Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212210003> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3212210003 abstract "Cyber-Physical Systems (CPS) have been broadly deployed in safety-critical domains, such as automotive systems, avionics, medical devices, etc. In recent years, Artificial Intelligence (AI) has been increasingly adopted to control CPS. Despite the popularity of AI-enabled CPS, few benchmarks are publicly available. There is also a lack of deep understanding on the performance and reliability of AI-enabled CPS across different industrial domains. To bridge this gap, we present a public benchmark of industry-level CPS in seven domains and build AI controllers for them via state-of-the-art deep reinforcement learning (DRL) methods. Based on that, we further perform a systematic evaluation of these AI-enabled systems with their traditional counterparts to identify current challenges and future opportunities. Our key findings include (1) AI controllers do not always outperform traditional controllers, (2) existing CPS testing techniques (falsification, specifically) fall short of analyzing AI-enabled CPS, and (3) building a hybrid system that strategically combines and switches between AI controllers and traditional controllers can achieve better performance across different domains. Our results highlight the need for new testing techniques for AI-enabled CPS and the need for more investigations into hybrid CPS to achieve optimal performance and reliability. Our benchmark, code, detailed evaluation results, and experiment scripts are available on https://sites.google.com/view/ai-cps-benchmark." @default.
- W3212210003 created "2021-11-22" @default.
- W3212210003 creator A5010478725 @default.
- W3212210003 creator A5015461582 @default.
- W3212210003 creator A5041448256 @default.
- W3212210003 creator A5049897209 @default.
- W3212210003 creator A5063835503 @default.
- W3212210003 creator A5070683475 @default.
- W3212210003 date "2022-05-21" @default.
- W3212210003 modified "2023-09-26" @default.
- W3212210003 title "When cyber-physical systems meet AI" @default.
- W3212210003 cites W2151554678 @default.
- W3212210003 cites W2604347212 @default.
- W3212210003 cites W2962692913 @default.
- W3212210003 cites W2963231286 @default.
- W3212210003 cites W2967844381 @default.
- W3212210003 cites W2980176926 @default.
- W3212210003 cites W3004091789 @default.
- W3212210003 cites W3100789280 @default.
- W3212210003 cites W3185432324 @default.
- W3212210003 doi "https://doi.org/10.1145/3510457.3513049" @default.
- W3212210003 hasPublicationYear "2022" @default.
- W3212210003 type Work @default.
- W3212210003 sameAs 3212210003 @default.
- W3212210003 citedByCount "2" @default.
- W3212210003 countsByYear W32122100032023 @default.
- W3212210003 crossrefType "proceedings-article" @default.
- W3212210003 hasAuthorship W3212210003A5010478725 @default.
- W3212210003 hasAuthorship W3212210003A5015461582 @default.
- W3212210003 hasAuthorship W3212210003A5041448256 @default.
- W3212210003 hasAuthorship W3212210003A5049897209 @default.
- W3212210003 hasAuthorship W3212210003A5063835503 @default.
- W3212210003 hasAuthorship W3212210003A5070683475 @default.
- W3212210003 hasBestOaLocation W32122100031 @default.
- W3212210003 hasConcept C100776233 @default.
- W3212210003 hasConcept C108583219 @default.
- W3212210003 hasConcept C111919701 @default.
- W3212210003 hasConcept C119857082 @default.
- W3212210003 hasConcept C121332964 @default.
- W3212210003 hasConcept C126322002 @default.
- W3212210003 hasConcept C127413603 @default.
- W3212210003 hasConcept C13280743 @default.
- W3212210003 hasConcept C146978453 @default.
- W3212210003 hasConcept C154945302 @default.
- W3212210003 hasConcept C15792166 @default.
- W3212210003 hasConcept C163258240 @default.
- W3212210003 hasConcept C179768478 @default.
- W3212210003 hasConcept C185798385 @default.
- W3212210003 hasConcept C205649164 @default.
- W3212210003 hasConcept C26517878 @default.
- W3212210003 hasConcept C38652104 @default.
- W3212210003 hasConcept C41008148 @default.
- W3212210003 hasConcept C43214815 @default.
- W3212210003 hasConcept C526921623 @default.
- W3212210003 hasConcept C62520636 @default.
- W3212210003 hasConcept C71924100 @default.
- W3212210003 hasConcept C97541855 @default.
- W3212210003 hasConceptScore W3212210003C100776233 @default.
- W3212210003 hasConceptScore W3212210003C108583219 @default.
- W3212210003 hasConceptScore W3212210003C111919701 @default.
- W3212210003 hasConceptScore W3212210003C119857082 @default.
- W3212210003 hasConceptScore W3212210003C121332964 @default.
- W3212210003 hasConceptScore W3212210003C126322002 @default.
- W3212210003 hasConceptScore W3212210003C127413603 @default.
- W3212210003 hasConceptScore W3212210003C13280743 @default.
- W3212210003 hasConceptScore W3212210003C146978453 @default.
- W3212210003 hasConceptScore W3212210003C154945302 @default.
- W3212210003 hasConceptScore W3212210003C15792166 @default.
- W3212210003 hasConceptScore W3212210003C163258240 @default.
- W3212210003 hasConceptScore W3212210003C179768478 @default.
- W3212210003 hasConceptScore W3212210003C185798385 @default.
- W3212210003 hasConceptScore W3212210003C205649164 @default.
- W3212210003 hasConceptScore W3212210003C26517878 @default.
- W3212210003 hasConceptScore W3212210003C38652104 @default.
- W3212210003 hasConceptScore W3212210003C41008148 @default.
- W3212210003 hasConceptScore W3212210003C43214815 @default.
- W3212210003 hasConceptScore W3212210003C526921623 @default.
- W3212210003 hasConceptScore W3212210003C62520636 @default.
- W3212210003 hasConceptScore W3212210003C71924100 @default.
- W3212210003 hasConceptScore W3212210003C97541855 @default.
- W3212210003 hasLocation W32122100031 @default.
- W3212210003 hasLocation W32122100032 @default.
- W3212210003 hasOpenAccess W3212210003 @default.
- W3212210003 hasPrimaryLocation W32122100031 @default.
- W3212210003 hasRelatedWork W2922457425 @default.
- W3212210003 hasRelatedWork W3014300295 @default.
- W3212210003 hasRelatedWork W3164822677 @default.
- W3212210003 hasRelatedWork W4223943233 @default.
- W3212210003 hasRelatedWork W4225161397 @default.
- W3212210003 hasRelatedWork W4250304930 @default.
- W3212210003 hasRelatedWork W4309045103 @default.
- W3212210003 hasRelatedWork W4312200629 @default.
- W3212210003 hasRelatedWork W4360585206 @default.
- W3212210003 hasRelatedWork W4364306694 @default.
- W3212210003 isParatext "false" @default.
- W3212210003 isRetracted "false" @default.
- W3212210003 magId "3212210003" @default.
- W3212210003 workType "article" @default.