Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890755534> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2890755534 abstract "The autonomous landing of an unmanned aerial vehicle (UAV) is still an open problem. Previous work focused on the use of hand-crafted geometric features and sensor-data fusion for identifying a fiducial marker and guide the UAV toward it. In this article we propose a method based on deep reinforcement learning that only requires low-resolution images coming from a down looking camera in order to drive the vehicle. The proposed approach is based on a hierarchy of Deep Q-Networks (DQNs) that are used as high-end control policy for the navigation in different phases. We implemented various technical solutions, such as the combination of vanilla and double DQNs trained using a form of prioritized buffer replay that separates experiences in multiple containers. The optimal control policy is learned without any human supervision, providing the agent with a sparse reward feedback indicating the success or failure of the landing. The results show that the quadrotor can autonomously land on a large variety of simulated environments and with relevant noise, proving that the underline DQNs are able to generalise effectively on unseen scenarios. Furthermore, it was proved that in some conditions the network outperformed human pilots." @default.
- W2890755534 created "2018-09-27" @default.
- W2890755534 creator A5009664515 @default.
- W2890755534 creator A5016136941 @default.
- W2890755534 creator A5020036481 @default.
- W2890755534 creator A5020786491 @default.
- W2890755534 creator A5088288633 @default.
- W2890755534 creator A5088598322 @default.
- W2890755534 creator A5091768977 @default.
- W2890755534 date "2018-06-01" @default.
- W2890755534 modified "2023-10-12" @default.
- W2890755534 title "Toward End-to-End Control for UAV Autonomous Landing via Deep Reinforcement Learning" @default.
- W2890755534 cites W1580579560 @default.
- W2890755534 cites W1602540331 @default.
- W2890755534 cites W1934909785 @default.
- W2890755534 cites W1969161726 @default.
- W2890755534 cites W1975713381 @default.
- W2890755534 cites W1980620643 @default.
- W2890755534 cites W1995067233 @default.
- W2890755534 cites W2027865396 @default.
- W2890755534 cites W2035981208 @default.
- W2890755534 cites W2076063813 @default.
- W2890755534 cites W2085277287 @default.
- W2890755534 cites W2085635066 @default.
- W2890755534 cites W2107726111 @default.
- W2890755534 cites W2132161921 @default.
- W2890755534 cites W2145339207 @default.
- W2890755534 cites W2170742340 @default.
- W2890755534 cites W2326713744 @default.
- W2890755534 cites W2341818270 @default.
- W2890755534 cites W2341833211 @default.
- W2890755534 cites W2418481778 @default.
- W2890755534 cites W2626368014 @default.
- W2890755534 cites W2767950020 @default.
- W2890755534 cites W2797935508 @default.
- W2890755534 cites W2963871073 @default.
- W2890755534 doi "https://doi.org/10.1109/icuas.2018.8453449" @default.
- W2890755534 hasPublicationYear "2018" @default.
- W2890755534 type Work @default.
- W2890755534 sameAs 2890755534 @default.
- W2890755534 citedByCount "46" @default.
- W2890755534 countsByYear W28907555342019 @default.
- W2890755534 countsByYear W28907555342020 @default.
- W2890755534 countsByYear W28907555342021 @default.
- W2890755534 countsByYear W28907555342022 @default.
- W2890755534 countsByYear W28907555342023 @default.
- W2890755534 crossrefType "proceedings-article" @default.
- W2890755534 hasAuthorship W2890755534A5009664515 @default.
- W2890755534 hasAuthorship W2890755534A5016136941 @default.
- W2890755534 hasAuthorship W2890755534A5020036481 @default.
- W2890755534 hasAuthorship W2890755534A5020786491 @default.
- W2890755534 hasAuthorship W2890755534A5088288633 @default.
- W2890755534 hasAuthorship W2890755534A5088598322 @default.
- W2890755534 hasAuthorship W2890755534A5091768977 @default.
- W2890755534 hasConcept C108583219 @default.
- W2890755534 hasConcept C115961682 @default.
- W2890755534 hasConcept C154945302 @default.
- W2890755534 hasConcept C162324750 @default.
- W2890755534 hasConcept C2775924081 @default.
- W2890755534 hasConcept C31170391 @default.
- W2890755534 hasConcept C34447519 @default.
- W2890755534 hasConcept C41008148 @default.
- W2890755534 hasConcept C74296488 @default.
- W2890755534 hasConcept C79403827 @default.
- W2890755534 hasConcept C97541855 @default.
- W2890755534 hasConcept C99498987 @default.
- W2890755534 hasConceptScore W2890755534C108583219 @default.
- W2890755534 hasConceptScore W2890755534C115961682 @default.
- W2890755534 hasConceptScore W2890755534C154945302 @default.
- W2890755534 hasConceptScore W2890755534C162324750 @default.
- W2890755534 hasConceptScore W2890755534C2775924081 @default.
- W2890755534 hasConceptScore W2890755534C31170391 @default.
- W2890755534 hasConceptScore W2890755534C34447519 @default.
- W2890755534 hasConceptScore W2890755534C41008148 @default.
- W2890755534 hasConceptScore W2890755534C74296488 @default.
- W2890755534 hasConceptScore W2890755534C79403827 @default.
- W2890755534 hasConceptScore W2890755534C97541855 @default.
- W2890755534 hasConceptScore W2890755534C99498987 @default.
- W2890755534 hasLocation W28907555341 @default.
- W2890755534 hasOpenAccess W2890755534 @default.
- W2890755534 hasPrimaryLocation W28907555341 @default.
- W2890755534 hasRelatedWork W260766989 @default.
- W2890755534 hasRelatedWork W2731899572 @default.
- W2890755534 hasRelatedWork W2959276766 @default.
- W2890755534 hasRelatedWork W2976657239 @default.
- W2890755534 hasRelatedWork W3009238340 @default.
- W2890755534 hasRelatedWork W3074294383 @default.
- W2890755534 hasRelatedWork W3139193008 @default.
- W2890755534 hasRelatedWork W3215138031 @default.
- W2890755534 hasRelatedWork W4206669594 @default.
- W2890755534 hasRelatedWork W4295941380 @default.
- W2890755534 isParatext "false" @default.
- W2890755534 isRetracted "false" @default.
- W2890755534 magId "2890755534" @default.
- W2890755534 workType "article" @default.