外观
论文arXiv 2610.2221513 天前
FutureLift：将轨迹提案提升为双向未来图用于运动预测
原文链接：FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting（arXiv 2610.22215 · 发布日期：2026-10-15）
FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting
FutureLift将多模态轨迹提案表示为异构未来图，对自动驾驶运动预测候选进行残差细化，并在Argoverse2和WOMD验证。
核心要点
- 强运动预测器的多模态提案仍有残差，现有细化器难以利用完整未来关系上下文。
- 方法把每个提案建成异构未来图，连接历史、地图、模式及其他智能体未来轨迹。
- 双向时间边让后续证据一次性修正早期片段，节点输出坐标残差和置信度校正。
- 在Argoverse2和Waymo Open Motion Dataset上，持续改进冻结提案并优于原生和专用细化器。
验证范围与局限：验证范围为Argoverse2和Waymo Open Motion Dataset上的边缘与联合运动预测。
英文摘要 (Abstract)
Accurate motion prediction is critical for safe autonomous driving, yet even strong forecasters leave residual errors in their multimodal proposals. Existing refiners compress complete proposals or update their segments sequentially, preventing the full proposed future from serving as explicit relational context for correction. We introduce FutureLift, a backbone-agnostic refiner that represents each multimodal proposal as a heterogeneous future graph, with spatially grounded temporal nodes connected to agent histories, map elements, alternative modes, and, for joint prediction, other agents future trajectories. Bidirectional temporal edges allow later evidence to revise earlier segments in a single pass, and the updated nodes predict residual coordinate and confidence corrections. Requiring only proposals, scores, and scene context, FutureLift provides a common refinement interface for structurally different forecasting backbones. On Argoverse2 and the Waymo Open Motion Dataset, it consistently improves frozen proposals and outperforms native and specialized refiners across marginal and joint forecasting. On the WOMD motion-prediction leaderboard, FutureLift ranks first in minADE (0.5049m) and minFDE (0.9942m) among the compared standard-input methods, without LiDAR or ensembling, while achieving a competitive 0.4874 Soft mAP.
作者：Daniel Grimm, J. Marius Zöllner
来源
本页事实对应的公开页面，以原文为准。