Risk-Informed Diffusion Transformer for Long-Tail Trajectory Prediction in the Crash Scenario

TL;DR

This paper introduces RI-DiT, a risk-informed diffusion transformer that improves long-tail trajectory prediction in crash scenarios by integrating risk data and traffic flow features, enhancing autonomous driving safety.

Contribution

The paper proposes a novel risk-informed diffusion transformer model that leverages crash scenario data and risk features to better predict rare, critical trajectories in autonomous driving.

Findings

Achieves low minADE of 0.016 m for top 10% tail data.

Effectively models long-tail trajectories with less smoothness in crash scenarios.

Demonstrates improved safety and prediction accuracy in real-world crash data.

Abstract

Trajectory prediction methods have been widely applied in autonomous driving technologies. Although the overall performance accuracy of trajectory prediction is relatively high, the lack of trajectory data in critical scenarios in the training data leads to the long-tail phenomenon. Normally, the trajectories of the tail data are more critical and more difficult to predict and may include rare scenarios such as crashes. To solve this problem, we extracted the trajectory data from real-world crash scenarios, which contain more long-tail data. Meanwhile, based on the trajectory data in this scenario, we integrated graph-based risk information and diffusion with transformer and proposed the Risk-Informed Diffusion Transformer (RI-DiT) trajectory prediction method. Extensive experiments were conducted on trajectory data in the real-world crash scenario, and the results show that the algorithm we proposed has good performance. When predicting the data of the tail 10\% (Top 10\%), the minADE and minFDE indicators are 0.016/2.667 m. At the same time, we showed the trajectory conditions of different long-tail distributions. The distribution of trajectory data is closer to the tail, the less smooth the trajectory is. Through the trajectory data in real-world crash scenarios, Our work expands the methods to overcome the long-tail challenges in trajectory prediction. Our method, RI-DiT, integrates inverse time to collision (ITTC) and the feature of traffic flow, which can predict long-tail trajectories more accurately and improve the safety of autonomous driving systems.