FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898045695> ?p ?o ?g. }

• W2898045695 abstract "Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly intractable to compute. This paper uses MC-Dropout and Bootstrapping to give computationally tractable and parallelizable uncertainty estimates. The methods are embedded in a Safe Reinforcement Learning framework to form uncertainty-aware navigation around pedestrians. The result is a collision avoidance policy that knows what it does not know and cautiously avoids pedestrians that exhibit unseen behavior. The policy is demonstrated in simulation to be more robust to novel observations and take safer actions than an uncertainty-unaware baseline." @default.
• W2898045695 created "2018-10-26" @default.
• W2898045695 creator A5011665886 @default.
• W2898045695 creator A5017253556 @default.
• W2898045695 creator A5064513857 @default.
• W2898045695 date "2018-10-19" @default.
• W2898045695 modified "2023-09-27" @default.
• W2898045695 title "Safe Reinforcement Learning with Model Uncertainty Estimates" @default.
• W2898045695 cites W1567512734 @default.
• W2898045695 cites W1585575029 @default.
• W2898045695 cites W1590642498 @default.
• W2898045695 cites W1845972764 @default.
• W2898045695 cites W192919555 @default.
• W2898045695 cites W1995945562 @default.
• W2898045695 cites W2039522160 @default.
• W2898045695 cites W2056257343 @default.
• W2898045695 cites W2062561016 @default.
• W2898045695 cites W2064675550 @default.
• W2898045695 cites W2095705004 @default.
• W2898045695 cites W2108677974 @default.
• W2898045695 cites W2164411961 @default.
• W2898045695 cites W2164479831 @default.
• W2898045695 cites W2165489953 @default.
• W2898045695 cites W2167052694 @default.
• W2898045695 cites W2233908551 @default.
• W2898045695 cites W2294678926 @default.
• W2898045695 cites W2302053044 @default.
• W2898045695 cites W2424778531 @default.
• W2898045695 cites W2462906003 @default.
• W2898045695 cites W2531327146 @default.
• W2898045695 cites W2556372419 @default.
• W2898045695 cites W2600383743 @default.
• W2898045695 cites W2604216058 @default.
• W2898045695 cites W2606757878 @default.
• W2898045695 cites W2615735215 @default.
• W2898045695 cites W2767449908 @default.
• W2898045695 cites W2799977193 @default.
• W2898045695 cites W2800978878 @default.
• W2898045695 cites W2807662017 @default.
• W2898045695 cites W2887927966 @default.
• W2898045695 cites W2950751653 @default.
• W2898045695 cites W2951266961 @default.
• W2898045695 cites W2963238274 @default.
• W2898045695 cites W2963472564 @default.
• W2898045695 cites W2963590277 @default.
• W2898045695 cites W2963938771 @default.
• W2898045695 cites W2964010366 @default.
• W2898045695 cites W2964016190 @default.
• W2898045695 cites W2964059111 @default.
• W2898045695 hasPublicationYear "2018" @default.
• W2898045695 type Work @default.
• W2898045695 sameAs 2898045695 @default.
• W2898045695 citedByCount "7" @default.
• W2898045695 countsByYear W28980456952019 @default.
• W2898045695 countsByYear W28980456952020 @default.
• W2898045695 countsByYear W28980456952021 @default.
• W2898045695 crossrefType "posted-content" @default.
• W2898045695 hasAuthorship W2898045695A5011665886 @default.
• W2898045695 hasAuthorship W2898045695A5017253556 @default.
• W2898045695 hasAuthorship W2898045695A5064513857 @default.
• W2898045695 hasConcept C107673813 @default.
• W2898045695 hasConcept C111368507 @default.
• W2898045695 hasConcept C119857082 @default.
• W2898045695 hasConcept C121704057 @default.
• W2898045695 hasConcept C12725497 @default.
• W2898045695 hasConcept C127313418 @default.
• W2898045695 hasConcept C149782125 @default.
• W2898045695 hasConcept C154945302 @default.
• W2898045695 hasConcept C207609745 @default.
• W2898045695 hasConcept C2776145597 @default.
• W2898045695 hasConcept C2776654903 @default.
• W2898045695 hasConcept C2780864053 @default.
• W2898045695 hasConcept C33923547 @default.
• W2898045695 hasConcept C38652104 @default.
• W2898045695 hasConcept C41008148 @default.
• W2898045695 hasConcept C50644808 @default.
• W2898045695 hasConcept C97541855 @default.
• W2898045695 hasConceptScore W2898045695C107673813 @default.
• W2898045695 hasConceptScore W2898045695C111368507 @default.
• W2898045695 hasConceptScore W2898045695C119857082 @default.
• W2898045695 hasConceptScore W2898045695C121704057 @default.
• W2898045695 hasConceptScore W2898045695C12725497 @default.
• W2898045695 hasConceptScore W2898045695C127313418 @default.
• W2898045695 hasConceptScore W2898045695C149782125 @default.
• W2898045695 hasConceptScore W2898045695C154945302 @default.
• W2898045695 hasConceptScore W2898045695C207609745 @default.
• W2898045695 hasConceptScore W2898045695C2776145597 @default.
• W2898045695 hasConceptScore W2898045695C2776654903 @default.
• W2898045695 hasConceptScore W2898045695C2780864053 @default.
• W2898045695 hasConceptScore W2898045695C33923547 @default.
• W2898045695 hasConceptScore W2898045695C38652104 @default.
• W2898045695 hasConceptScore W2898045695C41008148 @default.
• W2898045695 hasConceptScore W2898045695C50644808 @default.
• W2898045695 hasConceptScore W2898045695C97541855 @default.
• W2898045695 hasLocation W28980456951 @default.
• W2898045695 hasOpenAccess W2898045695 @default.
• W2898045695 hasPrimaryLocation W28980456951 @default.
• W2898045695 hasRelatedWork W2145339207 @default.
• W2898045695 hasRelatedWork W2884412095 @default.
• W2898045695 hasRelatedWork W2893463703 @default.

• next