Ourari, R. ; Cui, K. ; Elshamanhory, Ahmed A. ; Koeppl, H. (2022)
Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning.
doi: 10.48550/arXiv.2104.14912
Report, Bibliographie

Kurzbeschreibung (Abstract)

Collision avoidance algorithms are of central interest to many drone applications. In particular, decentralized approaches may be the key to enabling robust drone swarm solutions in cases where centralized communication becomes computationally prohibitive. In this work, we draw biological inspiration from flocks of starlings (Sturnus vulgaris) and apply the insight to end-to-end learned decentralized collision avoidance. More specifically, we propose a new, scalable observation model following a biomimetic nearest-neighbor information constraint that leads to fast learning and good collision avoidance behavior. By proposing a general reinforcement learning approach, we obtain an end-to-end learning-based approach to integrating collision avoidance with arbitrary tasks such as package collection and formation change. To validate the generality of this approach, we successfully apply our methodology through motion models of medium complexity, modeling momentum and nonetheless allowing direct application to real world quadrotors in conjunction with a standard PID controller. In contrast to prior works, we find that in our sufficiently rich motion model, nearest-neighbor information is indeed enough to learn effective collision avoidance behavior. Our learned policies are tested in simulation and subsequently transferred to real-world drones to validate their real-world applicability.

Typ des Eintrags:	Report
Erschienen:	2022
Autor(en):	Ourari, R. ; Cui, K. ; Elshamanhory, Ahmed A. ; Koeppl, H.
Art des Eintrags:	Bibliographie
Titel:	Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning
Sprache:	Englisch
Publikationsjahr:	18 Februar 2022
Verlag:	arXiv
Reihe:	Robotics
Auflage:	3. Version
DOI:	10.48550/arXiv.2104.14912
URL / URN:	https://arxiv.org/abs/2104.14912v3
Zugehörige Links:	Verwandtes Werk Verwandtes Werk
Kurzbeschreibung (Abstract):	Collision avoidance algorithms are of central interest to many drone applications. In particular, decentralized approaches may be the key to enabling robust drone swarm solutions in cases where centralized communication becomes computationally prohibitive. In this work, we draw biological inspiration from flocks of starlings (Sturnus vulgaris) and apply the insight to end-to-end learned decentralized collision avoidance. More specifically, we propose a new, scalable observation model following a biomimetic nearest-neighbor information constraint that leads to fast learning and good collision avoidance behavior. By proposing a general reinforcement learning approach, we obtain an end-to-end learning-based approach to integrating collision avoidance with arbitrary tasks such as package collection and formation change. To validate the generality of this approach, we successfully apply our methodology through motion models of medium complexity, modeling momentum and nonetheless allowing direct application to real world quadrotors in conjunction with a standard PID controller. In contrast to prior works, we find that in our sufficiently rich motion model, nearest-neighbor information is indeed enough to learn effective collision avoidance behavior. Our learned policies are tested in simulation and subsequently transferred to real-world drones to validate their real-world applicability.
Freie Schlagworte:	emergenCITY_KOM, Robotics, Artificial Intelligence, AI, Machine Learning, ML
Zusätzliche Informationen:	neuste Version zu "Decentralized Swarm Collision Avoidance for Quadrotors via End-to-End Reinforcement Learning"
Fachbereich(e)/-gebiet(e):	18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik > Bioinspirierte Kommunikationssysteme 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Nachrichtentechnik LOEWE LOEWE > LOEWE-Zentren LOEWE > LOEWE-Zentren > emergenCITY
Hinterlegungsdatum:	28 Feb 2022 09:56
Letzte Änderung:	19 Dez 2024 11:04
PPN:
Export:	MODSBibTeXMultiline CSVAtomSimple MetadataRDF+XMLEndNoteJSONASCII CitationIBW_RDAEP3 XMLHTML CitationDublin CoreT2T_XML
Suche nach Titel in:	TUfind oder in Google

Verfügbare Versionen dieses Eintrags

• Decentralized Swarm Collision Avoidance for Quadrotors via End-to-End Reinforcement Learning. (deposited 06 Sep 2021 07:19)
  • Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning. (deposited 28 Feb 2022 09:56) [Gegenwärtig angezeigt]

Frage zum Eintrag

Optionen (nur für Redakteure)

Redaktionelle Details anzeigen