Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200959103> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3200959103 endingPage "270" @default.
- W3200959103 startingPage "256" @default.
- W3200959103 abstract "Purpose This paper aims to realize a fully distributed multi-UAV collision detection and avoidance based on deep reinforcement learning (DRL). To deal with the problem of low sample efficiency in DRL and speed up the training. To improve the applicability and reliability of the DRL-based approach in multi-UAV control problems. Design/methodology/approach In this paper, a fully distributed collision detection and avoidance approach for multi-UAV based on DRL is proposed. A method that integrates human experience into policy training via a human experience-based adviser is proposed. The authors propose a hybrid control method which combines the learning-based policy with traditional model-based control. Extensive experiments including simulations, real flights and comparative experiments are conducted to evaluate the performance of the approach. Findings A fully distributed multi-UAV collision detection and avoidance method based on DRL is realized. The reward curve shows that the training process when integrating human experience is significantly accelerated and the mean episode reward is higher than the pure DRL method. The experimental results show that the DRL method with human experience integration has a significant improvement than the pure DRL method for multi-UAV collision detection and avoidance. Moreover, the safer flight brought by the hybrid control method has also been validated. Originality/value The fully distributed architecture is suitable for large-scale unmanned aerial vehicle (UAV) swarms and real applications. The DRL method with human experience integration has significantly accelerated the training compared to the pure DRL method. The proposed hybrid control strategy makes up for the shortcomings of two-dimensional light detection and ranging and other puzzles in applications." @default.
- W3200959103 created "2021-09-27" @default.
- W3200959103 creator A5007054845 @default.
- W3200959103 creator A5024298757 @default.
- W3200959103 creator A5039222132 @default.
- W3200959103 creator A5053112608 @default.
- W3200959103 creator A5080470028 @default.
- W3200959103 creator A5085719140 @default.
- W3200959103 date "2021-09-24" @default.
- W3200959103 modified "2023-09-26" @default.
- W3200959103 title "Integrating human experience in deep reinforcement learning for multi-UAV collision detection and avoidance" @default.
- W3200959103 cites W1578294898 @default.
- W3200959103 cites W2006619020 @default.
- W3200959103 cites W2018284273 @default.
- W3200959103 cites W2046456604 @default.
- W3200959103 cites W2072400093 @default.
- W3200959103 cites W2084601418 @default.
- W3200959103 cites W2133050889 @default.
- W3200959103 cites W2142943472 @default.
- W3200959103 cites W2145339207 @default.
- W3200959103 cites W2150818585 @default.
- W3200959103 cites W2156869222 @default.
- W3200959103 cites W2418368699 @default.
- W3200959103 cites W2799745602 @default.
- W3200959103 cites W2963722165 @default.
- W3200959103 cites W3040669448 @default.
- W3200959103 cites W3104860527 @default.
- W3200959103 cites W4246518147 @default.
- W3200959103 doi "https://doi.org/10.1108/ir-06-2021-0116" @default.
- W3200959103 hasPublicationYear "2021" @default.
- W3200959103 type Work @default.
- W3200959103 sameAs 3200959103 @default.
- W3200959103 citedByCount "2" @default.
- W3200959103 countsByYear W32009591032022 @default.
- W3200959103 countsByYear W32009591032023 @default.
- W3200959103 crossrefType "journal-article" @default.
- W3200959103 hasAuthorship W3200959103A5007054845 @default.
- W3200959103 hasAuthorship W3200959103A5024298757 @default.
- W3200959103 hasAuthorship W3200959103A5039222132 @default.
- W3200959103 hasAuthorship W3200959103A5053112608 @default.
- W3200959103 hasAuthorship W3200959103A5080470028 @default.
- W3200959103 hasAuthorship W3200959103A5085719140 @default.
- W3200959103 hasConcept C121704057 @default.
- W3200959103 hasConcept C154945302 @default.
- W3200959103 hasConcept C199668693 @default.
- W3200959103 hasConcept C2775924081 @default.
- W3200959103 hasConcept C2777016798 @default.
- W3200959103 hasConcept C2780864053 @default.
- W3200959103 hasConcept C38652104 @default.
- W3200959103 hasConcept C41008148 @default.
- W3200959103 hasConcept C97541855 @default.
- W3200959103 hasConceptScore W3200959103C121704057 @default.
- W3200959103 hasConceptScore W3200959103C154945302 @default.
- W3200959103 hasConceptScore W3200959103C199668693 @default.
- W3200959103 hasConceptScore W3200959103C2775924081 @default.
- W3200959103 hasConceptScore W3200959103C2777016798 @default.
- W3200959103 hasConceptScore W3200959103C2780864053 @default.
- W3200959103 hasConceptScore W3200959103C38652104 @default.
- W3200959103 hasConceptScore W3200959103C41008148 @default.
- W3200959103 hasConceptScore W3200959103C97541855 @default.
- W3200959103 hasIssue "2" @default.
- W3200959103 hasLocation W32009591031 @default.
- W3200959103 hasOpenAccess W3200959103 @default.
- W3200959103 hasPrimaryLocation W32009591031 @default.
- W3200959103 hasRelatedWork W1504073209 @default.
- W3200959103 hasRelatedWork W1600016555 @default.
- W3200959103 hasRelatedWork W2139274798 @default.
- W3200959103 hasRelatedWork W2162369036 @default.
- W3200959103 hasRelatedWork W2858289757 @default.
- W3200959103 hasRelatedWork W2897792155 @default.
- W3200959103 hasRelatedWork W3066494597 @default.
- W3200959103 hasRelatedWork W3200959103 @default.
- W3200959103 hasRelatedWork W3208724288 @default.
- W3200959103 hasRelatedWork W4293067752 @default.
- W3200959103 hasVolume "49" @default.
- W3200959103 isParatext "false" @default.
- W3200959103 isRetracted "false" @default.
- W3200959103 magId "3200959103" @default.
- W3200959103 workType "article" @default.