FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204169784> ?p ?o ?g. }

• W3204169784 endingPage "107" @default.
• W3204169784 startingPage "83" @default.
• W3204169784 abstract "Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations. Therefore, the learned approximations ignore the existing knowledge of physics or robotics. Especially for learning dynamics models, these black-box models are not desirable as the underlying principles are well understood and the standard deep networks can learn dynamics that violate these principles. To learn dynamics models with deep networks that guarantee physically plausible dynamics, we introduce physics-inspired deep networks that combine first principles from physics with deep learning. We incorporate Lagrangian mechanics within the model learning such that all approximated models adhere to the laws of physics and conserve energy. Deep Lagrangian Networks (DeLaN) parametrize the system energy using two networks. The parameters are obtained by minimizing the squared residual of the Euler–Lagrange differential equation. Therefore, the resulting model does not require specific knowledge of the individual system, is interpretable, and can be used as a forward, inverse, and energy model. Previously these properties were only obtained when using system identification techniques that require knowledge of the kinematic structure. We apply DeLaN to learning dynamics models and apply these models to control simulated and physical rigid body systems. The results show that the proposed approach obtains dynamics models that can be applied to physical systems for real-time control. Compared to standard deep networks, the physics-inspired models learn better models and capture the underlying structure of the dynamics." @default.
• W3204169784 created "2021-10-11" @default.
• W3204169784 creator A5042151011 @default.
• W3204169784 creator A5071367253 @default.
• W3204169784 date "2023-03-01" @default.
• W3204169784 modified "2023-10-02" @default.
• W3204169784 title "Combining physics and deep learning to learn continuous-time dynamics models" @default.
• W3204169784 cites W1569654252 @default.
• W3204169784 cites W1912570122 @default.
• W3204169784 cites W1960241449 @default.
• W3204169784 cites W1966948790 @default.
• W3204169784 cites W1970346034 @default.
• W3204169784 cites W1978075626 @default.
• W3204169784 cites W1988087578 @default.
• W3204169784 cites W1990277704 @default.
• W3204169784 cites W1993713840 @default.
• W3204169784 cites W1995090200 @default.
• W3204169784 cites W1998179438 @default.
• W3204169784 cites W2001524797 @default.
• W3204169784 cites W2007864935 @default.
• W3204169784 cites W2034825286 @default.
• W3204169784 cites W2064585749 @default.
• W3204169784 cites W2068793240 @default.
• W3204169784 cites W2080992175 @default.
• W3204169784 cites W2086756762 @default.
• W3204169784 cites W2097815751 @default.
• W3204169784 cites W2112651309 @default.
• W3204169784 cites W2129202194 @default.
• W3204169784 cites W2144556291 @default.
• W3204169784 cites W2148666448 @default.
• W3204169784 cites W2151569055 @default.
• W3204169784 cites W2154543878 @default.
• W3204169784 cites W2162977544 @default.
• W3204169784 cites W2527189750 @default.
• W3204169784 cites W2556096037 @default.
• W3204169784 cites W2607714105 @default.
• W3204169784 cites W2669655952 @default.
• W3204169784 cites W2783813470 @default.
• W3204169784 cites W2783840948 @default.
• W3204169784 cites W2911087563 @default.
• W3204169784 cites W2951386724 @default.
• W3204169784 cites W2953046228 @default.
• W3204169784 cites W2962944821 @default.
• W3204169784 cites W2963694596 @default.
• W3204169784 cites W2963983021 @default.
• W3204169784 cites W3004137006 @default.
• W3204169784 cites W3031634646 @default.
• W3204169784 cites W3080930191 @default.
• W3204169784 cites W3099878876 @default.
• W3204169784 cites W3101260193 @default.
• W3204169784 cites W3104709959 @default.
• W3204169784 cites W3104994358 @default.
• W3204169784 cites W3169805247 @default.
• W3204169784 cites W3173446233 @default.
• W3204169784 cites W3175955419 @default.
• W3204169784 cites W3185853995 @default.
• W3204169784 cites W3207175065 @default.
• W3204169784 cites W4243385754 @default.
• W3204169784 doi "https://doi.org/10.1177/02783649231169492" @default.
• W3204169784 hasPublicationYear "2023" @default.
• W3204169784 type Work @default.
• W3204169784 sameAs 3204169784 @default.
• W3204169784 citedByCount "0" @default.
• W3204169784 crossrefType "journal-article" @default.
• W3204169784 hasAuthorship W3204169784A5042151011 @default.
• W3204169784 hasAuthorship W3204169784A5071367253 @default.
• W3204169784 hasBestOaLocation W32041697842 @default.
• W3204169784 hasConcept C108583219 @default.
• W3204169784 hasConcept C119857082 @default.
• W3204169784 hasConcept C121332964 @default.
• W3204169784 hasConcept C154945302 @default.
• W3204169784 hasConcept C187523126 @default.
• W3204169784 hasConcept C34413123 @default.
• W3204169784 hasConcept C39920418 @default.
• W3204169784 hasConcept C41008148 @default.
• W3204169784 hasConcept C50644808 @default.
• W3204169784 hasConcept C74650414 @default.
• W3204169784 hasConcept C90509273 @default.
• W3204169784 hasConcept C94966114 @default.
• W3204169784 hasConceptScore W3204169784C108583219 @default.
• W3204169784 hasConceptScore W3204169784C119857082 @default.
• W3204169784 hasConceptScore W3204169784C121332964 @default.
• W3204169784 hasConceptScore W3204169784C154945302 @default.
• W3204169784 hasConceptScore W3204169784C187523126 @default.
• W3204169784 hasConceptScore W3204169784C34413123 @default.
• W3204169784 hasConceptScore W3204169784C39920418 @default.
• W3204169784 hasConceptScore W3204169784C41008148 @default.
• W3204169784 hasConceptScore W3204169784C50644808 @default.
• W3204169784 hasConceptScore W3204169784C74650414 @default.
• W3204169784 hasConceptScore W3204169784C90509273 @default.
• W3204169784 hasConceptScore W3204169784C94966114 @default.
• W3204169784 hasFunder F4320309480 @default.
• W3204169784 hasFunder F4320328192 @default.
• W3204169784 hasFunder F4320338335 @default.
• W3204169784 hasIssue "3" @default.
• W3204169784 hasLocation W32041697841 @default.
• W3204169784 hasLocation W32041697842 @default.
• W3204169784 hasOpenAccess W3204169784 @default.

• next