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

## TL;DR

This paper introduces a GAN-based method for multi-modal pedestrian trajectory prediction, leveraging Info-GAN to improve diversity and mode preservation without using L2-loss, validated on real and synthetic data.

## Contribution

The paper presents a novel application of Info-GAN for pedestrian trajectory prediction, addressing mode collapse and diversity issues without L2-loss.

## Key findings

- Enhanced diversity in trajectory samples
- Better preservation of distribution modes
- Validated on real and synthetic datasets

## Abstract

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.