Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386688703> ?p ?o ?g. }
- W4386688703 abstract "Abstract With the development of communication technology and mobile edge computing (MEC), self-driving has received more and more research interests. However, most object detection tasks for self-driving vehicles are still performed at vehicle terminals, which often requires a trade-off between detection accuracy and speed. To achieve efficient object detection without sacrificing accuracy, we propose an end–edge collaboration object detection approach based on Deep Reinforcement Learning (DRL) with a task prioritization mechanism. We use a time utility function to measure the efficiency of object detection task and aim to provide an online approach to maximize the average sum of the time utilities in all slots. Since this is an NP-hard mixed-integer nonlinear programming (MINLP) problem, we propose an online approach for task offloading and resource allocation based on Deep Reinforcement learning and Piecewise Linearization (DRPL). A deep neural network (DNN) is implemented as a flexible solution for learning offloading strategies based on road traffic conditions and wireless network environment, which can significantly reduce computational complexity. In addition, to accelerate DRPL network convergence, DNN outputs are grouped by in-vehicle cameras to form offloading strategies via permutation. Numerical results show that the DRPL scheme is at least 10% more effective and superior in terms of time utility compared to several representative offloading schemes for various vehicle local computing resource scenarios." @default.
- W4386688703 created "2023-09-13" @default.
- W4386688703 creator A5005722282 @default.
- W4386688703 creator A5038832558 @default.
- W4386688703 creator A5056970858 @default.
- W4386688703 creator A5077319251 @default.
- W4386688703 creator A5080125156 @default.
- W4386688703 creator A5081163184 @default.
- W4386688703 date "2023-09-12" @default.
- W4386688703 modified "2023-10-18" @default.
- W4386688703 title "A deep reinforcement learning assisted task offloading and resource allocation approach towards self-driving object detection" @default.
- W4386688703 cites W2007829711 @default.
- W4386688703 cites W2079135578 @default.
- W4386688703 cites W2145339207 @default.
- W4386688703 cites W2194775991 @default.
- W4386688703 cites W2502165879 @default.
- W4386688703 cites W2549139847 @default.
- W4386688703 cites W2604970008 @default.
- W4386688703 cites W2618530766 @default.
- W4386688703 cites W2751824500 @default.
- W4386688703 cites W2804825009 @default.
- W4386688703 cites W2899242765 @default.
- W4386688703 cites W2909706750 @default.
- W4386688703 cites W2918400102 @default.
- W4386688703 cites W2953901595 @default.
- W4386688703 cites W2963446712 @default.
- W4386688703 cites W2968424451 @default.
- W4386688703 cites W2982013914 @default.
- W4386688703 cites W2982379822 @default.
- W4386688703 cites W2996741864 @default.
- W4386688703 cites W3081211774 @default.
- W4386688703 cites W3094809434 @default.
- W4386688703 cites W3109463546 @default.
- W4386688703 cites W3124943657 @default.
- W4386688703 cites W3132987155 @default.
- W4386688703 cites W3161037238 @default.
- W4386688703 cites W3175796458 @default.
- W4386688703 cites W3194390908 @default.
- W4386688703 cites W4210964642 @default.
- W4386688703 cites W4213312819 @default.
- W4386688703 cites W4226027685 @default.
- W4386688703 cites W4292973831 @default.
- W4386688703 cites W4312318065 @default.
- W4386688703 cites W4312385552 @default.
- W4386688703 cites W4321194942 @default.
- W4386688703 cites W4323022502 @default.
- W4386688703 cites W4323897035 @default.
- W4386688703 cites W4324134937 @default.
- W4386688703 cites W64813323 @default.
- W4386688703 doi "https://doi.org/10.1186/s13677-023-00503-w" @default.
- W4386688703 hasPublicationYear "2023" @default.
- W4386688703 type Work @default.
- W4386688703 citedByCount "0" @default.
- W4386688703 crossrefType "journal-article" @default.
- W4386688703 hasAuthorship W4386688703A5005722282 @default.
- W4386688703 hasAuthorship W4386688703A5038832558 @default.
- W4386688703 hasAuthorship W4386688703A5056970858 @default.
- W4386688703 hasAuthorship W4386688703A5077319251 @default.
- W4386688703 hasAuthorship W4386688703A5080125156 @default.
- W4386688703 hasAuthorship W4386688703A5081163184 @default.
- W4386688703 hasBestOaLocation W43866887031 @default.
- W4386688703 hasConcept C108583219 @default.
- W4386688703 hasConcept C119857082 @default.
- W4386688703 hasConcept C120314980 @default.
- W4386688703 hasConcept C153180895 @default.
- W4386688703 hasConcept C154945302 @default.
- W4386688703 hasConcept C162307627 @default.
- W4386688703 hasConcept C162324750 @default.
- W4386688703 hasConcept C187736073 @default.
- W4386688703 hasConcept C2776061582 @default.
- W4386688703 hasConcept C2776151529 @default.
- W4386688703 hasConcept C2780451532 @default.
- W4386688703 hasConcept C29202148 @default.
- W4386688703 hasConcept C31258907 @default.
- W4386688703 hasConcept C41008148 @default.
- W4386688703 hasConcept C79403827 @default.
- W4386688703 hasConcept C97541855 @default.
- W4386688703 hasConceptScore W4386688703C108583219 @default.
- W4386688703 hasConceptScore W4386688703C119857082 @default.
- W4386688703 hasConceptScore W4386688703C120314980 @default.
- W4386688703 hasConceptScore W4386688703C153180895 @default.
- W4386688703 hasConceptScore W4386688703C154945302 @default.
- W4386688703 hasConceptScore W4386688703C162307627 @default.
- W4386688703 hasConceptScore W4386688703C162324750 @default.
- W4386688703 hasConceptScore W4386688703C187736073 @default.
- W4386688703 hasConceptScore W4386688703C2776061582 @default.
- W4386688703 hasConceptScore W4386688703C2776151529 @default.
- W4386688703 hasConceptScore W4386688703C2780451532 @default.
- W4386688703 hasConceptScore W4386688703C29202148 @default.
- W4386688703 hasConceptScore W4386688703C31258907 @default.
- W4386688703 hasConceptScore W4386688703C41008148 @default.
- W4386688703 hasConceptScore W4386688703C79403827 @default.
- W4386688703 hasConceptScore W4386688703C97541855 @default.
- W4386688703 hasFunder F4320321001 @default.
- W4386688703 hasIssue "1" @default.
- W4386688703 hasLocation W43866887031 @default.
- W4386688703 hasOpenAccess W4386688703 @default.
- W4386688703 hasPrimaryLocation W43866887031 @default.
- W4386688703 hasRelatedWork W2959276766 @default.
- W4386688703 hasRelatedWork W2970686063 @default.