SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehicles

TL;DR

SAIL introduces a comprehensive framework that improves long-tail trajectory prediction for autonomous vehicles by modeling key attributes and employing adaptive contrastive learning, significantly reducing errors in rare, critical scenarios.

Contribution

The paper presents a novel attribute-guided augmentation and adaptive contrastive learning approach specifically designed to address long-tail prediction challenges in autonomous vehicle scenarios.

Findings

Up to 28.8% reduction in prediction error on the hardest 1% of long-tail samples.

Superior performance on nuScenes and ETH/UCY datasets compared to state-of-the-art methods.

Effective modeling of trajectories across error, collision risk, and complexity attributes.

Abstract

Autonomous vehicles (AVs) rely on accurate trajectory prediction for safe navigation in diverse traffic environments, yet existing models struggle with long-tail scenarios-rare but safety-critical events characterized by abrupt maneuvers, high collision risks, and complex interactions. These challenges stem from data imbalance, inadequate definitions of long-tail trajectories, and suboptimal learning strategies that prioritize common behaviors over infrequent ones. To address this, we propose SAIL, a novel framework that systematically tackles the long-tail problem by first defining and modeling trajectories across three key attribute dimensions: prediction error, collision risk, and state complexity. Our approach then synergizes an attribute-guided augmentation and feature extraction process with a highly adaptive contrastive learning strategy. This strategy employs a continuous cosine momentum schedule, similarity-weighted hard-negative mining, and a dynamic pseudo-labeling mechanism based on evolving feature clustering. Furthermore, it incorporates a focusing mechanism to intensify learning on hard-positive samples within each identified class. This comprehensive design enables SAIL to excel at identifying and forecasting diverse and challenging long-tail events. Extensive evaluations on the nuScenes and ETH/UCY datasets demonstrate SAIL's superior performance, achieving up to 28.8% reduction in prediction error on the hardest 1% of long-tail samples compared to state-of-the-art baselines, while maintaining competitive accuracy across all scenarios. This framework advances reliable AV trajectory prediction in real-world, mixed-autonomy settings.