LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints

TL;DR

LAformer is a novel trajectory prediction method for autonomous driving that leverages lane-aware scene constraints and a two-stage process to improve accuracy at complex intersections.

Contribution

It introduces a lane-aware estimation module and a two-stage prediction framework, enhancing scene understanding and temporal consistency in trajectory prediction.

Findings

Outperforms existing methods on Argoverse 1 and nuScenes datasets.

Effectively filters relevant lane segments to improve prediction accuracy.

Utilizes a two-stage process for better temporal consistency.

Abstract

Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on one-stage trajectory prediction models, which condition future trajectories on observed trajectories combined with fused scene information. However, they often struggle with complex scene constraints, such as those encountered at intersections. To this end, we present a novel method, called LAformer. It uses a temporally dense lane-aware estimation module to select only the top highly potential lane segments in an HD map, which effectively and continuously aligns motion dynamics with scene information, reducing the representation requirements for the subsequent attention-based decoder by filtering out irrelevant lane segments. Additionally, unlike one-stage prediction models, LAformer utilizes predictions from the first stage as anchor trajectories and adds a second-stage motion refinement module to further explore temporal consistency across the complete time horizon. Extensive experiments on Argoverse 1 and nuScenes demonstrate that LAformer achieves excellent performance for multimodal trajectory prediction.