Asymmetrical Bi-RNNs (U-RNNs), 2nd place solution at the Trajnet++ Challenge for pedestrian trajectory forecasting

Raphaël Rozenberg (1, 2) , Joseph Gesnouin (3, 1) , Fabien Moutarde (1)

1 CAOR - Centre de Robotique
2 ENS-PSL - École normale supérieure - Paris
3 VeDeCom - VEhicule DEcarboné et COmmuniquant et sa Mobilité

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Raphaël Rozenberg, Joseph Gesnouin, Fabien Moutarde. Asymmetrical Bi-RNNs (U-RNNs), 2nd place solution at the Trajnet++ Challenge for pedestrian trajectory forecasting. Workshop on Long-term Human Motion Prediction, 2021 IEEE International Conference on Robotics and Automation (ICRA), May 2021, Xi'an, China. ⟨hal-03244860⟩