FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385858105> ?p ?o ?g. }

• W4385858105 abstract "Robots are active agents that operate in dynamic scenarios with noisy sensors. Predictions based on these noisy sensor measurements often lead to errors and can be unreliable. To this end, roboticists have used fusion methods using multiple observations. Lately, neural networks have dominated the accuracy charts for perception-driven predictions for robotic decision-making and often lack uncertainty metrics associated with the predictions. Here, we present a mathematical formulation to obtain the heteroscedastic aleatoric uncertainty of any arbitrary distribution without prior knowledge about the data. The approach has no prior assumptions about the prediction labels and is agnostic to network architecture. Furthermore, our class of networks, Ajna, adds minimal computation and requires only a small change to the loss function while training neural networks to obtain uncertainty of predictions, enabling real-time operation even on resource-constrained robots. In addition, we study the informational cues present in the uncertainties of predicted values and their utility in the unification of common robotics problems. In particular, we present an approach to dodge dynamic obstacles, navigate through a cluttered scene, fly through unknown gaps, and segment an object pile, without computing depth but rather using the uncertainties of optical flow obtained from a monocular camera with onboard sensing and computation. We successfully evaluate and demonstrate the proposed Ajna network on four aforementioned common robotics and computer vision tasks and show comparable results to methods directly using depth. Our work demonstrates a generalized deep uncertainty method and demonstrates its utilization in robotics applications." @default.
• W4385858105 created "2023-08-17" @default.
• W4385858105 creator A5036912867 @default.
• W4385858105 creator A5055752014 @default.
• W4385858105 creator A5067776602 @default.
• W4385858105 creator A5083553427 @default.
• W4385858105 date "2023-08-16" @default.
• W4385858105 modified "2023-10-04" @default.
• W4385858105 title "Ajna: Generalized deep uncertainty for minimal perception on parsimonious robots" @default.
• W4385858105 cites W1986099000 @default.
• W4385858105 cites W2105934661 @default.
• W4385858105 cites W2111051539 @default.
• W4385858105 cites W2138835141 @default.
• W4385858105 cites W2299529128 @default.
• W4385858105 cites W2409009991 @default.
• W4385858105 cites W2548527721 @default.
• W4385858105 cites W2560474170 @default.
• W4385858105 cites W2609883120 @default.
• W4385858105 cites W2782339814 @default.
• W4385858105 cites W2786318586 @default.
• W4385858105 cites W2887479417 @default.
• W4385858105 cites W2887922452 @default.
• W4385858105 cites W2911107439 @default.
• W4385858105 cites W2963150697 @default.
• W4385858105 cites W2963169347 @default.
• W4385858105 cites W2963782415 @default.
• W4385858105 cites W2964339591 @default.
• W4385858105 cites W2970594690 @default.
• W4385858105 cites W2981353488 @default.
• W4385858105 cites W2981762858 @default.
• W4385858105 cites W2983371255 @default.
• W4385858105 cites W3003962966 @default.
• W4385858105 cites W3011524659 @default.
• W4385858105 cites W3034475171 @default.
• W4385858105 cites W3034726754 @default.
• W4385858105 cites W3035358681 @default.
• W4385858105 cites W3035655707 @default.
• W4385858105 cites W3038041713 @default.
• W4385858105 cites W3049165116 @default.
• W4385858105 cites W3081167590 @default.
• W4385858105 cites W3091146474 @default.
• W4385858105 cites W3100280854 @default.
• W4385858105 cites W3100388886 @default.
• W4385858105 cites W3101037136 @default.
• W4385858105 cites W3102100346 @default.
• W4385858105 cites W3102961490 @default.
• W4385858105 cites W3125925759 @default.
• W4385858105 cites W3157695134 @default.
• W4385858105 cites W3175647732 @default.
• W4385858105 cites W3177583232 @default.
• W4385858105 cites W3180341139 @default.
• W4385858105 cites W3185877016 @default.
• W4385858105 cites W3199238138 @default.
• W4385858105 cites W3202871755 @default.
• W4385858105 cites W3205543860 @default.
• W4385858105 cites W3207490987 @default.
• W4385858105 cites W4206184617 @default.
• W4385858105 cites W4214503168 @default.
• W4385858105 cites W4214520160 @default.
• W4385858105 cites W4229007520 @default.
• W4385858105 cites W4282919408 @default.
• W4385858105 cites W4313154783 @default.
• W4385858105 cites W764651262 @default.
• W4385858105 doi "https://doi.org/10.1126/scirobotics.add5139" @default.
• W4385858105 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37585545" @default.
• W4385858105 hasPublicationYear "2023" @default.
• W4385858105 type Work @default.
• W4385858105 citedByCount "0" @default.
• W4385858105 crossrefType "journal-article" @default.
• W4385858105 hasAuthorship W4385858105A5036912867 @default.
• W4385858105 hasAuthorship W4385858105A5055752014 @default.
• W4385858105 hasAuthorship W4385858105A5067776602 @default.
• W4385858105 hasAuthorship W4385858105A5083553427 @default.
• W4385858105 hasBestOaLocation W43858581051 @default.
• W4385858105 hasConcept C11413529 @default.
• W4385858105 hasConcept C119857082 @default.
• W4385858105 hasConcept C154945302 @default.
• W4385858105 hasConcept C34413123 @default.
• W4385858105 hasConcept C41008148 @default.
• W4385858105 hasConcept C45374587 @default.
• W4385858105 hasConcept C50644808 @default.
• W4385858105 hasConcept C65909025 @default.
• W4385858105 hasConcept C90509273 @default.
• W4385858105 hasConceptScore W4385858105C11413529 @default.
• W4385858105 hasConceptScore W4385858105C119857082 @default.
• W4385858105 hasConceptScore W4385858105C154945302 @default.
• W4385858105 hasConceptScore W4385858105C34413123 @default.
• W4385858105 hasConceptScore W4385858105C41008148 @default.
• W4385858105 hasConceptScore W4385858105C45374587 @default.
• W4385858105 hasConceptScore W4385858105C50644808 @default.
• W4385858105 hasConceptScore W4385858105C65909025 @default.
• W4385858105 hasConceptScore W4385858105C90509273 @default.
• W4385858105 hasIssue "81" @default.
• W4385858105 hasLocation W43858581051 @default.
• W4385858105 hasLocation W43858581052 @default.
• W4385858105 hasOpenAccess W4385858105 @default.
• W4385858105 hasPrimaryLocation W43858581051 @default.
• W4385858105 hasRelatedWork W1508899372 @default.
• W4385858105 hasRelatedWork W2045758229 @default.
• W4385858105 hasRelatedWork W2398963826 @default.

• next