Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098074920> ?p ?o ?g. }
- W3098074920 abstract "Differentiable simulators provide an avenue for closing the sim-to-real gap by enabling the use of efficient, gradient-based optimization algorithms to find the simulation parameters that best fit the observed sensor readings. Nonetheless, these analytical models can only predict the dynamical behavior of systems for which they have been designed. In this work, we study the augmentation of a novel differentiable rigid-body physics engine via neural networks that is able to learn nonlinear relationships between dynamic quantities and can thus learn effects not accounted for in traditional simulators.Such augmentations require less data to train and generalize better compared to entirely data-driven models. Through extensive experiments, we demonstrate the ability of our hybrid simulator to learn complex dynamics involving frictional contacts from real data, as well as match known models of viscous friction, and present an approach for automatically discovering useful augmentations. We show that, besides benefiting dynamics modeling, inserting neural networks can accelerate model-based control architectures. We observe a ten-fold speed-up when replacing the QP solver inside a model-predictive gait controller for quadruped robots with a neural network, allowing us to significantly improve control delays as we demonstrate in real-hardware experiments. We publish code, additional results and videos from our experiments on our project webpage at this https URL." @default.
- W3098074920 created "2020-11-23" @default.
- W3098074920 creator A5044231418 @default.
- W3098074920 creator A5058208745 @default.
- W3098074920 creator A5073253090 @default.
- W3098074920 creator A5077367921 @default.
- W3098074920 creator A5083125607 @default.
- W3098074920 date "2020-11-09" @default.
- W3098074920 modified "2023-09-27" @default.
- W3098074920 title "NeuralSim: Augmenting Differentiable Simulators with Neural Networks" @default.
- W3098074920 cites W1975537977 @default.
- W3098074920 cites W1987371344 @default.
- W3098074920 cites W2084399420 @default.
- W3098074920 cites W2113115376 @default.
- W3098074920 cites W2119659301 @default.
- W3098074920 cites W2157720571 @default.
- W3098074920 cites W2158782408 @default.
- W3098074920 cites W2195098255 @default.
- W3098074920 cites W2552391307 @default.
- W3098074920 cites W2754732998 @default.
- W3098074920 cites W2772160107 @default.
- W3098074920 cites W2782118025 @default.
- W3098074920 cites W2791763507 @default.
- W3098074920 cites W2793955514 @default.
- W3098074920 cites W2804623852 @default.
- W3098074920 cites W2885596080 @default.
- W3098074920 cites W2891122218 @default.
- W3098074920 cites W2899283552 @default.
- W3098074920 cites W2899460553 @default.
- W3098074920 cites W2900466252 @default.
- W3098074920 cites W2901694158 @default.
- W3098074920 cites W2909962969 @default.
- W3098074920 cites W2910744956 @default.
- W3098074920 cites W2911087563 @default.
- W3098074920 cites W2925173345 @default.
- W3098074920 cites W2946544065 @default.
- W3098074920 cites W2962867885 @default.
- W3098074920 cites W2963021886 @default.
- W3098074920 cites W2963030226 @default.
- W3098074920 cites W2963285578 @default.
- W3098074920 cites W2963294969 @default.
- W3098074920 cites W2963504959 @default.
- W3098074920 cites W2963755523 @default.
- W3098074920 cites W2963906246 @default.
- W3098074920 cites W2967571189 @default.
- W3098074920 cites W2968042644 @default.
- W3098074920 cites W2970529185 @default.
- W3098074920 cites W2971162686 @default.
- W3098074920 cites W2972810470 @default.
- W3098074920 cites W2981067082 @default.
- W3098074920 cites W2986023562 @default.
- W3098074920 cites W2995253198 @default.
- W3098074920 cites W3005143466 @default.
- W3098074920 cites W3007913393 @default.
- W3098074920 cites W3035580435 @default.
- W3098074920 cites W3038186741 @default.
- W3098074920 cites W3038540964 @default.
- W3098074920 cites W3039737909 @default.
- W3098074920 cites W3086784814 @default.
- W3098074920 cites W3090381223 @default.
- W3098074920 cites W3095435181 @default.
- W3098074920 cites W3127216876 @default.
- W3098074920 cites W3135508935 @default.
- W3098074920 cites W618254468 @default.
- W3098074920 hasPublicationYear "2020" @default.
- W3098074920 type Work @default.
- W3098074920 sameAs 3098074920 @default.
- W3098074920 citedByCount "5" @default.
- W3098074920 countsByYear W30980749202021 @default.
- W3098074920 crossrefType "posted-content" @default.
- W3098074920 hasAuthorship W3098074920A5044231418 @default.
- W3098074920 hasAuthorship W3098074920A5058208745 @default.
- W3098074920 hasAuthorship W3098074920A5073253090 @default.
- W3098074920 hasAuthorship W3098074920A5077367921 @default.
- W3098074920 hasAuthorship W3098074920A5083125607 @default.
- W3098074920 hasConcept C121332964 @default.
- W3098074920 hasConcept C127413603 @default.
- W3098074920 hasConcept C133731056 @default.
- W3098074920 hasConcept C134306372 @default.
- W3098074920 hasConcept C154945302 @default.
- W3098074920 hasConcept C158622935 @default.
- W3098074920 hasConcept C177264268 @default.
- W3098074920 hasConcept C190390380 @default.
- W3098074920 hasConcept C199360897 @default.
- W3098074920 hasConcept C202615002 @default.
- W3098074920 hasConcept C203479927 @default.
- W3098074920 hasConcept C2775924081 @default.
- W3098074920 hasConcept C2776760102 @default.
- W3098074920 hasConcept C2778770139 @default.
- W3098074920 hasConcept C33923547 @default.
- W3098074920 hasConcept C41008148 @default.
- W3098074920 hasConcept C47446073 @default.
- W3098074920 hasConcept C50644808 @default.
- W3098074920 hasConcept C62520636 @default.
- W3098074920 hasConcept C6557445 @default.
- W3098074920 hasConcept C86803240 @default.
- W3098074920 hasConceptScore W3098074920C121332964 @default.
- W3098074920 hasConceptScore W3098074920C127413603 @default.
- W3098074920 hasConceptScore W3098074920C133731056 @default.
- W3098074920 hasConceptScore W3098074920C134306372 @default.