Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model
This addresses the challenge of improving reliability in autonomous driving systems by focusing on long-tail scenarios, representing an incremental advance through a novel training refinement approach.
The paper tackles the problem of rarely observed long-tail scenarios in trajectory prediction for autonomous driving by proposing GALTraj, a generative active learning method that identifies and augments rare tail samples with a controllable diffusion model, resulting in significant performance boosts on tail samples and enhanced accuracy on head samples across multiple datasets and backbones.
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.