Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308146710> ?p ?o ?g. }
- W4308146710 endingPage "757" @default.
- W4308146710 startingPage "744" @default.
- W4308146710 abstract "Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving (AD) system. However, most proposed methods aim at addressing one of the two challenges mentioned above with a single model. To tackle this dilemma, this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting (ST-SIGMA), an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework. ST-SIGMA adopts a trident encoder–decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view (BEV) maps simultaneously. Specifically, an iterative aggregation network is first employed as the scene semantic encoder (SSE) to learn diverse scene information. To preserve dynamic interactions of traffic agents, ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder. Meanwhile, a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed. Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-the-art (SOTA) methods in terms of scene perception and trajectory forecasting, respectively. Therefore, the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in real-world AD scenarios." @default.
- W4308146710 created "2022-11-08" @default.
- W4308146710 creator A5004081553 @default.
- W4308146710 creator A5007569823 @default.
- W4308146710 creator A5013029508 @default.
- W4308146710 creator A5018822389 @default.
- W4308146710 creator A5053099436 @default.
- W4308146710 creator A5073411266 @default.
- W4308146710 date "2022-11-02" @default.
- W4308146710 modified "2023-09-30" @default.
- W4308146710 title "ST‐SIGMA: Spatio‐temporal semantics and interaction graph aggregation for multi‐agent perception and trajectory forecasting" @default.
- W4308146710 cites W2581887665 @default.
- W4308146710 cites W2883638665 @default.
- W4308146710 cites W2884561390 @default.
- W4308146710 cites W2949708697 @default.
- W4308146710 cites W2962766617 @default.
- W4308146710 cites W2962771259 @default.
- W4308146710 cites W2963076818 @default.
- W4308146710 cites W2963323244 @default.
- W4308146710 cites W2963727135 @default.
- W4308146710 cites W2964062501 @default.
- W4308146710 cites W2968008415 @default.
- W4308146710 cites W2968296999 @default.
- W4308146710 cites W2968337686 @default.
- W4308146710 cites W2971686478 @default.
- W4308146710 cites W2985871763 @default.
- W4308146710 cites W3034295100 @default.
- W4308146710 cites W3035096461 @default.
- W4308146710 cites W3035360167 @default.
- W4308146710 cites W3035461736 @default.
- W4308146710 cites W3035574168 @default.
- W4308146710 cites W3036899852 @default.
- W4308146710 cites W3096609285 @default.
- W4308146710 cites W3107209377 @default.
- W4308146710 cites W3107422826 @default.
- W4308146710 cites W3114753236 @default.
- W4308146710 cites W3116651890 @default.
- W4308146710 cites W3149485574 @default.
- W4308146710 cites W3153727940 @default.
- W4308146710 cites W3167095230 @default.
- W4308146710 cites W3177765762 @default.
- W4308146710 cites W3196864007 @default.
- W4308146710 cites W4210257598 @default.
- W4308146710 cites W4290716501 @default.
- W4308146710 cites W4312420906 @default.
- W4308146710 cites W4312473433 @default.
- W4308146710 cites W4312825882 @default.
- W4308146710 cites W639708223 @default.
- W4308146710 doi "https://doi.org/10.1049/cit2.12145" @default.
- W4308146710 hasPublicationYear "2022" @default.
- W4308146710 type Work @default.
- W4308146710 citedByCount "2" @default.
- W4308146710 countsByYear W43081467102023 @default.
- W4308146710 crossrefType "journal-article" @default.
- W4308146710 hasAuthorship W4308146710A5004081553 @default.
- W4308146710 hasAuthorship W4308146710A5007569823 @default.
- W4308146710 hasAuthorship W4308146710A5013029508 @default.
- W4308146710 hasAuthorship W4308146710A5018822389 @default.
- W4308146710 hasAuthorship W4308146710A5053099436 @default.
- W4308146710 hasAuthorship W4308146710A5073411266 @default.
- W4308146710 hasBestOaLocation W43081467101 @default.
- W4308146710 hasConcept C104317684 @default.
- W4308146710 hasConcept C111919701 @default.
- W4308146710 hasConcept C118505674 @default.
- W4308146710 hasConcept C121332964 @default.
- W4308146710 hasConcept C1276947 @default.
- W4308146710 hasConcept C132525143 @default.
- W4308146710 hasConcept C13662910 @default.
- W4308146710 hasConcept C138885662 @default.
- W4308146710 hasConcept C154945302 @default.
- W4308146710 hasConcept C184337299 @default.
- W4308146710 hasConcept C185592680 @default.
- W4308146710 hasConcept C199360897 @default.
- W4308146710 hasConcept C2776401178 @default.
- W4308146710 hasConcept C41008148 @default.
- W4308146710 hasConcept C41895202 @default.
- W4308146710 hasConcept C55493867 @default.
- W4308146710 hasConcept C63479239 @default.
- W4308146710 hasConcept C80444323 @default.
- W4308146710 hasConceptScore W4308146710C104317684 @default.
- W4308146710 hasConceptScore W4308146710C111919701 @default.
- W4308146710 hasConceptScore W4308146710C118505674 @default.
- W4308146710 hasConceptScore W4308146710C121332964 @default.
- W4308146710 hasConceptScore W4308146710C1276947 @default.
- W4308146710 hasConceptScore W4308146710C132525143 @default.
- W4308146710 hasConceptScore W4308146710C13662910 @default.
- W4308146710 hasConceptScore W4308146710C138885662 @default.
- W4308146710 hasConceptScore W4308146710C154945302 @default.
- W4308146710 hasConceptScore W4308146710C184337299 @default.
- W4308146710 hasConceptScore W4308146710C185592680 @default.
- W4308146710 hasConceptScore W4308146710C199360897 @default.
- W4308146710 hasConceptScore W4308146710C2776401178 @default.
- W4308146710 hasConceptScore W4308146710C41008148 @default.
- W4308146710 hasConceptScore W4308146710C41895202 @default.
- W4308146710 hasConceptScore W4308146710C55493867 @default.
- W4308146710 hasConceptScore W4308146710C63479239 @default.
- W4308146710 hasConceptScore W4308146710C80444323 @default.
- W4308146710 hasFunder F4320321001 @default.