PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

Résumé

Nowadays, our mobility systems are evolving into the era of intelligent vehicles that aim to improve road safety. Due to their vulnerability, pedestrians are the users who will benefit the most from these developments. However, predicting their trajectory is one of the most challenging concerns. Indeed, accurate prediction requires a good understanding of multi-agent interactions that can be complex. Learning the underlying spatial and temporal patterns caused by these interactions is even more of a competitive and open problem that many researchers are tackling. In this paper, we introduce a model called PRediction Transformer (PReTR) that extracts features from the multi-agent scenes by employing a factorized spatio-temporal attention module. It shows less computational needs than previously studied models with empirically better results. Besides, previous works in motion prediction suffer from the exposure bias problem caused by generating future sequences conditioned on model prediction samples rather than ground-truth samples. In order to go beyond the proposed solutions, we leverage encoder-decoder Transformer networks for parallel decoding a set of learned object queries. This non-autoregressive solution avoids the need for iterative conditioning and arguably decreases training and testing computational time. We evaluate our model on the ETH/UCY datasets, a publicly available benchmark for pedestrian trajectory prediction. Finally, we justify our usage of the parallel decoding technique by showing that the trajectory prediction task can be better solved as a non-autoregressive task.

Dates et versions

hal-03952397 , version 1 (23-01-2023)

Identifiants

Citer

Lina Achaji, Thierno Barry, Thibault Fouqueray, Julien Moreau, Francois Aioun, et al.. PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer. 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), Oct 2022, Macau, China. pp.2457-2464, ⟨10.1109/ITSC55140.2022.9922451⟩. ⟨hal-03952397⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More