Personalized Trajectory Prediction via Distribution Discrimination

TL;DR

This paper introduces a distribution discrimination method for personalized trajectory prediction, enhancing the ability to distinguish diverse motion patterns by learning discriminative latent distributions, and demonstrates its effectiveness on benchmark datasets.

Contribution

The paper proposes a novel distribution discrimination approach that improves multi-modal trajectory prediction by learning more discriminative latent distributions as a plug-and-play module.

Findings

Improved prediction accuracy on ETH and UCY datasets.

Introduced the PCMD metric for evaluating latent distribution quality.

Effective integration with existing stochastic models.

Abstract

Trajectory prediction is confronted with the dilemma to capture the multi-modal nature of future dynamics with both diversity and accuracy. In this paper, we present a distribution discrimination (DisDis) method to predict personalized motion patterns by distinguishing the potential distributions. Motivated by that the motion pattern of each person is personalized due to his/her habit, our DisDis learns the latent distribution to represent different motion patterns and optimize it by the contrastive discrimination. This distribution discrimination encourages latent distributions to be more discriminative. Our method can be integrated with existing multi-modal stochastic predictive models as a plug-and-play module to learn the more discriminative latent distribution. To evaluate the latent distribution, we further propose a new metric, probability cumulative minimum distance (PCMD) curve, which cumulatively calculates the minimum distance on the sorted probabilities. Experimental results on the ETH and UCY datasets show the effectiveness of our method.