Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212357731> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3212357731 endingPage "151992" @default.
- W3212357731 startingPage "151983" @default.
- W3212357731 abstract "Decision-making is still a significant challenge to realize fully autonomous driving. Using deep reinforcement learning (DRL) to solve autonomous driving decision-making problems is a recent trend. A common method is to encode surrounding vehicles in a grid to describe the state space to help DRL network extract the scene features. However, in the process of human driving, surrounding vehicles at different positions have different contributions to decision-making. Meanwhile, the network is difficult to fully extract useful features in a sparse state, which can also lead to catastrophic actions. Therefore, this work proposes a spatial attention module to calculate different weights to represent different contributions to decision-making results. And a channel attention module is proposed to fully extract useful features in sparse state features. These two attention modules are integrated into dueling double deep Q network, named D3QN-DA, as a high-level decision-maker of a hierarchical hierarchical control structure based decision-making system. To improve agent performance, an emergency safe checker is introduced in this system. And the agent is trained and test with a designed reward function from safety and efficiency in simulation. The experimental results show that the proposed method increases the safety rate by 54%, and the average explore distance by 30%, which is safer and more intelligent for the decision-making process of automatic driving." @default.
- W3212357731 created "2021-11-22" @default.
- W3212357731 creator A5003914299 @default.
- W3212357731 creator A5058675689 @default.
- W3212357731 creator A5062676583 @default.
- W3212357731 creator A5072870907 @default.
- W3212357731 creator A5082792511 @default.
- W3212357731 date "2021-01-01" @default.
- W3212357731 modified "2023-10-14" @default.
- W3212357731 title "Tactical Decision-Making for Autonomous Driving Using Dueling Double Deep Q Network With Double Attention" @default.
- W3212357731 cites W1520048352 @default.
- W3212357731 cites W1965455100 @default.
- W3212357731 cites W1991665457 @default.
- W3212357731 cites W2011931151 @default.
- W3212357731 cites W2056877664 @default.
- W3212357731 cites W2145339207 @default.
- W3212357731 cites W2404189583 @default.
- W3212357731 cites W2406067508 @default.
- W3212357731 cites W2548395657 @default.
- W3212357731 cites W2752782242 @default.
- W3212357731 cites W2783963507 @default.
- W3212357731 cites W2904263972 @default.
- W3212357731 cites W2956161617 @default.
- W3212357731 cites W2957408986 @default.
- W3212357731 cites W2963794428 @default.
- W3212357731 cites W2977843878 @default.
- W3212357731 cites W2980781976 @default.
- W3212357731 cites W2989958156 @default.
- W3212357731 cites W3090027660 @default.
- W3212357731 cites W3100789280 @default.
- W3212357731 cites W3100944043 @default.
- W3212357731 cites W3102777717 @default.
- W3212357731 cites W3103889895 @default.
- W3212357731 cites W3123212791 @default.
- W3212357731 cites W32403112 @default.
- W3212357731 cites W4293682399 @default.
- W3212357731 doi "https://doi.org/10.1109/access.2021.3127105" @default.
- W3212357731 hasPublicationYear "2021" @default.
- W3212357731 type Work @default.
- W3212357731 sameAs 3212357731 @default.
- W3212357731 citedByCount "11" @default.
- W3212357731 countsByYear W32123577312022 @default.
- W3212357731 countsByYear W32123577312023 @default.
- W3212357731 crossrefType "journal-article" @default.
- W3212357731 hasAuthorship W3212357731A5003914299 @default.
- W3212357731 hasAuthorship W3212357731A5058675689 @default.
- W3212357731 hasAuthorship W3212357731A5062676583 @default.
- W3212357731 hasAuthorship W3212357731A5072870907 @default.
- W3212357731 hasAuthorship W3212357731A5082792511 @default.
- W3212357731 hasBestOaLocation W32123577311 @default.
- W3212357731 hasConcept C127413603 @default.
- W3212357731 hasConcept C154945302 @default.
- W3212357731 hasConcept C38652104 @default.
- W3212357731 hasConcept C41008148 @default.
- W3212357731 hasConcept C42475967 @default.
- W3212357731 hasConceptScore W3212357731C127413603 @default.
- W3212357731 hasConceptScore W3212357731C154945302 @default.
- W3212357731 hasConceptScore W3212357731C38652104 @default.
- W3212357731 hasConceptScore W3212357731C41008148 @default.
- W3212357731 hasConceptScore W3212357731C42475967 @default.
- W3212357731 hasLocation W32123577311 @default.
- W3212357731 hasOpenAccess W3212357731 @default.
- W3212357731 hasPrimaryLocation W32123577311 @default.
- W3212357731 hasRelatedWork W2030496847 @default.
- W3212357731 hasRelatedWork W2093578348 @default.
- W3212357731 hasRelatedWork W2358668433 @default.
- W3212357731 hasRelatedWork W2376932109 @default.
- W3212357731 hasRelatedWork W2390279801 @default.
- W3212357731 hasRelatedWork W2748952813 @default.
- W3212357731 hasRelatedWork W2899084033 @default.
- W3212357731 hasRelatedWork W3007967230 @default.
- W3212357731 hasRelatedWork W3107474891 @default.
- W3212357731 hasRelatedWork W4313313264 @default.
- W3212357731 hasVolume "9" @default.
- W3212357731 isParatext "false" @default.
- W3212357731 isRetracted "false" @default.
- W3212357731 magId "3212357731" @default.
- W3212357731 workType "article" @default.