PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

TL;DR

PreTR introduces a non-autoregressive Transformer model for pedestrian trajectory prediction that efficiently captures multi-agent spatio-temporal interactions, outperforming previous models in accuracy and computational efficiency.

Contribution

The paper presents PReTR, a novel non-autoregressive Transformer with spatio-temporal attention for trajectory prediction, reducing computational costs and addressing exposure bias.

Findings

Empirically better results on ETH/UCY datasets

Less computational needs compared to prior models

Effective non-autoregressive trajectory prediction

Abstract

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.