AI 中文总结
针对自动驾驶时序记忆易失效的问题，提出 MomADv2 框架，含选择性记忆查询模块与流匹配残差修正器，在多数据集上使碰撞率降 15.6%。
AI 中文摘要
长 horizon 规划对于复杂场景下的安全自动驾驶至关重要。现有方法通过时序记忆提升规划连续性，但当驾驶指令变化时，此类记忆可能失效并误导决策。因此，选择性利用有用历史信息、抑制与指令不一致的记忆仍是关键挑战。为解决该问题，我们提出 MomADv2，一种面向长 horizon 端到端自动驾驶的可靠状态空间记忆框架。MomADv2 的核心是引入选择性状态空间规划记忆查询模块，该模块基于时序连续性和指令一致性筛选历史规划查询，选择与当前指令相关的规划模式，并通过选择性状态空间机制建模规划意图的演化。为进一步缓解长 horizon 规划中的局部轨迹偏差和误差累积，我们设计了流匹配轨迹残差修正器，它从修正后的规划输出中学习到专家轨迹的连续残差修正场，在保留基于锚点规划稳定性的同时实现细粒度轨迹修正。在闭环 NAVSIM 和 Bench2Drive，以及开环 nuScenes 上开展的大量实验表明，在 6 秒规划条件下，MomADv2 相比 MomAD 提升了长 horizon 规划一致性，并将平均碰撞率降低了 15.6%。
英文摘要
Long-horizon planning is critical for safe autonomous driving in complex scenarios. Existing methods improve planning continuity with temporal memory, but such memory may become invalid and mislead decisions when the driving command changes. Thus, selectively leveraging useful history while suppressing command-inconsistent memory remains a key challenge. To address this issue, we propose MomADv2, a reliable state-space memory framework for long-horizon end-to-end autonomous driving. At its core, MomADv2 introduces a Selective State-Space Planning Memory Query Module, which filters historical planning queries based on temporal continuity and command consistency, selects planning modes relevant to the current command, and models the evolution of planning intentions through a selective state-space mechanism. To further alleviate local trajectory deviations and error accumulation in long-horizon planning, we design a Flow-Matching Trajectory Residual Refiner. It learns a continuous residual correction field from the refined planning output to the expert trajectory, enabling fine-grained trajectory refinement while preserving the stability of anchor-based planning. Extensive experiments on closed-loop NAVSIM and Bench2Drive, as well as open-loop nuScenes, demonstrate that MomADv2 improves long-horizon planning consistency and reduces the average collision rate by 15.6% over MomAD under 6-second planning.
Comments16 pages, 6 figures
