Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories With GANs

This paper proposes a novel approach for predicting the motion of pedestrians interacting with others. It uses a Generative Adversarial Network (GAN) to sample plausible predictions for any agent in the scene. As GANs are very susceptible to mode collapsing and dropping, we show that the recently pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Amirian, Javad, Hayet, Jean-Bernard, Pettre, Julien
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Encoding
Gallium nitride
Generative adversarial networks
Generators
Mathematical model
Trajectory
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a novel approach for predicting the motion of pedestrians interacting with others. It uses a Generative Adversarial Network (GAN) to sample plausible predictions for any agent in the scene. As GANs are very susceptible to mode collapsing and dropping, we show that the recently proposed Info-GAN allows dramatic improvements in multi-modal pedestrian trajectory prediction to avoid these issues. We also left out L2-loss in training the generator, unlike some previous works, because it causes serious mode collapsing though faster convergence. We show through experiments on real and synthetic data that the proposed method leads to generate more diverse samples and to preserve the modes of the predictive distribution. In particular, to prove this claim, we have designed a toy example dataset of trajectories that can be used to assess the performance of different methods in preserving the predictive distribution modes.
ISSN:2160-7516
DOI:10.1109/CVPRW.2019.00359