Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184179613> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3184179613 abstract "Validating the safety of autonomous systems generally requires the use of high-fidelity simulators that adequately capture the variability of real-world scenarios. However, it is generally not feasible to exhaustively search the space of simulation scenarios for failures. Adaptive stress testing (AST) is a method that uses reinforcement learning to find the most likely failure of a system. AST with a deep reinforcement learning solver has been shown to be effective in finding failures across a range of different systems. This approach generally involves running many simulations, which can be very expensive when using a high-fidelity simulator. To improve efficiency, we present a method that first finds failures in a low-fidelity simulator. It then uses the backward algorithm, which trains a deep neural network policy using a single expert demonstration, to adapt the low-fidelity failures to high-fidelity. We have created a series of autonomous vehicle validation case studies that represent some of the ways low-fidelity and high-fidelity simulators can differ, such as time discretization. We demonstrate in a variety of case studies that this new AST approach is able to find failures with significantly fewer high-fidelity simulation steps than are needed when just running AST directly in high-fidelity. As a proof of concept, we also demonstrate AST on NVIDIA’s DriveSim simulator, an industry state-of-the-art high-fidelity simulator for finding failures in autonomous vehicles." @default.
- W3184179613 created "2021-08-02" @default.
- W3184179613 creator A5021157455 @default.
- W3184179613 creator A5059386117 @default.
- W3184179613 creator A5068326377 @default.
- W3184179613 date "2021-09-27" @default.
- W3184179613 modified "2023-10-16" @default.
- W3184179613 title "Finding Failures in High-Fidelity Simulation using Adaptive Stress Testing and the Backward Algorithm" @default.
- W3184179613 cites W1965455100 @default.
- W3184179613 cites W2064675550 @default.
- W3184179613 cites W2525936901 @default.
- W3184179613 cites W2798302610 @default.
- W3184179613 cites W2897535010 @default.
- W3184179613 cites W2963003663 @default.
- W3184179613 cites W2963343478 @default.
- W3184179613 cites W2963440325 @default.
- W3184179613 cites W2989981704 @default.
- W3184179613 cites W2990956645 @default.
- W3184179613 cites W3112716182 @default.
- W3184179613 cites W3116276887 @default.
- W3184179613 cites W3148740559 @default.
- W3184179613 doi "https://doi.org/10.1109/iros51168.2021.9636072" @default.
- W3184179613 hasPublicationYear "2021" @default.
- W3184179613 type Work @default.
- W3184179613 sameAs 3184179613 @default.
- W3184179613 citedByCount "6" @default.
- W3184179613 countsByYear W31841796132022 @default.
- W3184179613 countsByYear W31841796132023 @default.
- W3184179613 crossrefType "proceedings-article" @default.
- W3184179613 hasAuthorship W3184179613A5021157455 @default.
- W3184179613 hasAuthorship W3184179613A5059386117 @default.
- W3184179613 hasAuthorship W3184179613A5068326377 @default.
- W3184179613 hasBestOaLocation W31841796132 @default.
- W3184179613 hasConcept C113364801 @default.
- W3184179613 hasConcept C113775141 @default.
- W3184179613 hasConcept C119599485 @default.
- W3184179613 hasConcept C127413603 @default.
- W3184179613 hasConcept C136197465 @default.
- W3184179613 hasConcept C154945302 @default.
- W3184179613 hasConcept C190839683 @default.
- W3184179613 hasConcept C199360897 @default.
- W3184179613 hasConcept C205649164 @default.
- W3184179613 hasConcept C2776459999 @default.
- W3184179613 hasConcept C2778770139 @default.
- W3184179613 hasConcept C41008148 @default.
- W3184179613 hasConcept C44154836 @default.
- W3184179613 hasConcept C50644808 @default.
- W3184179613 hasConcept C58640448 @default.
- W3184179613 hasConcept C76155785 @default.
- W3184179613 hasConcept C79403827 @default.
- W3184179613 hasConcept C97541855 @default.
- W3184179613 hasConceptScore W3184179613C113364801 @default.
- W3184179613 hasConceptScore W3184179613C113775141 @default.
- W3184179613 hasConceptScore W3184179613C119599485 @default.
- W3184179613 hasConceptScore W3184179613C127413603 @default.
- W3184179613 hasConceptScore W3184179613C136197465 @default.
- W3184179613 hasConceptScore W3184179613C154945302 @default.
- W3184179613 hasConceptScore W3184179613C190839683 @default.
- W3184179613 hasConceptScore W3184179613C199360897 @default.
- W3184179613 hasConceptScore W3184179613C205649164 @default.
- W3184179613 hasConceptScore W3184179613C2776459999 @default.
- W3184179613 hasConceptScore W3184179613C2778770139 @default.
- W3184179613 hasConceptScore W3184179613C41008148 @default.
- W3184179613 hasConceptScore W3184179613C44154836 @default.
- W3184179613 hasConceptScore W3184179613C50644808 @default.
- W3184179613 hasConceptScore W3184179613C58640448 @default.
- W3184179613 hasConceptScore W3184179613C76155785 @default.
- W3184179613 hasConceptScore W3184179613C79403827 @default.
- W3184179613 hasConceptScore W3184179613C97541855 @default.
- W3184179613 hasLocation W31841796131 @default.
- W3184179613 hasLocation W31841796132 @default.
- W3184179613 hasOpenAccess W3184179613 @default.
- W3184179613 hasPrimaryLocation W31841796131 @default.
- W3184179613 hasRelatedWork W1693617288 @default.
- W3184179613 hasRelatedWork W1994984379 @default.
- W3184179613 hasRelatedWork W2080814342 @default.
- W3184179613 hasRelatedWork W2891713159 @default.
- W3184179613 hasRelatedWork W3166669706 @default.
- W3184179613 hasRelatedWork W4282813506 @default.
- W3184179613 hasRelatedWork W4288727373 @default.
- W3184179613 hasRelatedWork W4306765721 @default.
- W3184179613 hasRelatedWork W4322759750 @default.
- W3184179613 hasRelatedWork W575009904 @default.
- W3184179613 isParatext "false" @default.
- W3184179613 isRetracted "false" @default.
- W3184179613 magId "3184179613" @default.
- W3184179613 workType "article" @default.