Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221056186> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4221056186 endingPage "18793" @default.
- W4221056186 startingPage "18785" @default.
- W4221056186 abstract "For safe and efficient navigation in driving environment, autonomous vehicles are supposed to predict future trajectories of surrounding vehicles dynamically and tackle the uncertainty of environment. Early works view uncertainty as distributions in different modals, and perform this task by enumerating a mass of trajectories, but can hardly cover all the possible modal distributions. Recently, generative model has risen to hold promise for modelling such distributions, something that we will build upon here. Target at predefined modals of vehicle agents, this paper proposes Spatial-Temporal Generative Model (STGM), a new learning algorithm that leverages a stochastic generative model to mitigate modal distributions problem. To be more specific, a Conditional Variational Auto-Encoder (CVAE) is leveraged to construct the framework of STGM, in which the input is augmented into modal distributions to gain modality-wise trajectories. Besides, for the stability of prediction, we also come up with a new modal-wise sampling trick as an alternative of traditional random sampling in CVAE. Considering that multiple layer perception (MLP) based CVAE is incapable of extracting spatial and temporal features effectively, we use two respective encoders before CVAE: Spatial Encoder and Temporal Encoder, and align them with a closed modal set. Additionally, inspired by the Total Probability Formula, we adopt a Modal Prediction Model to refine the confidences of modal-wise trajectories. After empirical evaluation on two public datasets, we find that STGM almost outperforms the baselines, such as Covernet, MTP, and so on." @default.
- W4221056186 created "2022-04-03" @default.
- W4221056186 creator A5018698878 @default.
- W4221056186 creator A5025846026 @default.
- W4221056186 creator A5027058691 @default.
- W4221056186 date "2022-10-01" @default.
- W4221056186 modified "2023-10-14" @default.
- W4221056186 title "STGM: Vehicle Trajectory Prediction Based on Generative Model for Spatial-Temporal Features" @default.
- W4221056186 cites W2099340661 @default.
- W4221056186 cites W2101105382 @default.
- W4221056186 cites W2105934661 @default.
- W4221056186 cites W2212870984 @default.
- W4221056186 cites W2519503047 @default.
- W4221056186 cites W2623391680 @default.
- W4221056186 cites W2782474430 @default.
- W4221056186 cites W2791814097 @default.
- W4221056186 cites W2792239816 @default.
- W4221056186 cites W2883602772 @default.
- W4221056186 cites W2919115771 @default.
- W4221056186 cites W2932960505 @default.
- W4221056186 cites W2963001155 @default.
- W4221056186 cites W2963309363 @default.
- W4221056186 cites W2963353290 @default.
- W4221056186 cites W2963906196 @default.
- W4221056186 cites W2963914175 @default.
- W4221056186 cites W2963945905 @default.
- W4221056186 cites W2967177252 @default.
- W4221056186 cites W2969040309 @default.
- W4221056186 cites W2980695382 @default.
- W4221056186 cites W2989851631 @default.
- W4221056186 cites W2997958396 @default.
- W4221056186 cites W3002813111 @default.
- W4221056186 cites W3035671534 @default.
- W4221056186 cites W3035692480 @default.
- W4221056186 cites W3105115779 @default.
- W4221056186 cites W3114753236 @default.
- W4221056186 cites W3129684859 @default.
- W4221056186 doi "https://doi.org/10.1109/tits.2022.3160648" @default.
- W4221056186 hasPublicationYear "2022" @default.
- W4221056186 type Work @default.
- W4221056186 citedByCount "5" @default.
- W4221056186 countsByYear W42210561862023 @default.
- W4221056186 crossrefType "journal-article" @default.
- W4221056186 hasAuthorship W4221056186A5018698878 @default.
- W4221056186 hasAuthorship W4221056186A5025846026 @default.
- W4221056186 hasAuthorship W4221056186A5027058691 @default.
- W4221056186 hasConcept C105795698 @default.
- W4221056186 hasConcept C112972136 @default.
- W4221056186 hasConcept C119857082 @default.
- W4221056186 hasConcept C121332964 @default.
- W4221056186 hasConcept C1276947 @default.
- W4221056186 hasConcept C13662910 @default.
- W4221056186 hasConcept C149441793 @default.
- W4221056186 hasConcept C153180895 @default.
- W4221056186 hasConcept C154945302 @default.
- W4221056186 hasConcept C167966045 @default.
- W4221056186 hasConcept C185592680 @default.
- W4221056186 hasConcept C188027245 @default.
- W4221056186 hasConcept C33923547 @default.
- W4221056186 hasConcept C39890363 @default.
- W4221056186 hasConcept C41008148 @default.
- W4221056186 hasConcept C71139939 @default.
- W4221056186 hasConceptScore W4221056186C105795698 @default.
- W4221056186 hasConceptScore W4221056186C112972136 @default.
- W4221056186 hasConceptScore W4221056186C119857082 @default.
- W4221056186 hasConceptScore W4221056186C121332964 @default.
- W4221056186 hasConceptScore W4221056186C1276947 @default.
- W4221056186 hasConceptScore W4221056186C13662910 @default.
- W4221056186 hasConceptScore W4221056186C149441793 @default.
- W4221056186 hasConceptScore W4221056186C153180895 @default.
- W4221056186 hasConceptScore W4221056186C154945302 @default.
- W4221056186 hasConceptScore W4221056186C167966045 @default.
- W4221056186 hasConceptScore W4221056186C185592680 @default.
- W4221056186 hasConceptScore W4221056186C188027245 @default.
- W4221056186 hasConceptScore W4221056186C33923547 @default.
- W4221056186 hasConceptScore W4221056186C39890363 @default.
- W4221056186 hasConceptScore W4221056186C41008148 @default.
- W4221056186 hasConceptScore W4221056186C71139939 @default.
- W4221056186 hasIssue "10" @default.
- W4221056186 hasLocation W42210561861 @default.
- W4221056186 hasOpenAccess W4221056186 @default.
- W4221056186 hasPrimaryLocation W42210561861 @default.
- W4221056186 hasRelatedWork W1534961803 @default.
- W4221056186 hasRelatedWork W2108501770 @default.
- W4221056186 hasRelatedWork W2949416428 @default.
- W4221056186 hasRelatedWork W3017062960 @default.
- W4221056186 hasRelatedWork W3215252950 @default.
- W4221056186 hasRelatedWork W4241824423 @default.
- W4221056186 hasRelatedWork W4253371817 @default.
- W4221056186 hasRelatedWork W4293428270 @default.
- W4221056186 hasRelatedWork W4310743516 @default.
- W4221056186 hasRelatedWork W2310403681 @default.
- W4221056186 hasVolume "23" @default.
- W4221056186 isParatext "false" @default.
- W4221056186 isRetracted "false" @default.
- W4221056186 workType "article" @default.