Critical Example Mining for Vehicle Trajectory Prediction using Flow-based Generative Models

TL;DR

This paper introduces a data-driven critical example mining method that identifies challenging vehicle trajectories based on their rarity, improving understanding and robustness of autonomous vehicle prediction models.

Contribution

It presents a novel approach to estimate trajectory rareness and mine critical examples, highlighting uncommon cases to enhance prediction model performance.

Findings

Mined subset increases prediction error by +108.1% on 5% samples.

Critical examples include rare scenarios like sudden brakes and lane changes.

Method improves understanding of challenging driving scenarios.

Abstract

Precise trajectory prediction in complex driving scenarios is essential for autonomous vehicles. In practice, different driving scenarios present varying levels of difficulty for trajectory prediction models. However, most existing research focuses on the average precision of prediction results, while ignoring the underlying distribution of the input scenarios. This paper proposes a critical example mining method that utilizes a data-driven approach to estimate the rareness of the trajectories. By combining the rareness estimation of observations with whole trajectories, the proposed method effectively identifies a subset of data that is relatively hard to predict BEFORE feeding them to a specific prediction model. The experimental results show that the mined subset has higher prediction error when applied to different downstream prediction models, which reaches +108.1% error (greater than two times compared to the average on dataset) when mining 5% samples. Further analysis indicates that the mined critical examples include uncommon cases such as sudden brake and cancelled lane-change, which helps to better understand and improve the performance of prediction models.