Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385695945> ?p ?o ?g. }
- W4385695945 endingPage "85926" @default.
- W4385695945 startingPage "85914" @default.
- W4385695945 abstract "Reliably predicting the motion of contestant vehicles surrounding an autonomous racecar is crucial for effective and performant ego-motion planning. Although highly expressive, deep neural networks are black-box models, making their usage challenging in this safety-critical applications of autonomous racing. On the other hand, physics-based models provide high safety guarantees for the predicted trajectory but lack accuracy. The method presented in this paper targets this trade-off. We introduce a method to predict the trajectories of opposing racecars with deep neural networks considering physical constraints to restrict the output and to improve its feasibility.We report the method’s performance against an LSTM-based encoder-decoder architecture on data acquired from multi-agent racing simulations. The proposed method outperforms the baseline model in prediction accuracy and robustness. Still, it fulfills quality guarantees of smoothness and consistency of the predicted trajectory and prevents out-of-track predictions. Thus, a robust real-world application of the model with high prediction accuracy is proven. The presented model was deployed on the racecar of the Technical University of Munich for the Indy Autonomous Challenge 2021. The code used in this research is available as open-source software at www.github.com/TUMFTM/MixNet." @default.
- W4385695945 created "2023-08-10" @default.
- W4385695945 creator A5019994361 @default.
- W4385695945 creator A5045985153 @default.
- W4385695945 creator A5079718896 @default.
- W4385695945 creator A5091224383 @default.
- W4385695945 date "2023-01-01" @default.
- W4385695945 modified "2023-10-14" @default.
- W4385695945 title "MixNet: Physics Constrained Deep Neural Motion Prediction for Autonomous Racing" @default.
- W4385695945 cites W2048093873 @default.
- W4385695945 cites W2055556996 @default.
- W4385695945 cites W2092272787 @default.
- W4385695945 cites W2105934661 @default.
- W4385695945 cites W2136707818 @default.
- W4385695945 cites W2162966954 @default.
- W4385695945 cites W2477231637 @default.
- W4385695945 cites W2567297805 @default.
- W4385695945 cites W2580495915 @default.
- W4385695945 cites W2740071316 @default.
- W4385695945 cites W2769282630 @default.
- W4385695945 cites W2774231091 @default.
- W4385695945 cites W2784715585 @default.
- W4385695945 cites W2891376043 @default.
- W4385695945 cites W2891385160 @default.
- W4385695945 cites W2892825772 @default.
- W4385695945 cites W2905173465 @default.
- W4385695945 cites W2951357333 @default.
- W4385695945 cites W2955189650 @default.
- W4385695945 cites W2963906196 @default.
- W4385695945 cites W2969811230 @default.
- W4385695945 cites W2990360961 @default.
- W4385695945 cites W3003906095 @default.
- W4385695945 cites W3007298738 @default.
- W4385695945 cites W3034722190 @default.
- W4385695945 cites W3035574168 @default.
- W4385695945 cites W3086854072 @default.
- W4385695945 cites W3090166818 @default.
- W4385695945 cites W3091155851 @default.
- W4385695945 cites W3114224083 @default.
- W4385695945 cites W3116651890 @default.
- W4385695945 cites W3116942665 @default.
- W4385695945 cites W3131888273 @default.
- W4385695945 cites W4205518878 @default.
- W4385695945 cites W4225339769 @default.
- W4385695945 cites W4225642194 @default.
- W4385695945 cites W4231339208 @default.
- W4385695945 cites W4285228542 @default.
- W4385695945 cites W4308333989 @default.
- W4385695945 cites W4308336521 @default.
- W4385695945 cites W4315797158 @default.
- W4385695945 cites W4319599085 @default.
- W4385695945 cites W4367665672 @default.
- W4385695945 doi "https://doi.org/10.1109/access.2023.3303841" @default.
- W4385695945 hasPublicationYear "2023" @default.
- W4385695945 type Work @default.
- W4385695945 citedByCount "0" @default.
- W4385695945 crossrefType "journal-article" @default.
- W4385695945 hasAuthorship W4385695945A5019994361 @default.
- W4385695945 hasAuthorship W4385695945A5045985153 @default.
- W4385695945 hasAuthorship W4385695945A5079718896 @default.
- W4385695945 hasAuthorship W4385695945A5091224383 @default.
- W4385695945 hasBestOaLocation W43856959451 @default.
- W4385695945 hasConcept C104317684 @default.
- W4385695945 hasConcept C111919701 @default.
- W4385695945 hasConcept C118505674 @default.
- W4385695945 hasConcept C119857082 @default.
- W4385695945 hasConcept C121332964 @default.
- W4385695945 hasConcept C1276947 @default.
- W4385695945 hasConcept C13662910 @default.
- W4385695945 hasConcept C154945302 @default.
- W4385695945 hasConcept C177264268 @default.
- W4385695945 hasConcept C185592680 @default.
- W4385695945 hasConcept C199360897 @default.
- W4385695945 hasConcept C2776760102 @default.
- W4385695945 hasConcept C2984842247 @default.
- W4385695945 hasConcept C41008148 @default.
- W4385695945 hasConcept C50644808 @default.
- W4385695945 hasConcept C55493867 @default.
- W4385695945 hasConcept C63479239 @default.
- W4385695945 hasConceptScore W4385695945C104317684 @default.
- W4385695945 hasConceptScore W4385695945C111919701 @default.
- W4385695945 hasConceptScore W4385695945C118505674 @default.
- W4385695945 hasConceptScore W4385695945C119857082 @default.
- W4385695945 hasConceptScore W4385695945C121332964 @default.
- W4385695945 hasConceptScore W4385695945C1276947 @default.
- W4385695945 hasConceptScore W4385695945C13662910 @default.
- W4385695945 hasConceptScore W4385695945C154945302 @default.
- W4385695945 hasConceptScore W4385695945C177264268 @default.
- W4385695945 hasConceptScore W4385695945C185592680 @default.
- W4385695945 hasConceptScore W4385695945C199360897 @default.
- W4385695945 hasConceptScore W4385695945C2776760102 @default.
- W4385695945 hasConceptScore W4385695945C2984842247 @default.
- W4385695945 hasConceptScore W4385695945C41008148 @default.
- W4385695945 hasConceptScore W4385695945C50644808 @default.
- W4385695945 hasConceptScore W4385695945C55493867 @default.
- W4385695945 hasConceptScore W4385695945C63479239 @default.
- W4385695945 hasFunder F4320321450 @default.
- W4385695945 hasFunder F4320323383 @default.