Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209013105> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3209013105 abstract "Abstract We describe the design and implementation of an autonomous prototype vehicle which finds an empty parking slot in a parking area, and parks itself in the empty parking slot, using neural networks based on deep reinforcement learning (RL). To perform an autonomous parking procedure for our prototype vehicle, two different artificial neural networks (ANNs) are trained using a deep RL Algorithm in a simulation environment and embedded into the computing platform of the prototype car. One of the ANNs enables the vehicle to drive autonomously in the parking environment. At the same time, an image processing algorithm is used to determine whether a parking slot is empty. When the image processing algorithm finds a suitable parking slot, a different ANN is activated and performs a safe parking procedure. However, ANN‐based machine learning techniques require high processing power and impose a high computational burden on embedded CPU and GPU platforms. To alleviate the computational burden, one can achieve higher performance and less power consumption using an application‐specific hardware design, where logic resources are fully exploited according to the algorithm of interest, in an energy‐efficient manner. In this article, hardware accelerators for our ANN models are designed and generated via the Vivado high‐level synthesis (HLS) tool, targeting an ARM based programmable SoC platform, ZedBoard. Our ANN accelerators have achieved a speedup of 17x as compared to an ARM software implementation. For deeper fully‐connected layers used in deep RL‐based solutions, function‐level parallelism (Vivado's dataflow) is employed to improve the computational efficiency. Our proposed stage‐level description for fully connected layers outperforms recent studies in terms of computation time." @default.
- W3209013105 created "2021-11-08" @default.
- W3209013105 creator A5007841716 @default.
- W3209013105 creator A5069831788 @default.
- W3209013105 creator A5075461122 @default.
- W3209013105 date "2021-11-02" @default.
- W3209013105 modified "2023-10-01" @default.
- W3209013105 title "Deep reinforcement learning‐based autonomous parking design with neural network compute accelerators" @default.
- W3209013105 cites W1474440726 @default.
- W3209013105 cites W1568192366 @default.
- W3209013105 cites W2060881101 @default.
- W3209013105 cites W2071576608 @default.
- W3209013105 cites W2145339207 @default.
- W3209013105 cites W2147726041 @default.
- W3209013105 cites W2170510975 @default.
- W3209013105 cites W2344086698 @default.
- W3209013105 cites W2404540148 @default.
- W3209013105 cites W2538756378 @default.
- W3209013105 cites W2591922920 @default.
- W3209013105 cites W2611709845 @default.
- W3209013105 cites W2622302604 @default.
- W3209013105 cites W2765869897 @default.
- W3209013105 cites W2769693685 @default.
- W3209013105 cites W2783681199 @default.
- W3209013105 cites W2792690031 @default.
- W3209013105 cites W2888100907 @default.
- W3209013105 cites W2889665471 @default.
- W3209013105 cites W2897827648 @default.
- W3209013105 cites W2964021469 @default.
- W3209013105 cites W2965571038 @default.
- W3209013105 cites W2981207549 @default.
- W3209013105 cites W2997106510 @default.
- W3209013105 cites W2997442807 @default.
- W3209013105 cites W3004395734 @default.
- W3209013105 cites W3048436360 @default.
- W3209013105 cites W3107869225 @default.
- W3209013105 cites W3165574855 @default.
- W3209013105 doi "https://doi.org/10.1002/cpe.6670" @default.
- W3209013105 hasPublicationYear "2021" @default.
- W3209013105 type Work @default.
- W3209013105 sameAs 3209013105 @default.
- W3209013105 citedByCount "2" @default.
- W3209013105 countsByYear W32090131052022 @default.
- W3209013105 countsByYear W32090131052023 @default.
- W3209013105 crossrefType "journal-article" @default.
- W3209013105 hasAuthorship W3209013105A5007841716 @default.
- W3209013105 hasAuthorship W3209013105A5069831788 @default.
- W3209013105 hasAuthorship W3209013105A5075461122 @default.
- W3209013105 hasConcept C108583219 @default.
- W3209013105 hasConcept C149635348 @default.
- W3209013105 hasConcept C154945302 @default.
- W3209013105 hasConcept C173608175 @default.
- W3209013105 hasConcept C41008148 @default.
- W3209013105 hasConcept C50644808 @default.
- W3209013105 hasConcept C68339613 @default.
- W3209013105 hasConcept C96324660 @default.
- W3209013105 hasConcept C97541855 @default.
- W3209013105 hasConceptScore W3209013105C108583219 @default.
- W3209013105 hasConceptScore W3209013105C149635348 @default.
- W3209013105 hasConceptScore W3209013105C154945302 @default.
- W3209013105 hasConceptScore W3209013105C173608175 @default.
- W3209013105 hasConceptScore W3209013105C41008148 @default.
- W3209013105 hasConceptScore W3209013105C50644808 @default.
- W3209013105 hasConceptScore W3209013105C68339613 @default.
- W3209013105 hasConceptScore W3209013105C96324660 @default.
- W3209013105 hasConceptScore W3209013105C97541855 @default.
- W3209013105 hasIssue "9" @default.
- W3209013105 hasLocation W32090131051 @default.
- W3209013105 hasOpenAccess W3209013105 @default.
- W3209013105 hasPrimaryLocation W32090131051 @default.
- W3209013105 hasRelatedWork W1482977628 @default.
- W3209013105 hasRelatedWork W1587906417 @default.
- W3209013105 hasRelatedWork W1594844924 @default.
- W3209013105 hasRelatedWork W2027229894 @default.
- W3209013105 hasRelatedWork W2100229967 @default.
- W3209013105 hasRelatedWork W2187181201 @default.
- W3209013105 hasRelatedWork W2356029519 @default.
- W3209013105 hasRelatedWork W2368438474 @default.
- W3209013105 hasRelatedWork W2387826868 @default.
- W3209013105 hasRelatedWork W3205626426 @default.
- W3209013105 hasVolume "34" @default.
- W3209013105 isParatext "false" @default.
- W3209013105 isRetracted "false" @default.
- W3209013105 magId "3209013105" @default.
- W3209013105 workType "article" @default.