Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949490711> ?p ?o ?g. }
- W2949490711 abstract "Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of training data. In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when sufficient data augmentation is used) outperforms state-of-the-art methods and flies more consistently than many human pilots. Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient on-board processing critical for real-world deployment. From a broader perspective, our results underline the importance of extensive data augmentation techniques to improve robustness in end-to-end learning setups." @default.
- W2949490711 created "2019-06-27" @default.
- W2949490711 creator A5024763828 @default.
- W2949490711 creator A5032952197 @default.
- W2949490711 creator A5039203502 @default.
- W2949490711 creator A5052810777 @default.
- W2949490711 creator A5075952375 @default.
- W2949490711 date "2017-08-19" @default.
- W2949490711 modified "2023-09-27" @default.
- W2949490711 title "Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation" @default.
- W2949490711 cites W1569657508 @default.
- W2949490711 cites W1964201035 @default.
- W2949490711 cites W1993309788 @default.
- W2949490711 cites W1996626756 @default.
- W2949490711 cites W2010302808 @default.
- W2949490711 cites W2038794597 @default.
- W2949490711 cites W2050155800 @default.
- W2949490711 cites W2053621240 @default.
- W2949490711 cites W2056083843 @default.
- W2949490711 cites W2059100041 @default.
- W2949490711 cites W2059704894 @default.
- W2949490711 cites W2104733512 @default.
- W2949490711 cites W2133233905 @default.
- W2949490711 cites W2145339207 @default.
- W2949490711 cites W2151210636 @default.
- W2949490711 cites W2153062878 @default.
- W2949490711 cites W2206316079 @default.
- W2949490711 cites W2218761850 @default.
- W2949490711 cites W2342840547 @default.
- W2949490711 cites W2465948386 @default.
- W2949490711 cites W2487365028 @default.
- W2949490711 cites W2518876086 @default.
- W2949490711 cites W2604382266 @default.
- W2949490711 cites W2605314490 @default.
- W2949490711 cites W2615547864 @default.
- W2949490711 cites W2739330054 @default.
- W2949490711 cites W276602078 @default.
- W2949490711 cites W2767621168 @default.
- W2949490711 cites W2949907962 @default.
- W2949490711 cites W2951384764 @default.
- W2949490711 cites W2952578114 @default.
- W2949490711 cites W2953100850 @default.
- W2949490711 cites W2953248129 @default.
- W2949490711 cites W2963864421 @default.
- W2949490711 cites W2964043796 @default.
- W2949490711 hasPublicationYear "2017" @default.
- W2949490711 type Work @default.
- W2949490711 sameAs 2949490711 @default.
- W2949490711 citedByCount "3" @default.
- W2949490711 countsByYear W29494907112018 @default.
- W2949490711 crossrefType "posted-content" @default.
- W2949490711 hasAuthorship W2949490711A5024763828 @default.
- W2949490711 hasAuthorship W2949490711A5032952197 @default.
- W2949490711 hasAuthorship W2949490711A5039203502 @default.
- W2949490711 hasAuthorship W2949490711A5052810777 @default.
- W2949490711 hasAuthorship W2949490711A5075952375 @default.
- W2949490711 hasConcept C104317684 @default.
- W2949490711 hasConcept C105339364 @default.
- W2949490711 hasConcept C108583219 @default.
- W2949490711 hasConcept C115903868 @default.
- W2949490711 hasConcept C119857082 @default.
- W2949490711 hasConcept C127413603 @default.
- W2949490711 hasConcept C132964779 @default.
- W2949490711 hasConcept C14185376 @default.
- W2949490711 hasConcept C154945302 @default.
- W2949490711 hasConcept C185592680 @default.
- W2949490711 hasConcept C199360897 @default.
- W2949490711 hasConcept C201995342 @default.
- W2949490711 hasConcept C2780451532 @default.
- W2949490711 hasConcept C41008148 @default.
- W2949490711 hasConcept C50644808 @default.
- W2949490711 hasConcept C55493867 @default.
- W2949490711 hasConcept C63479239 @default.
- W2949490711 hasConcept C74296488 @default.
- W2949490711 hasConcept C79403827 @default.
- W2949490711 hasConceptScore W2949490711C104317684 @default.
- W2949490711 hasConceptScore W2949490711C105339364 @default.
- W2949490711 hasConceptScore W2949490711C108583219 @default.
- W2949490711 hasConceptScore W2949490711C115903868 @default.
- W2949490711 hasConceptScore W2949490711C119857082 @default.
- W2949490711 hasConceptScore W2949490711C127413603 @default.
- W2949490711 hasConceptScore W2949490711C132964779 @default.
- W2949490711 hasConceptScore W2949490711C14185376 @default.
- W2949490711 hasConceptScore W2949490711C154945302 @default.
- W2949490711 hasConceptScore W2949490711C185592680 @default.
- W2949490711 hasConceptScore W2949490711C199360897 @default.
- W2949490711 hasConceptScore W2949490711C201995342 @default.
- W2949490711 hasConceptScore W2949490711C2780451532 @default.
- W2949490711 hasConceptScore W2949490711C41008148 @default.
- W2949490711 hasConceptScore W2949490711C50644808 @default.
- W2949490711 hasConceptScore W2949490711C55493867 @default.
- W2949490711 hasConceptScore W2949490711C63479239 @default.
- W2949490711 hasConceptScore W2949490711C74296488 @default.
- W2949490711 hasConceptScore W2949490711C79403827 @default.
- W2949490711 hasLocation W29494907111 @default.
- W2949490711 hasOpenAccess W2949490711 @default.
- W2949490711 hasPrimaryLocation W29494907111 @default.
- W2949490711 hasRelatedWork W2550227132 @default.
- W2949490711 hasRelatedWork W2771862810 @default.
- W2949490711 hasRelatedWork W2795837361 @default.