Matches in SemOpenAlex for { <https://semopenalex.org/work/W3023885224> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3023885224 abstract "The contribution of this paper is a framework for training and evaluation of Model Predictive Control (MPC) implemented using constrained neural networks. Recent studies have proposed to use neural networks with differentiable convex optimization layers to implement model predictive controllers. The motivation is to replace real-time optimization in safety critical feedback control systems with learnt mappings in the form of neural networks with optimization layers. Such mappings take as the input the state vector and predict the control law as the output. The learning takes place using training data generated from off-line MPC simulations. However, a general framework for characterization of learning approaches in terms of both model validation and efficient training data generation is lacking in literature. In this paper, we take the first steps towards developing such a coherent framework. We discuss how the learning problem has similarities with system identification, in particular input design, model structure selection and model validation. We consider the study of neural network architectures in PyTorch with the explicit MPC constraints implemented as a differentiable optimization layer using CVXPY. We propose an efficient approach of generating MPC input samples subject to the MPC model constraints using a hit-and-run sampler. The corresponding true outputs are generated by solving the MPC offline using OSOP. We propose different metrics to validate the resulting approaches. Our study further aims to explore the advantages of incorporating domain knowledge into the network structure from a training and evaluation perspective. Different model structures are numerically tested using the proposed framework in order to obtain more insights in the properties of constrained neural networks based MPC." @default.
- W3023885224 created "2020-05-13" @default.
- W3023885224 creator A5009228952 @default.
- W3023885224 creator A5045354671 @default.
- W3023885224 creator A5073689885 @default.
- W3023885224 date "2020-05-08" @default.
- W3023885224 modified "2023-09-23" @default.
- W3023885224 title "On Training and Evaluation of Neural Network Approaches for Model Predictive Control" @default.
- W3023885224 cites W124292005 @default.
- W3023885224 cites W1506806321 @default.
- W3023885224 cites W1678380195 @default.
- W3023885224 cites W2008206038 @default.
- W3023885224 cites W2061757541 @default.
- W3023885224 cites W2087884651 @default.
- W3023885224 cites W2108473514 @default.
- W3023885224 cites W2116773335 @default.
- W3023885224 cites W2171505650 @default.
- W3023885224 cites W2192203593 @default.
- W3023885224 cites W2595118681 @default.
- W3023885224 cites W2749680651 @default.
- W3023885224 cites W2769646558 @default.
- W3023885224 cites W2887532679 @default.
- W3023885224 cites W2915011563 @default.
- W3023885224 cites W2919115771 @default.
- W3023885224 cites W2964121744 @default.
- W3023885224 cites W2970791107 @default.
- W3023885224 cites W2970971581 @default.
- W3023885224 cites W2981925314 @default.
- W3023885224 cites W2989836659 @default.
- W3023885224 cites W3012044484 @default.
- W3023885224 cites W65587653 @default.
- W3023885224 cites W2290452516 @default.
- W3023885224 doi "https://doi.org/10.48550/arxiv.2005.04112" @default.
- W3023885224 hasPublicationYear "2020" @default.
- W3023885224 type Work @default.
- W3023885224 sameAs 3023885224 @default.
- W3023885224 citedByCount "0" @default.
- W3023885224 crossrefType "posted-content" @default.
- W3023885224 hasAuthorship W3023885224A5009228952 @default.
- W3023885224 hasAuthorship W3023885224A5045354671 @default.
- W3023885224 hasAuthorship W3023885224A5073689885 @default.
- W3023885224 hasBestOaLocation W30238852241 @default.
- W3023885224 hasConcept C11413529 @default.
- W3023885224 hasConcept C116834253 @default.
- W3023885224 hasConcept C119857082 @default.
- W3023885224 hasConcept C134306372 @default.
- W3023885224 hasConcept C137836250 @default.
- W3023885224 hasConcept C154945302 @default.
- W3023885224 hasConcept C172205157 @default.
- W3023885224 hasConcept C202615002 @default.
- W3023885224 hasConcept C2775924081 @default.
- W3023885224 hasConcept C33923547 @default.
- W3023885224 hasConcept C36503486 @default.
- W3023885224 hasConcept C41008148 @default.
- W3023885224 hasConcept C50644808 @default.
- W3023885224 hasConcept C59822182 @default.
- W3023885224 hasConcept C86803240 @default.
- W3023885224 hasConceptScore W3023885224C11413529 @default.
- W3023885224 hasConceptScore W3023885224C116834253 @default.
- W3023885224 hasConceptScore W3023885224C119857082 @default.
- W3023885224 hasConceptScore W3023885224C134306372 @default.
- W3023885224 hasConceptScore W3023885224C137836250 @default.
- W3023885224 hasConceptScore W3023885224C154945302 @default.
- W3023885224 hasConceptScore W3023885224C172205157 @default.
- W3023885224 hasConceptScore W3023885224C202615002 @default.
- W3023885224 hasConceptScore W3023885224C2775924081 @default.
- W3023885224 hasConceptScore W3023885224C33923547 @default.
- W3023885224 hasConceptScore W3023885224C36503486 @default.
- W3023885224 hasConceptScore W3023885224C41008148 @default.
- W3023885224 hasConceptScore W3023885224C50644808 @default.
- W3023885224 hasConceptScore W3023885224C59822182 @default.
- W3023885224 hasConceptScore W3023885224C86803240 @default.
- W3023885224 hasLocation W30238852241 @default.
- W3023885224 hasOpenAccess W3023885224 @default.
- W3023885224 hasPrimaryLocation W30238852241 @default.
- W3023885224 hasRelatedWork W12170026 @default.
- W3023885224 hasRelatedWork W2181881614 @default.
- W3023885224 hasRelatedWork W2386387936 @default.
- W3023885224 hasRelatedWork W2961085424 @default.
- W3023885224 hasRelatedWork W3046775127 @default.
- W3023885224 hasRelatedWork W3107474891 @default.
- W3023885224 hasRelatedWork W4205958290 @default.
- W3023885224 hasRelatedWork W4286629047 @default.
- W3023885224 hasRelatedWork W1629725936 @default.
- W3023885224 hasRelatedWork W4224009465 @default.
- W3023885224 isParatext "false" @default.
- W3023885224 isRetracted "false" @default.
- W3023885224 magId "3023885224" @default.
- W3023885224 workType "article" @default.