Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights

TL;DR

This paper introduces DTGAN, a novel GAN-based framework that automatically captures implicit social interactions in pedestrian trajectories using random weights, significantly improving prediction accuracy without pre-defined rules.

Contribution

The work extends GANs to graph sequence data with random weights, enabling automatic modeling of social interactions for pedestrian trajectory prediction, surpassing existing rule-based methods.

Findings

Achieves 16.7% improvement in ADE

Achieves 39.3% improvement in FDE

Outperforms existing methods on public datasets

Abstract

Pedestrian trajectory prediction is a critical technology in the evolution of self-driving cars toward complete artificial intelligence. Over recent years, focusing on the trajectories of pedestrians to model their social interactions has surged with great interest in more accurate trajectory predictions. However, existing methods for modeling pedestrian social interactions rely on pre-defined rules, struggling to capture non-explicit social interactions. In this work, we propose a novel framework named DTGAN, which extends the application of Generative Adversarial Networks (GANs) to graph sequence data, with the primary objective of automatically capturing implicit social interactions and achieving precise predictions of pedestrian trajectory. DTGAN innovatively incorporates random weights within each graph to eliminate the need for pre-defined interaction rules. We further enhance the performance of DTGAN by exploring diverse task loss functions during adversarial training, which yields improvements of 16.7\% and 39.3\% on metrics ADE and FDE, respectively. The effectiveness and accuracy of our framework are verified on two public datasets. The experimental results show that our proposed DTGAN achieves superior performance and is well able to understand pedestrians' intentions.