier>DOI: 10.48550/arxiv.2406.04159</identifier><language>eng</language><subject>Computer Science - Multiagent Systems ; Computer Science - Robotics</subject><creationdate>2024-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2406.04159$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2406.04159$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Aschu, Demetros</creatorcontrib><creatorcontrib>Peter, Robinroy</creatorcontrib><creatorcontrib>Karaf, Sausar</creatorcontrib><creatorcontrib>Fedoseev, Aleksey</creatorcontrib><creatorcontrib>Tsetserukou, Dzmitry</creatorcontrib><title>MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning</title><description>Achieving safe and precise landings for a swarm of drones poses a significant
challenge, primarily attributed to conventional control and planning methods.
This paper presents the implementation of multi-agent deep reinforcement
learning (MADRL) techniques for the precise landing of a drone swarm at
relocated target locations. The system is trained in a realistic simulated
environment with a maximum velocity of 3 m/s in training spaces of 4 x 4 x 4 m
and deployed utilizing Crazyflie drones with a Vicon indoor localization
system. The experimental results revealed that the proposed approach achieved a
landing accuracy of 2.26 cm on stationary and 3.93 cm on moving platforms
surpassing a baseline method used with a Proportional-integral-derivative (PID)
controller with an Artificial Potential Field (APF). This research highlights
drone landing technologies that eliminate the need for analytical centralized
systems, potentially offering scalability and revolutionizing applications in
logistics, safety, and rescue missions.</description><subject>Computer Science - Multiagent Systems</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjs0KgkAURmfTIqoHaNV9gWwsjWonWbRQEGudXOxqAzrKVft5-xpp3-qDw_ngCDG1peVsXFcukF_qYS0dubakY7vbobiGXhygvhHvwIOgSrGACNs7RAVqrXQOWcXgc6UJzk_ksoGuMTjsilZhTroFn6iGmJT-qimVBgWEbN5jMciwaGjy25GYHQ-X_WnelyQ1qxL5nZiipC9a_Tc-HHlAyg</recordid><startdate>20240606</startdate><enddate>20240606</enddate><creator>Aschu, Demetros</creator><creator>Peter, Robinroy</creator><creator>Karaf, Sausar</creator><creator>Fedoseev, Aleksey</creator><creator>Tsetserukou, Dzmitry</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240606</creationdate><title>MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning</title><author>Aschu, Demetros ; Peter, Robinroy ; Karaf, Sausar ; Fedoseev, Aleksey ; Tsetserukou, Dzmitry</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2406_041593</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Multiagent Systems</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Aschu, Demetros</creatorcontrib><creatorcontrib>Peter, Robinroy</creatorcontrib><creatorcontrib>Karaf, Sausar</creatorcontrib><creatorcontrib>Fedoseev, Aleksey</creatorcontrib><creatorcontrib>Tsetserukou, Dzmitry</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Aschu, Demetros</au><au>Peter, Robinroy</au><au>Karaf, Sausar</au><au>Fedoseev, Aleksey</au><au>Tsetserukou, Dzmitry</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning</atitle><date>2024-06-06</date><risdate>2024</risdate><abstract>Achieving safe and precise landings for a swarm of drones poses a significant
challenge, primarily attributed to conventional control and planning methods.
This paper presents the implementation of multi-agent deep reinforcement
learning (MADRL) techniques for the precise landing of a drone swarm at
relocated target locations. The system is trained in a realistic simulated
environment with a maximum velocity of 3 m/s in training spaces of 4 x 4 x 4 m
and deployed utilizing Crazyflie drones with a Vicon indoor localization
system. The experimental results revealed that the proposed approach achieved a
landing accuracy of 2.26 cm on stationary and 3.93 cm on moving platforms
surpassing a baseline method used with a Proportional-integral-derivative (PID)
controller with an Artificial Potential Field (APF). This research highlights
drone landing technologies that eliminate the need for analytical centralized
systems, potentially offering scalability and revolutionizing applications in
logistics, safety, and rescue missions.</abstract><doi>10.48550/arxiv.2406.04159</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2406.04159 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2406_04159 |
| source | arXiv.org |
| subjects | Computer Science - Multiagent Systems Computer Science - Robotics |
| title | MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T14%3A07%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MARLander:%20A%20Local%20Path%20Planning%20for%20Drone%20Swarms%20using%20Multiagent%20Deep%20Reinforcement%20Learning&rft.au=Aschu,%20Demetros&rft.date=2024-06-06&rft_id=info:doi/10.48550/arxiv.2406.04159&rft_dat=%3Carxiv_GOX%3E2406_04159%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |