Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383097675> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4383097675 abstract "Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the fragmented human driving data collected in the real world and then generates realistic traffic scenarios. TrafficGen is an autoregressive neural generative model with an encoder-decoder architecture. In each autoregressive iteration, it first encodes the current traffic context with the attention mechanism and then decodes a vehicle's initial state followed by generating its long trajectory. We evaluate the trained model in terms of vehicle placement and trajectories, and the experimental result shows our method has substantial improvements over baselines for generating traffic scenarios. After training, TrafficGen can also augment existing traffic scenarios, by adding new vehicles and extending the fragmented trajectories. We further demonstrate that importing the generated scenarios into a simulator as an interactive training environment improves the performance and safety of a driving agent learned from reinforcement learning. Model and data are available at https://metadriverse.github.io/trafficgen." @default.
- W4383097675 created "2023-07-05" @default.
- W4383097675 creator A5023855672 @default.
- W4383097675 creator A5033444412 @default.
- W4383097675 creator A5064938053 @default.
- W4383097675 creator A5081844561 @default.
- W4383097675 creator A5087474202 @default.
- W4383097675 date "2023-05-29" @default.
- W4383097675 modified "2023-09-25" @default.
- W4383097675 title "TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios" @default.
- W4383097675 cites W2056877664 @default.
- W4383097675 cites W2903709398 @default.
- W4383097675 cites W2955189650 @default.
- W4383097675 cites W2957066083 @default.
- W4383097675 cites W2991501130 @default.
- W4383097675 cites W3034722190 @default.
- W4383097675 cites W3098394944 @default.
- W4383097675 cites W3104790740 @default.
- W4383097675 cites W3173280621 @default.
- W4383097675 cites W3181350748 @default.
- W4383097675 cites W3207915602 @default.
- W4383097675 doi "https://doi.org/10.1109/icra48891.2023.10160296" @default.
- W4383097675 hasPublicationYear "2023" @default.
- W4383097675 type Work @default.
- W4383097675 citedByCount "0" @default.
- W4383097675 crossrefType "proceedings-article" @default.
- W4383097675 hasAuthorship W4383097675A5023855672 @default.
- W4383097675 hasAuthorship W4383097675A5033444412 @default.
- W4383097675 hasAuthorship W4383097675A5064938053 @default.
- W4383097675 hasAuthorship W4383097675A5081844561 @default.
- W4383097675 hasAuthorship W4383097675A5087474202 @default.
- W4383097675 hasBestOaLocation W43830976752 @default.
- W4383097675 hasConcept C111919701 @default.
- W4383097675 hasConcept C118505674 @default.
- W4383097675 hasConcept C119857082 @default.
- W4383097675 hasConcept C121332964 @default.
- W4383097675 hasConcept C127413603 @default.
- W4383097675 hasConcept C1276947 @default.
- W4383097675 hasConcept C13662910 @default.
- W4383097675 hasConcept C149782125 @default.
- W4383097675 hasConcept C151730666 @default.
- W4383097675 hasConcept C154945302 @default.
- W4383097675 hasConcept C159877910 @default.
- W4383097675 hasConcept C162324750 @default.
- W4383097675 hasConcept C22212356 @default.
- W4383097675 hasConcept C2778391309 @default.
- W4383097675 hasConcept C2779343474 @default.
- W4383097675 hasConcept C2780015235 @default.
- W4383097675 hasConcept C41008148 @default.
- W4383097675 hasConcept C79403827 @default.
- W4383097675 hasConcept C86803240 @default.
- W4383097675 hasConcept C87833898 @default.
- W4383097675 hasConcept C97541855 @default.
- W4383097675 hasConceptScore W4383097675C111919701 @default.
- W4383097675 hasConceptScore W4383097675C118505674 @default.
- W4383097675 hasConceptScore W4383097675C119857082 @default.
- W4383097675 hasConceptScore W4383097675C121332964 @default.
- W4383097675 hasConceptScore W4383097675C127413603 @default.
- W4383097675 hasConceptScore W4383097675C1276947 @default.
- W4383097675 hasConceptScore W4383097675C13662910 @default.
- W4383097675 hasConceptScore W4383097675C149782125 @default.
- W4383097675 hasConceptScore W4383097675C151730666 @default.
- W4383097675 hasConceptScore W4383097675C154945302 @default.
- W4383097675 hasConceptScore W4383097675C159877910 @default.
- W4383097675 hasConceptScore W4383097675C162324750 @default.
- W4383097675 hasConceptScore W4383097675C22212356 @default.
- W4383097675 hasConceptScore W4383097675C2778391309 @default.
- W4383097675 hasConceptScore W4383097675C2779343474 @default.
- W4383097675 hasConceptScore W4383097675C2780015235 @default.
- W4383097675 hasConceptScore W4383097675C41008148 @default.
- W4383097675 hasConceptScore W4383097675C79403827 @default.
- W4383097675 hasConceptScore W4383097675C86803240 @default.
- W4383097675 hasConceptScore W4383097675C87833898 @default.
- W4383097675 hasConceptScore W4383097675C97541855 @default.
- W4383097675 hasLocation W43830976751 @default.
- W4383097675 hasLocation W43830976752 @default.
- W4383097675 hasOpenAccess W4383097675 @default.
- W4383097675 hasPrimaryLocation W43830976751 @default.
- W4383097675 hasRelatedWork W2056851291 @default.
- W4383097675 hasRelatedWork W2275988210 @default.
- W4383097675 hasRelatedWork W2356875448 @default.
- W4383097675 hasRelatedWork W3022038857 @default.
- W4383097675 hasRelatedWork W3209094908 @default.
- W4383097675 hasRelatedWork W3211008319 @default.
- W4383097675 hasRelatedWork W4206669594 @default.
- W4383097675 hasRelatedWork W4210912933 @default.
- W4383097675 hasRelatedWork W4319083788 @default.
- W4383097675 hasRelatedWork W4365211772 @default.
- W4383097675 isParatext "false" @default.
- W4383097675 isRetracted "false" @default.
- W4383097675 workType "article" @default.