Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209810522> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3209810522 endingPage "1470" @default.
- W3209810522 startingPage "1456" @default.
- W3209810522 abstract "In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which often are the kinematic and dynamic constraints of the system, are then only restored when synthesizing the motion, which introduces possibly heavy distortions. In this work, we propose to use those approximate trajectory distributions as close-to-optimal discriminators in the popular generative adversarial framework to stabilize and accelerate the learning procedure. The two problems of adaptability and robustness are addressed with our method. In order to adapt the motions to varying contexts, we propose to use a product of Gaussian policies defined in several parametrized task spaces. Robustness to perturbations and varying dynamics is ensured with the use of stochastic gradient descent and ensemble methods to learn the stochastic dynamics. Two experiments are performed on a 7-DoF manipulator to validate the approach." @default.
- W3209810522 created "2021-11-08" @default.
- W3209810522 creator A5048780399 @default.
- W3209810522 creator A5050199260 @default.
- W3209810522 creator A5080609835 @default.
- W3209810522 date "2020-01-01" @default.
- W3209810522 modified "2023-09-26" @default.
- W3209810522 title "Generative adversarial training of product of policies for robust and adaptive movement primitives" @default.
- W3209810522 hasPublicationYear "2020" @default.
- W3209810522 type Work @default.
- W3209810522 sameAs 3209810522 @default.
- W3209810522 citedByCount "2" @default.
- W3209810522 countsByYear W32098105222020 @default.
- W3209810522 countsByYear W32098105222021 @default.
- W3209810522 crossrefType "journal-article" @default.
- W3209810522 hasAuthorship W3209810522A5048780399 @default.
- W3209810522 hasAuthorship W3209810522A5050199260 @default.
- W3209810522 hasAuthorship W3209810522A5080609835 @default.
- W3209810522 hasConcept C104317684 @default.
- W3209810522 hasConcept C11413529 @default.
- W3209810522 hasConcept C119857082 @default.
- W3209810522 hasConcept C121332964 @default.
- W3209810522 hasConcept C154945302 @default.
- W3209810522 hasConcept C177606310 @default.
- W3209810522 hasConcept C185592680 @default.
- W3209810522 hasConcept C18903297 @default.
- W3209810522 hasConcept C37736160 @default.
- W3209810522 hasConcept C39890363 @default.
- W3209810522 hasConcept C39920418 @default.
- W3209810522 hasConcept C41008148 @default.
- W3209810522 hasConcept C55439883 @default.
- W3209810522 hasConcept C55493867 @default.
- W3209810522 hasConcept C63479239 @default.
- W3209810522 hasConcept C74650414 @default.
- W3209810522 hasConcept C86803240 @default.
- W3209810522 hasConceptScore W3209810522C104317684 @default.
- W3209810522 hasConceptScore W3209810522C11413529 @default.
- W3209810522 hasConceptScore W3209810522C119857082 @default.
- W3209810522 hasConceptScore W3209810522C121332964 @default.
- W3209810522 hasConceptScore W3209810522C154945302 @default.
- W3209810522 hasConceptScore W3209810522C177606310 @default.
- W3209810522 hasConceptScore W3209810522C185592680 @default.
- W3209810522 hasConceptScore W3209810522C18903297 @default.
- W3209810522 hasConceptScore W3209810522C37736160 @default.
- W3209810522 hasConceptScore W3209810522C39890363 @default.
- W3209810522 hasConceptScore W3209810522C39920418 @default.
- W3209810522 hasConceptScore W3209810522C41008148 @default.
- W3209810522 hasConceptScore W3209810522C55439883 @default.
- W3209810522 hasConceptScore W3209810522C55493867 @default.
- W3209810522 hasConceptScore W3209810522C63479239 @default.
- W3209810522 hasConceptScore W3209810522C74650414 @default.
- W3209810522 hasConceptScore W3209810522C86803240 @default.
- W3209810522 hasLocation W32098105221 @default.
- W3209810522 hasOpenAccess W3209810522 @default.
- W3209810522 hasPrimaryLocation W32098105221 @default.
- W3209810522 hasRelatedWork W2001095967 @default.
- W3209810522 hasRelatedWork W2162206751 @default.
- W3209810522 hasRelatedWork W2260246986 @default.
- W3209810522 hasRelatedWork W2509546504 @default.
- W3209810522 hasRelatedWork W2751302235 @default.
- W3209810522 hasRelatedWork W2942009982 @default.
- W3209810522 hasRelatedWork W2964224524 @default.
- W3209810522 hasRelatedWork W3003906095 @default.
- W3209810522 hasRelatedWork W3004517342 @default.
- W3209810522 hasRelatedWork W3008006006 @default.
- W3209810522 hasRelatedWork W3013324456 @default.
- W3209810522 hasRelatedWork W3015304327 @default.
- W3209810522 hasRelatedWork W3155778979 @default.
- W3209810522 hasRelatedWork W3170198852 @default.
- W3209810522 hasRelatedWork W3180968645 @default.
- W3209810522 hasRelatedWork W3181705464 @default.
- W3209810522 hasRelatedWork W3182698822 @default.
- W3209810522 hasRelatedWork W3199537478 @default.
- W3209810522 hasRelatedWork W3204858865 @default.
- W3209810522 hasRelatedWork W2159984758 @default.
- W3209810522 isParatext "false" @default.
- W3209810522 isRetracted "false" @default.
- W3209810522 magId "3209810522" @default.
- W3209810522 workType "article" @default.