Matches in SemOpenAlex for { <https://semopenalex.org/work/W2588610658> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2588610658 abstract "We investigate the use of deep artificial neural networks to approximate the optimal state-feedback control of continuous time, deterministic, non-linear systems. The networks are trained in a supervised manner using trajectories generated by solving the optimal control problem via the Hermite-Simpson transcription method. We find that deep networks are able to represent the optimal state-feedback with high accuracy and precision well outside the training area. We consider non-linear dynamical models under different cost functions that result in both smooth and discontinuous (bang-bang) optimal control solutions. In particular, we investigate the inverted pendulum swing-up and stabilization, a multicopter pin-point landing and a spacecraft free landing problem. Across all domains, we find that deep networks significantly outperform shallow networks in the ability to build an accurate functional representation of the optimal control. In the case of spacecraft and multicopter landing, deep networks are able to achieve safe landings consistently even when starting well outside of the training area." @default.
- W2588610658 created "2017-02-24" @default.
- W2588610658 creator A5020258120 @default.
- W2588610658 creator A5043984392 @default.
- W2588610658 creator A5067306471 @default.
- W2588610658 date "2016-12-01" @default.
- W2588610658 modified "2023-10-18" @default.
- W2588610658 title "Learning the optimal state-feedback using deep networks" @default.
- W2588610658 cites W1677182931 @default.
- W2588610658 cites W1970101292 @default.
- W2588610658 cites W2029776687 @default.
- W2588610658 cites W2032155858 @default.
- W2588610658 cites W2038818107 @default.
- W2588610658 cites W2047090868 @default.
- W2588610658 cites W2076063813 @default.
- W2588610658 cites W2087465258 @default.
- W2588610658 cites W2105080564 @default.
- W2588610658 cites W2108984317 @default.
- W2588610658 cites W2145755350 @default.
- W2588610658 cites W2221321873 @default.
- W2588610658 cites W2546302380 @default.
- W2588610658 cites W2919115771 @default.
- W2588610658 doi "https://doi.org/10.1109/ssci.2016.7850105" @default.
- W2588610658 hasPublicationYear "2016" @default.
- W2588610658 type Work @default.
- W2588610658 sameAs 2588610658 @default.
- W2588610658 citedByCount "16" @default.
- W2588610658 countsByYear W25886106582018 @default.
- W2588610658 countsByYear W25886106582019 @default.
- W2588610658 countsByYear W25886106582020 @default.
- W2588610658 countsByYear W25886106582021 @default.
- W2588610658 countsByYear W25886106582022 @default.
- W2588610658 countsByYear W25886106582023 @default.
- W2588610658 crossrefType "proceedings-article" @default.
- W2588610658 hasAuthorship W2588610658A5020258120 @default.
- W2588610658 hasAuthorship W2588610658A5043984392 @default.
- W2588610658 hasAuthorship W2588610658A5067306471 @default.
- W2588610658 hasConcept C108583219 @default.
- W2588610658 hasConcept C11413529 @default.
- W2588610658 hasConcept C121332964 @default.
- W2588610658 hasConcept C126255220 @default.
- W2588610658 hasConcept C127413603 @default.
- W2588610658 hasConcept C146978453 @default.
- W2588610658 hasConcept C154945302 @default.
- W2588610658 hasConcept C158622935 @default.
- W2588610658 hasConcept C17744445 @default.
- W2588610658 hasConcept C192921069 @default.
- W2588610658 hasConcept C199539241 @default.
- W2588610658 hasConcept C2775924081 @default.
- W2588610658 hasConcept C2776359362 @default.
- W2588610658 hasConcept C29829512 @default.
- W2588610658 hasConcept C33923547 @default.
- W2588610658 hasConcept C41008148 @default.
- W2588610658 hasConcept C47446073 @default.
- W2588610658 hasConcept C48103436 @default.
- W2588610658 hasConcept C50644808 @default.
- W2588610658 hasConcept C62520636 @default.
- W2588610658 hasConcept C91575142 @default.
- W2588610658 hasConcept C94625758 @default.
- W2588610658 hasConceptScore W2588610658C108583219 @default.
- W2588610658 hasConceptScore W2588610658C11413529 @default.
- W2588610658 hasConceptScore W2588610658C121332964 @default.
- W2588610658 hasConceptScore W2588610658C126255220 @default.
- W2588610658 hasConceptScore W2588610658C127413603 @default.
- W2588610658 hasConceptScore W2588610658C146978453 @default.
- W2588610658 hasConceptScore W2588610658C154945302 @default.
- W2588610658 hasConceptScore W2588610658C158622935 @default.
- W2588610658 hasConceptScore W2588610658C17744445 @default.
- W2588610658 hasConceptScore W2588610658C192921069 @default.
- W2588610658 hasConceptScore W2588610658C199539241 @default.
- W2588610658 hasConceptScore W2588610658C2775924081 @default.
- W2588610658 hasConceptScore W2588610658C2776359362 @default.
- W2588610658 hasConceptScore W2588610658C29829512 @default.
- W2588610658 hasConceptScore W2588610658C33923547 @default.
- W2588610658 hasConceptScore W2588610658C41008148 @default.
- W2588610658 hasConceptScore W2588610658C47446073 @default.
- W2588610658 hasConceptScore W2588610658C48103436 @default.
- W2588610658 hasConceptScore W2588610658C50644808 @default.
- W2588610658 hasConceptScore W2588610658C62520636 @default.
- W2588610658 hasConceptScore W2588610658C91575142 @default.
- W2588610658 hasConceptScore W2588610658C94625758 @default.
- W2588610658 hasLocation W25886106581 @default.
- W2588610658 hasOpenAccess W2588610658 @default.
- W2588610658 hasPrimaryLocation W25886106581 @default.
- W2588610658 hasRelatedWork W1526749865 @default.
- W2588610658 hasRelatedWork W1573267871 @default.
- W2588610658 hasRelatedWork W2088253028 @default.
- W2588610658 hasRelatedWork W2104679583 @default.
- W2588610658 hasRelatedWork W2550491676 @default.
- W2588610658 hasRelatedWork W2904902274 @default.
- W2588610658 hasRelatedWork W2985170256 @default.
- W2588610658 hasRelatedWork W3142409280 @default.
- W2588610658 hasRelatedWork W3196329154 @default.
- W2588610658 hasRelatedWork W4210544627 @default.
- W2588610658 isParatext "false" @default.
- W2588610658 isRetracted "false" @default.
- W2588610658 magId "2588610658" @default.
- W2588610658 workType "article" @default.