LTN: Long-Term Network for Long-Term Motion Prediction

TL;DR

This paper introduces LTN, a two-stage long-term motion prediction framework combining CVAE-based trajectory proposals with classification, outperforming existing methods on real-world datasets.

Contribution

The paper proposes a novel two-stage framework for long-term trajectory prediction that integrates regression and classification, addressing divergence issues in LSTM-based models.

Findings

Outperforms state-of-the-art methods in long-term prediction accuracy.

Effective on multiple real-world datasets including ETH/UCY, SDD, and nuScenes.

Demonstrates robustness in complex real-world scenarios.

Abstract

Making accurate motion prediction of surrounding agents such as pedestrians and vehicles is a critical task when robots are trying to perform autonomous navigation tasks. Recent research on multi-modal trajectory prediction, including regression and classification approaches, perform very well at short-term prediction. However, when it comes to long-term prediction, most Long Short-Term Memory (LSTM) based models tend to diverge far away from the ground truth. Therefore, in this work, we present a two-stage framework for long-term trajectory prediction, which is named as Long-Term Network (LTN). Our Long-Term Network integrates both the regression and classification approaches. We first generate a set of proposed trajectories with our proposed distribution using a Conditional Variational Autoencoder (CVAE), and then classify them with binary labels, and output the trajectories with the highest score. We demonstrate our Long-Term Network's performance with experiments on two real-world pedestrian datasets: ETH/UCY, Stanford Drone Dataset (SDD), and one challenging real-world driving forecasting dataset: nuScenes. The results show that our method outperforms multiple state-of-the-art approaches in long-term trajectory prediction in terms of accuracy.