Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081702502> ?p ?o ?g. }
- W3081702502 abstract "We present an imitation learning method for autonomous drone patrolling based only on raw videos. Different from previous methods, we propose to let the drone learn patrolling in the air by observing and imitating how a human navigator does it on the ground. The observation process enables the automatic collection and annotation of data using inter-frame geometric consistency, resulting in less manual effort and high accuracy. Then a newly designed neural network is trained based on the annotated data to predict appropriate directions and translations for the drone to patrol in a lane-keeping manner as humans. Our method allows the drone to fly at a high altitude with a broad view and low risk. It can also detect all accessible directions at crossroads and further carry out the integration of available user instructions and autonomous patrolling control commands. Extensive experiments are conducted to demonstrate the accuracy of the proposed imitating learning process as well as the reliability of the holistic system for autonomous drone navigation. The codes, datasets as well as video demonstrations are available at https://vsislab.github.io/uavpatrol" @default.
- W3081702502 created "2020-09-08" @default.
- W3081702502 creator A5012470834 @default.
- W3081702502 creator A5047100124 @default.
- W3081702502 creator A5061179511 @default.
- W3081702502 creator A5069281260 @default.
- W3081702502 creator A5077509941 @default.
- W3081702502 date "2020-08-30" @default.
- W3081702502 modified "2023-10-16" @default.
- W3081702502 title "Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator" @default.
- W3081702502 cites W1493644597 @default.
- W3081702502 cites W2151103935 @default.
- W3081702502 cites W2155182160 @default.
- W3081702502 cites W2218761850 @default.
- W3081702502 cites W2296673577 @default.
- W3081702502 cites W2302255633 @default.
- W3081702502 cites W2346227780 @default.
- W3081702502 cites W2395047452 @default.
- W3081702502 cites W2533363744 @default.
- W3081702502 cites W2558899534 @default.
- W3081702502 cites W2568917080 @default.
- W3081702502 cites W2570977491 @default.
- W3081702502 cites W2576628805 @default.
- W3081702502 cites W2615547864 @default.
- W3081702502 cites W2759507904 @default.
- W3081702502 cites W2769112066 @default.
- W3081702502 cites W2782491529 @default.
- W3081702502 cites W2782715402 @default.
- W3081702502 cites W2788239209 @default.
- W3081702502 cites W2794803852 @default.
- W3081702502 cites W2805327738 @default.
- W3081702502 cites W2806163172 @default.
- W3081702502 cites W2946887169 @default.
- W3081702502 cites W2962730596 @default.
- W3081702502 cites W2962787969 @default.
- W3081702502 cites W2962894046 @default.
- W3081702502 cites W2962957031 @default.
- W3081702502 cites W2963110888 @default.
- W3081702502 cites W2963802910 @default.
- W3081702502 cites W2982095652 @default.
- W3081702502 cites W3004383953 @default.
- W3081702502 cites W3103278230 @default.
- W3081702502 doi "https://doi.org/10.48550/arxiv.2008.13193" @default.
- W3081702502 hasPublicationYear "2020" @default.
- W3081702502 type Work @default.
- W3081702502 sameAs 3081702502 @default.
- W3081702502 citedByCount "0" @default.
- W3081702502 crossrefType "posted-content" @default.
- W3081702502 hasAuthorship W3081702502A5012470834 @default.
- W3081702502 hasAuthorship W3081702502A5047100124 @default.
- W3081702502 hasAuthorship W3081702502A5061179511 @default.
- W3081702502 hasAuthorship W3081702502A5069281260 @default.
- W3081702502 hasAuthorship W3081702502A5077509941 @default.
- W3081702502 hasBestOaLocation W30817025021 @default.
- W3081702502 hasConcept C107457646 @default.
- W3081702502 hasConcept C108583219 @default.
- W3081702502 hasConcept C110698143 @default.
- W3081702502 hasConcept C111919701 @default.
- W3081702502 hasConcept C121332964 @default.
- W3081702502 hasConcept C126042441 @default.
- W3081702502 hasConcept C126388530 @default.
- W3081702502 hasConcept C127413603 @default.
- W3081702502 hasConcept C146978453 @default.
- W3081702502 hasConcept C154945302 @default.
- W3081702502 hasConcept C15744967 @default.
- W3081702502 hasConcept C163258240 @default.
- W3081702502 hasConcept C177264268 @default.
- W3081702502 hasConcept C17744445 @default.
- W3081702502 hasConcept C199360897 @default.
- W3081702502 hasConcept C199539241 @default.
- W3081702502 hasConcept C2776436953 @default.
- W3081702502 hasConcept C2776760102 @default.
- W3081702502 hasConcept C2779199153 @default.
- W3081702502 hasConcept C31972630 @default.
- W3081702502 hasConcept C41008148 @default.
- W3081702502 hasConcept C43214815 @default.
- W3081702502 hasConcept C54355233 @default.
- W3081702502 hasConcept C59519942 @default.
- W3081702502 hasConcept C62520636 @default.
- W3081702502 hasConcept C76155785 @default.
- W3081702502 hasConcept C77805123 @default.
- W3081702502 hasConcept C86803240 @default.
- W3081702502 hasConcept C98045186 @default.
- W3081702502 hasConceptScore W3081702502C107457646 @default.
- W3081702502 hasConceptScore W3081702502C108583219 @default.
- W3081702502 hasConceptScore W3081702502C110698143 @default.
- W3081702502 hasConceptScore W3081702502C111919701 @default.
- W3081702502 hasConceptScore W3081702502C121332964 @default.
- W3081702502 hasConceptScore W3081702502C126042441 @default.
- W3081702502 hasConceptScore W3081702502C126388530 @default.
- W3081702502 hasConceptScore W3081702502C127413603 @default.
- W3081702502 hasConceptScore W3081702502C146978453 @default.
- W3081702502 hasConceptScore W3081702502C154945302 @default.
- W3081702502 hasConceptScore W3081702502C15744967 @default.
- W3081702502 hasConceptScore W3081702502C163258240 @default.
- W3081702502 hasConceptScore W3081702502C177264268 @default.
- W3081702502 hasConceptScore W3081702502C17744445 @default.
- W3081702502 hasConceptScore W3081702502C199360897 @default.
- W3081702502 hasConceptScore W3081702502C199539241 @default.
- W3081702502 hasConceptScore W3081702502C2776436953 @default.