Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehicles

TL;DR

This paper presents a real-time method for detecting out-of-distribution scenes in autonomous vehicle trajectory prediction, enhancing safety by identifying unreliable predictions during inference.

Contribution

It introduces a change-point detection framework for OOD detection in trajectory prediction, effective even in deceptive OOD scenarios, with lightweight solutions suitable for real-time use.

Findings

Effective OOD detection in real-time scenarios

Handles deceptive OOD scenes that are hard to detect visually

Demonstrated on multiple real-world datasets

Abstract

Accurate trajectory prediction is essential for the safe operation of autonomous vehicles in real-world environments. Even well-trained machine learning models may produce unreliable predictions due to discrepancies between training data and real-world conditions encountered during inference. In particular, the training dataset tends to overrepresent common scenes (e.g., straight lanes) while underrepresenting less frequent ones (e.g., traffic circles). In addition, it often overlooks unpredictable real-world events such as sudden braking or falling objects. To ensure safety, it is critical to detect in real-time when a model's predictions become unreliable. Leveraging the intuition that in-distribution (ID) scenes exhibit error patterns similar to training data, while out-of-distribution (OOD) scenes do not, we introduce a principled, real-time approach for OOD detection by framing it as a change-point detection problem. We address the challenging settings where the OOD scenes are deceptive, meaning that they are not easily detectable by human intuitions. Our lightweight solutions can handle the occurrence of OOD at any time during trajectory prediction inference. Experimental results on multiple real-world datasets using a benchmark trajectory prediction model demonstrate the effectiveness of our methods.