AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction
This work addresses a critical safety problem for autonomous driving by improving forward region perception in HD map construction, representing a novel method rather than an incremental improvement.
The paper tackles the safety flaw in online HD map construction by addressing the 'spatially backward-looking' nature of existing methods, which fail to improve perception in unseen forward regions critical for autonomous driving. The proposed AMap framework uses a 'distill-from-future' paradigm to enhance current-frame perception, outperforming state-of-the-art temporal models in forward regions while maintaining single-frame inference efficiency.
Online High-Definition (HD) map construction is pivotal for autonomous driving. While recent approaches leverage historical temporal fusion to improve performance, we identify a critical safety flaw in this paradigm: it is inherently ``spatially backward-looking." These methods predominantly enhance map reconstruction in traversed areas, offering minimal improvement for the unseen road ahead. Crucially, our analysis of downstream planning tasks reveals a severe asymmetry: while rearward perception errors are often tolerable, inaccuracies in the forward region directly precipitate hazardous driving maneuvers. To bridge this safety gap, we propose AMap, a novel framework for Ahead-aware online HD Mapping. We pioneer a ``distill-from-future" paradigm, where a teacher model with privileged access to future temporal contexts guides a lightweight student model restricted to the current frame. This process implicitly compresses prospective knowledge into the student model, endowing it with ``look-ahead" capabilities at zero inference-time cost. Technically, we introduce a Multi-Level BEV Distillation strategy with spatial masking and an Asymmetric Query Adaptation module to effectively transfer future-aware representations to the student's static queries. Extensive experiments on the nuScenes and Argoverse 2 benchmark demonstrate that AMap significantly enhances current-frame perception. Most notably, it outperforms state-of-the-art temporal models in critical forward regions while maintaining the efficiency of single current frame inference.