Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897097805> ?p ?o ?g. }
- W2897097805 abstract "Autonomous micro aerial vehicles still struggle with fast and agile maneuvers, dynamic environments, imperfect sensing, and state estimation drift. Autonomous drone racing brings these challenges to the fore. Human pilots can fly a previously unseen track after a handful of practice runs. In contrast, state-of-the-art autonomous navigation algorithms require either a precise metric map of the environment or a large amount of training data collected in the track of interest. To bridge this gap, we propose an approach that can fly a new track in a previously unseen environment without a precise map or expensive data collection. Our approach represents the global track layout with coarse gate locations, which can be easily estimated from a single demonstration flight. At test time, a convolutional network predicts the poses of the closest gates along with their uncertainty. These predictions are incorporated by an extended Kalman filter to maintain optimal maximum-a-posteriori estimates of gate locations. This allows the framework to cope with misleading high-variance estimates that could stem from poor observability or lack of visible gates. Given the estimated gate poses, we use model predictive control to quickly and accurately navigate through the track. We conduct extensive experiments in the physical world, demonstrating agile and robust flight through complex and diverse previously-unseen race tracks. The presented approach was used to win the IROS 2018 Autonomous Drone Race Competition, outracing the second-placing team by a factor of two." @default.
- W2897097805 created "2018-10-26" @default.
- W2897097805 creator A5003892206 @default.
- W2897097805 creator A5006181255 @default.
- W2897097805 creator A5008591453 @default.
- W2897097805 creator A5043405996 @default.
- W2897097805 creator A5057116316 @default.
- W2897097805 creator A5076203786 @default.
- W2897097805 creator A5090113830 @default.
- W2897097805 date "2018-10-15" @default.
- W2897097805 modified "2023-09-22" @default.
- W2897097805 title "Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing" @default.
- W2897097805 cites W1560021816 @default.
- W2897097805 cites W2091790851 @default.
- W2897097805 cites W2162991084 @default.
- W2897097805 cites W2167340365 @default.
- W2897097805 cites W2171666055 @default.
- W2897097805 cites W2181845023 @default.
- W2897097805 cites W2216550548 @default.
- W2897097805 cites W2218761850 @default.
- W2897097805 cites W2296673577 @default.
- W2897097805 cites W2411412724 @default.
- W2897097805 cites W2465948386 @default.
- W2897097805 cites W2557430988 @default.
- W2897097805 cites W2564632156 @default.
- W2897097805 cites W2599032451 @default.
- W2897097805 cites W2746584771 @default.
- W2897097805 cites W2772982620 @default.
- W2897097805 cites W2788239209 @default.
- W2897097805 cites W2794268423 @default.
- W2897097805 cites W2891998247 @default.
- W2897097805 cites W2949490711 @default.
- W2897097805 cites W2962865553 @default.
- W2897097805 cites W3102327032 @default.
- W2897097805 hasPublicationYear "2018" @default.
- W2897097805 type Work @default.
- W2897097805 sameAs 2897097805 @default.
- W2897097805 citedByCount "2" @default.
- W2897097805 countsByYear W28970978052020 @default.
- W2897097805 crossrefType "posted-content" @default.
- W2897097805 hasAuthorship W2897097805A5003892206 @default.
- W2897097805 hasAuthorship W2897097805A5006181255 @default.
- W2897097805 hasAuthorship W2897097805A5008591453 @default.
- W2897097805 hasAuthorship W2897097805A5043405996 @default.
- W2897097805 hasAuthorship W2897097805A5057116316 @default.
- W2897097805 hasAuthorship W2897097805A5076203786 @default.
- W2897097805 hasAuthorship W2897097805A5090113830 @default.
- W2897097805 hasConcept C111472728 @default.
- W2897097805 hasConcept C111919701 @default.
- W2897097805 hasConcept C115903868 @default.
- W2897097805 hasConcept C119857082 @default.
- W2897097805 hasConcept C138885662 @default.
- W2897097805 hasConcept C14185376 @default.
- W2897097805 hasConcept C154945302 @default.
- W2897097805 hasConcept C157286648 @default.
- W2897097805 hasConcept C28826006 @default.
- W2897097805 hasConcept C33923547 @default.
- W2897097805 hasConcept C36299963 @default.
- W2897097805 hasConcept C41008148 @default.
- W2897097805 hasConcept C54355233 @default.
- W2897097805 hasConcept C59519942 @default.
- W2897097805 hasConcept C75553542 @default.
- W2897097805 hasConcept C79403827 @default.
- W2897097805 hasConcept C86803240 @default.
- W2897097805 hasConcept C89600930 @default.
- W2897097805 hasConcept C89992363 @default.
- W2897097805 hasConceptScore W2897097805C111472728 @default.
- W2897097805 hasConceptScore W2897097805C111919701 @default.
- W2897097805 hasConceptScore W2897097805C115903868 @default.
- W2897097805 hasConceptScore W2897097805C119857082 @default.
- W2897097805 hasConceptScore W2897097805C138885662 @default.
- W2897097805 hasConceptScore W2897097805C14185376 @default.
- W2897097805 hasConceptScore W2897097805C154945302 @default.
- W2897097805 hasConceptScore W2897097805C157286648 @default.
- W2897097805 hasConceptScore W2897097805C28826006 @default.
- W2897097805 hasConceptScore W2897097805C33923547 @default.
- W2897097805 hasConceptScore W2897097805C36299963 @default.
- W2897097805 hasConceptScore W2897097805C41008148 @default.
- W2897097805 hasConceptScore W2897097805C54355233 @default.
- W2897097805 hasConceptScore W2897097805C59519942 @default.
- W2897097805 hasConceptScore W2897097805C75553542 @default.
- W2897097805 hasConceptScore W2897097805C79403827 @default.
- W2897097805 hasConceptScore W2897097805C86803240 @default.
- W2897097805 hasConceptScore W2897097805C89600930 @default.
- W2897097805 hasConceptScore W2897097805C89992363 @default.
- W2897097805 hasLocation W28970978051 @default.
- W2897097805 hasOpenAccess W2897097805 @default.
- W2897097805 hasPrimaryLocation W28970978051 @default.
- W2897097805 hasRelatedWork W2106789842 @default.
- W2897097805 hasRelatedWork W2145670400 @default.
- W2897097805 hasRelatedWork W2751330670 @default.
- W2897097805 hasRelatedWork W2886996772 @default.
- W2897097805 hasRelatedWork W2889923199 @default.
- W2897097805 hasRelatedWork W2890755534 @default.
- W2897097805 hasRelatedWork W2905052477 @default.
- W2897097805 hasRelatedWork W2911926163 @default.
- W2897097805 hasRelatedWork W2929174622 @default.
- W2897097805 hasRelatedWork W2967464230 @default.
- W2897097805 hasRelatedWork W2981589598 @default.
- W2897097805 hasRelatedWork W2982095652 @default.