Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311554643> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4311554643 abstract "Autonomous vehicle (AV) stacks are typically built in a modular fashion, with explicit components performing detection, tracking, prediction, planning, control, etc. While modularity improves reusability, interpretability, and generalizability, it also suffers from compounding errors, information bottlenecks, and integration challenges. To overcome these challenges, a prominent approach is to convert the AV stack into an end-to-end neural network and train it with data. While such approaches have achieved impressive results, they typically lack interpretability and reusability, and they eschew principled analytical components, such as planning and control, in favor of deep neural networks. To enable the joint optimization of AV stacks while retaining modularity, we present DiffStack, a differentiable and modular stack for prediction, planning, and control. Crucially, our model-based planning and control algorithms leverage recent advancements in differentiable optimization to produce gradients, enabling optimization of upstream components, such as prediction, via backpropagation through planning and control. Our results on the nuScenes dataset indicate that end-to-end training with DiffStack yields substantial improvements in open-loop and closed-loop planning metrics by, e.g., learning to make fewer prediction errors that would affect planning. Beyond these immediate benefits, DiffStack opens up new opportunities for fully data-driven yet modular and interpretable AV architectures. Project website: https://sites.google.com/view/diffstack" @default.
- W4311554643 created "2022-12-27" @default.
- W4311554643 creator A5036260775 @default.
- W4311554643 creator A5050003000 @default.
- W4311554643 creator A5069739104 @default.
- W4311554643 creator A5091869385 @default.
- W4311554643 date "2022-12-13" @default.
- W4311554643 modified "2023-09-26" @default.
- W4311554643 title "DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles" @default.
- W4311554643 doi "https://doi.org/10.48550/arxiv.2212.06437" @default.
- W4311554643 hasPublicationYear "2022" @default.
- W4311554643 type Work @default.
- W4311554643 citedByCount "0" @default.
- W4311554643 crossrefType "posted-content" @default.
- W4311554643 hasAuthorship W4311554643A5036260775 @default.
- W4311554643 hasAuthorship W4311554643A5050003000 @default.
- W4311554643 hasAuthorship W4311554643A5069739104 @default.
- W4311554643 hasAuthorship W4311554643A5091869385 @default.
- W4311554643 hasBestOaLocation W43115546431 @default.
- W4311554643 hasConcept C101468663 @default.
- W4311554643 hasConcept C111919701 @default.
- W4311554643 hasConcept C119857082 @default.
- W4311554643 hasConcept C134306372 @default.
- W4311554643 hasConcept C137981799 @default.
- W4311554643 hasConcept C153083717 @default.
- W4311554643 hasConcept C154945302 @default.
- W4311554643 hasConcept C175202392 @default.
- W4311554643 hasConcept C199360897 @default.
- W4311554643 hasConcept C202615002 @default.
- W4311554643 hasConcept C2777904410 @default.
- W4311554643 hasConcept C2779478453 @default.
- W4311554643 hasConcept C2781067378 @default.
- W4311554643 hasConcept C2781121602 @default.
- W4311554643 hasConcept C33923547 @default.
- W4311554643 hasConcept C41008148 @default.
- W4311554643 hasConcept C50644808 @default.
- W4311554643 hasConcept C54355233 @default.
- W4311554643 hasConcept C86803240 @default.
- W4311554643 hasConceptScore W4311554643C101468663 @default.
- W4311554643 hasConceptScore W4311554643C111919701 @default.
- W4311554643 hasConceptScore W4311554643C119857082 @default.
- W4311554643 hasConceptScore W4311554643C134306372 @default.
- W4311554643 hasConceptScore W4311554643C137981799 @default.
- W4311554643 hasConceptScore W4311554643C153083717 @default.
- W4311554643 hasConceptScore W4311554643C154945302 @default.
- W4311554643 hasConceptScore W4311554643C175202392 @default.
- W4311554643 hasConceptScore W4311554643C199360897 @default.
- W4311554643 hasConceptScore W4311554643C202615002 @default.
- W4311554643 hasConceptScore W4311554643C2777904410 @default.
- W4311554643 hasConceptScore W4311554643C2779478453 @default.
- W4311554643 hasConceptScore W4311554643C2781067378 @default.
- W4311554643 hasConceptScore W4311554643C2781121602 @default.
- W4311554643 hasConceptScore W4311554643C33923547 @default.
- W4311554643 hasConceptScore W4311554643C41008148 @default.
- W4311554643 hasConceptScore W4311554643C50644808 @default.
- W4311554643 hasConceptScore W4311554643C54355233 @default.
- W4311554643 hasConceptScore W4311554643C86803240 @default.
- W4311554643 hasLocation W43115546431 @default.
- W4311554643 hasOpenAccess W4311554643 @default.
- W4311554643 hasPrimaryLocation W43115546431 @default.
- W4311554643 hasRelatedWork W2001975253 @default.
- W4311554643 hasRelatedWork W2011563808 @default.
- W4311554643 hasRelatedWork W2888805005 @default.
- W4311554643 hasRelatedWork W3041008096 @default.
- W4311554643 hasRelatedWork W3091402349 @default.
- W4311554643 hasRelatedWork W3121191823 @default.
- W4311554643 hasRelatedWork W3203961807 @default.
- W4311554643 hasRelatedWork W4206534706 @default.
- W4311554643 hasRelatedWork W4229079080 @default.
- W4311554643 hasRelatedWork W4298392860 @default.
- W4311554643 isParatext "false" @default.
- W4311554643 isRetracted "false" @default.
- W4311554643 workType "article" @default.