LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints
This work addresses the problem of accurate trajectory prediction for autonomous vehicles, particularly in complex scenes like intersections, though it appears incremental as it builds on existing two-stage and attention-based methods.
The paper tackles trajectory prediction for autonomous driving by introducing LAformer, a two-stage model that uses lane-aware scene constraints and motion refinement to improve accuracy at intersections, achieving excellent performance on Argoverse 1 and nuScenes datasets.
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.