Trajectory Prediction using Generative Adversarial Network in Multi-Class Scenarios

TL;DR

This paper introduces a generative adversarial network-based model for multi-class traffic trajectory prediction, integrating class information into sequence-to-sequence models with LSTM and transformer encoders, evaluated on the Stanford Drone dataset.

Contribution

It presents a novel multi-class trajectory prediction model using GANs that incorporates class labels into sequence models, enhancing multi-modal behavior learning.

Findings

Incorporating class information improves prediction accuracy.

Transformer encoders outperform LSTM in this task.

The model effectively captures multi-modal traffic behaviors.

Abstract

Predicting traffic agents' trajectories is an important task for auto-piloting. Most previous work on trajectory prediction only considers a single class of road agents. We use a sequence-to-sequence model to predict future paths from observed paths and we incorporate class information into the model by concatenating extracted label representations with traditional location inputs. We experiment with both LSTM and transformer encoders and we use generative adversarial network as introduced in Social GAN to learn the multi-modal behavior of traffic agents. We train our model on Stanford Drone dataset which includes 6 classes of road agents and evaluate the impact of different model components on the prediction performance in multi-class scenes.