Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296413562> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4296413562 abstract "Trajectory prediction has been a long-standing problem in intelligent systems like autonomous driving and robot navigation. Models trained on large-scale benchmarks have made significant progress in improving prediction accuracy. However, the importance on efficiency for real-time applications has been less emphasized. This paper proposes an attention-based graph model, named GATraj, which achieves a good balance of prediction accuracy and inference speed. We use attention mechanisms to model the spatial-temporal dynamics of agents, such as pedestrians or vehicles, and a graph convolutional network to model their interactions. Additionally, a Laplacian mixture decoder is implemented to mitigate mode collapse and generate diverse multimodal predictions for each agent. GATraj achieves state-of-the-art prediction performance at a much higher speed when tested on the ETH/UCY datasets for pedestrian trajectories, and good performance at about 100 Hz inference speed when tested on the nuScenes dataset for autonomous driving. We conduct extensive experiments to analyze the probability estimation of the Laplacian mixture decoder and compare it with a Gaussian mixture decoder for predicting different multimodalities. Furthermore, comprehensive ablation studies demonstrate the effectiveness of each proposed module in GATraj. The code is released at https://github.com/mengmengliu1998/GATraj." @default.
- W4296413562 created "2022-09-20" @default.
- W4296413562 creator A5010902953 @default.
- W4296413562 creator A5014321482 @default.
- W4296413562 creator A5020817045 @default.
- W4296413562 creator A5030949589 @default.
- W4296413562 creator A5055768799 @default.
- W4296413562 creator A5078143614 @default.
- W4296413562 date "2022-09-16" @default.
- W4296413562 modified "2023-10-16" @default.
- W4296413562 title "GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model" @default.
- W4296413562 doi "https://doi.org/10.48550/arxiv.2209.07857" @default.
- W4296413562 hasPublicationYear "2022" @default.
- W4296413562 type Work @default.
- W4296413562 citedByCount "0" @default.
- W4296413562 crossrefType "posted-content" @default.
- W4296413562 hasAuthorship W4296413562A5010902953 @default.
- W4296413562 hasAuthorship W4296413562A5014321482 @default.
- W4296413562 hasAuthorship W4296413562A5020817045 @default.
- W4296413562 hasAuthorship W4296413562A5030949589 @default.
- W4296413562 hasAuthorship W4296413562A5055768799 @default.
- W4296413562 hasAuthorship W4296413562A5078143614 @default.
- W4296413562 hasBestOaLocation W42964135621 @default.
- W4296413562 hasConcept C119857082 @default.
- W4296413562 hasConcept C121332964 @default.
- W4296413562 hasConcept C125411270 @default.
- W4296413562 hasConcept C1276947 @default.
- W4296413562 hasConcept C132525143 @default.
- W4296413562 hasConcept C13662910 @default.
- W4296413562 hasConcept C154945302 @default.
- W4296413562 hasConcept C163716315 @default.
- W4296413562 hasConcept C177264268 @default.
- W4296413562 hasConcept C199360897 @default.
- W4296413562 hasConcept C2776214188 @default.
- W4296413562 hasConcept C2776760102 @default.
- W4296413562 hasConcept C41008148 @default.
- W4296413562 hasConcept C62520636 @default.
- W4296413562 hasConcept C80444323 @default.
- W4296413562 hasConcept C90509273 @default.
- W4296413562 hasConceptScore W4296413562C119857082 @default.
- W4296413562 hasConceptScore W4296413562C121332964 @default.
- W4296413562 hasConceptScore W4296413562C125411270 @default.
- W4296413562 hasConceptScore W4296413562C1276947 @default.
- W4296413562 hasConceptScore W4296413562C132525143 @default.
- W4296413562 hasConceptScore W4296413562C13662910 @default.
- W4296413562 hasConceptScore W4296413562C154945302 @default.
- W4296413562 hasConceptScore W4296413562C163716315 @default.
- W4296413562 hasConceptScore W4296413562C177264268 @default.
- W4296413562 hasConceptScore W4296413562C199360897 @default.
- W4296413562 hasConceptScore W4296413562C2776214188 @default.
- W4296413562 hasConceptScore W4296413562C2776760102 @default.
- W4296413562 hasConceptScore W4296413562C41008148 @default.
- W4296413562 hasConceptScore W4296413562C62520636 @default.
- W4296413562 hasConceptScore W4296413562C80444323 @default.
- W4296413562 hasConceptScore W4296413562C90509273 @default.
- W4296413562 hasLocation W42964135621 @default.
- W4296413562 hasOpenAccess W4296413562 @default.
- W4296413562 hasPrimaryLocation W42964135621 @default.
- W4296413562 hasRelatedWork W2171541671 @default.
- W4296413562 hasRelatedWork W2389073067 @default.
- W4296413562 hasRelatedWork W2903025760 @default.
- W4296413562 hasRelatedWork W2911485121 @default.
- W4296413562 hasRelatedWork W2961085424 @default.
- W4296413562 hasRelatedWork W2963058055 @default.
- W4296413562 hasRelatedWork W4286629047 @default.
- W4296413562 hasRelatedWork W4289147272 @default.
- W4296413562 hasRelatedWork W4306674287 @default.
- W4296413562 hasRelatedWork W4224009465 @default.
- W4296413562 isParatext "false" @default.
- W4296413562 isRetracted "false" @default.
- W4296413562 workType "article" @default.