Search papers, labs, and topics across Lattice.
This paper introduces a Progressive Retrospective Framework (PRF) to improve trajectory prediction from variable-length, incomplete observations, a common challenge in autonomous driving. PRF uses a cascade of retrospective units, each with a Retrospective Distillation Module (RDM) to distill features and a Retrospective Prediction Module (RPM) to recover previous timesteps. Combined with a Rolling-Start Training Strategy (RSTS) for data efficiency, PRF achieves state-of-the-art performance on Argoverse 2 and Argoverse 1 datasets, demonstrating its effectiveness and plug-and-play nature.
Incomplete trajectory data got you down? This plug-and-play framework progressively aligns features from incomplete observations with complete ones, boosting prediction accuracy in autonomous driving scenarios.
Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often yields variable-length, incomplete observations, posing a challenge to these methods. A common strategy is to directly map features from incomplete observations to those from complete ones. This one-shot mapping, however, struggles to learn accurate representations for short trajectories due to significant information gaps. To address this issue, we propose a Progressive Retrospective Framework (PRF), which gradually aligns features from incomplete observations with those from complete ones via a cascade of retrospective units. Each unit consists of a Retrospective Distillation Module (RDM) and a Retrospective Prediction Module (RPM), where RDM distills features and RPM recovers previous timesteps using the distilled features. Moreover, we propose a Rolling-Start Training Strategy (RSTS) that enhances data efficiency during PRF training. PRF is plug-and-play with existing methods. Extensive experiments on datasets Argoverse 2 and Argoverse 1 demonstrate the effectiveness of PRF. Code is available at https://github.com/zhouhao94/PRF.
