Motion Forecasting via Model-Based Risk Minimization

TL;DR

This paper introduces a novel model-based risk minimization sampling method for trajectory prediction in autonomous vehicles, leveraging ensemble neural networks to improve accuracy and reliability in multi-modal trajectory forecasting.

Contribution

It proposes a new ensemble sampling approach that addresses limitations of probability-based sampling, framing trajectory prediction as a risk minimization problem with diverse neural network models.

Findings

Outperforms state-of-the-art methods on nuScenes dataset

Constructs diverse ensembles for optimal trajectory sampling

Provides insights into ensembling strategies effectiveness

Abstract

Forecasting the future trajectories of surrounding agents is crucial for autonomous vehicles to ensure safe, efficient, and comfortable route planning. While model ensembling has improved prediction accuracy in various fields, its application in trajectory prediction is limited due to the multi-modal nature of predictions. In this paper, we propose a novel sampling method applicable to trajectory prediction based on the predictions of multiple models. We first show that conventional sampling based on predicted probabilities can degrade performance due to missing alignment between models. To address this problem, we introduce a new method that generates optimal trajectories from a set of neural networks, framing it as a risk minimization problem with a variable loss function. By using state-of-the-art models as base learners, our approach constructs diverse and effective ensembles for optimal trajectory sampling. Extensive experiments on the nuScenes prediction dataset demonstrate that our method surpasses current state-of-the-art techniques, achieving top ranks on the leaderboard. We also provide a comprehensive empirical study on ensembling strategies, offering insights into their effectiveness. Our findings highlight the potential of advanced ensembling techniques in trajectory prediction, significantly improving predictive performance and paving the way for more reliable predicted trajectories.