Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model

TL;DR

This paper introduces GALTraj, a novel active learning approach that uses a controllable diffusion model to generate diverse, realistic long-tail trajectory scenarios, improving autonomous driving predictions without changing model architecture.

Contribution

GALTraj is the first method to integrate generative active learning with controllable diffusion models for long-tail trajectory prediction, enhancing data diversity and model performance.

Findings

Significant improvement in tail sample prediction accuracy.

Enhanced overall trajectory prediction performance.

Effective augmentation of rare scenarios with realistic trajectories.

Abstract

While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures, such as using hypernetworks. In contrast, we propose refining the training process to unlock each model's potential without altering its structure. We introduce Generative Active Learning for Trajectory prediction (GALTraj), the first method to successfully deploy generative active learning into trajectory prediction. It actively identifies rare tail samples where the model fails and augments these samples with a controllable diffusion model during training. In our framework, generating scenarios that are diverse, realistic, and preserve tail-case characteristics is paramount. Accordingly, we design a tail-aware generation method that applies tailored diffusion guidance to generate trajectories that both capture rare behaviors and respect traffic rules. Unlike prior simulation methods focused solely on scenario diversity, GALTraj is the first to show how simulator-driven augmentation benefits long-tail learning in trajectory prediction. Experiments on multiple trajectory datasets (WOMD, Argoverse2) with popular backbones (QCNet, MTR) confirm that our method significantly boosts performance on tail samples and also enhances accuracy on head samples.