Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction

TL;DR

This paper investigates a hybrid model combining LSTM and Transformer architectures to improve vehicle trajectory prediction by capturing complex spatial and temporal interactions, aiming for more interpretable and robust autonomous driving systems.

Contribution

It introduces a novel hybrid LSTM-Transformer model for trajectory prediction, integrating spatial and temporal features in a unified framework.

Findings

The hybrid model effectively captures vehicle interactions.

It demonstrates potential for improved interpretability.

Benchmark results show competitive performance.

Abstract

Accurate vehicle trajectory prediction is crucial for ensuring safe and efficient autonomous driving. This work explores the integration of Transformer based model with Long Short-Term Memory (LSTM) based technique to enhance spatial and temporal feature learning in vehicle trajectory prediction. Here, a hybrid model that combines LSTMs for temporal encoding with a Transformer encoder for capturing complex interactions between vehicles is proposed. Spatial trajectory features of the neighboring vehicles are processed and goes through a masked scatter mechanism in a grid based environment, which is then combined with temporal trajectory of the vehicles. This combined trajectory data are learned by sequential LSTM encoding and Transformer based attention layers. The proposed model is benchmarked against predecessor LSTM based methods, including STA-LSTM, SA-LSTM, CS-LSTM, and NaiveLSTM. Our results, while not outperforming it's predecessor, demonstrate the potential of integrating Transformers with LSTM based technique to build interpretable trajectory prediction model. Future work will explore alternative architectures using Transformer applications to further enhance performance. This study provides a promising direction for improving trajectory prediction models by leveraging transformer based architectures, paving the way for more robust and interpretable vehicle trajectory prediction system.