MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

08/20/2021
by   Patrick Dendorfer, et al.
6

Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature. While generative adversarial networks can learn a distribution over future trajectories, they tend to predict out-of-distribution samples when the distribution of future trajectories is a mixture of multiple, possibly disconnected modes. To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene, while a second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input. This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 14

page 16

research
04/20/2019

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

This paper proposes a novel approach for predicting the motion of pedest...
research
04/21/2020

Take a NAP: Non-Autoregressive Prediction for Pedestrian Trajectories

Pedestrian trajectory prediction is a challenging task as there are thre...
research
02/02/2018

Selective Sampling and Mixture Models in Generative Adversarial Networks

In this paper, we propose a multi-generator extension to the adversarial...
research
12/12/2019

Semantic segmentation of trajectories with improved agent models for pedestrian behavior analysis

In this paper, we propose a method for semantic segmentation of pedestri...
research
06/08/2020

Learning disconnected manifolds: a no GANs land

Typical architectures of Generative AdversarialNetworks make use of a un...
research
06/09/2019

Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction

Future prediction is a fundamental principle of intelligence that helps ...
research
03/31/2022

End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps

In this paper, we aim to forecast a future trajectory distribution of a ...

Please sign up or login with your details

Forgot password? Click here to reset