This paper presents online-capable deep learning model for probabilistic vehicle trajectory prediction. We propose a simple encoder-decoder architecture based on multihead attention. The proposed model generates the distribution of the predicted trajectories for multiple vehicles in parallel. Our approach to model the interactions can learn to attend to a few influential vehicles in an unsupervised manner, which can improve the interpretability of the network. The experiments using naturalistic trajectories at highway show the clear improvement in terms of positional error on both longitudinal and lateral direction.
Multi-Head Attention based Probabilistic Vehicle Trajectory Prediction
2020 IEEE Intelligent Vehicles Symposium (IV) ; 1720-1725
2020-10-19
1555648 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
MULTI-HEAD ATTENTION BASED PROBABILISTIC VEHICLE TRAJECTORY PREDICTION
British Library Conference Proceedings | 2020
|Attention Based Vehicle Trajectory Prediction
IEEE | 2021
|Probabilistic Vehicle Trajectory Prediction Based on LSTM Encoder-Decoder and Attention Mechanism
British Library Conference Proceedings | 2022
|Probabilistic Vehicle Trajectory Prediction Based on LSTM Encoder-Decoder and Attention Mechanism
SAE Technical Papers | 2022
|