发表机构
Nanyang Technological University; Beijing Jiaotong University; North University of China; Dalian University of Technology; Tsinghua University（南洋理工大学; 北京交通大学; 中北大学; 大连理工大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MomWorld提出动量感知潜在世界模型，通过提取并传播场景运动趋势，联合预测未来配置与动量，并采用MoFlow流匹配细化轨迹，在6秒规划时域内将平均碰撞率相对MomAD降低12.2%。
AI 中文摘要
长时域规划使自动驾驶车辆能够预测场景演变和潜在风险，从而在复杂交互中支持安全稳定的决策。然而，现有方法难以将观测历史中的运动趋势传播到未来。基于单一潜在状态的长距离展开可能会进一步削弱有用的动态信息，保留过时的运动模式，并干扰可靠的近期规划。我们提出了MomWorld，一种用于长时域规划的动量感知潜在世界模型。MomWorld从历史到当前的观测中提取场景运动趋势，并将潜在动量传播到未来时域，联合预测未来的配置和动量状态。一种可学习的动量保持机制保留稳定趋势，场景条件化的动量更新适应未来动态，而场景自适应重置门在突变情况下抑制过时的动量。我们进一步提出了MoFlow，一种动量条件化的流匹配模块，该模块仅需少量积分步骤即可将基础轨迹细化为与预测的未来场景演变对齐，并通过时域感知的残差融合保留近期规划稳定性，同时允许更强的长距离修正。在NAVSIM、nuScenes和Bench2Drive上的大量实验表明，MomWorld提高了长时域规划的一致性，并在6秒规划时域内相对于MomAD将平均碰撞率降低了12.2%。
英文摘要
Long-horizon planning enables autonomous vehicles to anticipate scene evolution and potential risks, supporting safe and stable decisions in complex interactions. However, existing methods struggle to propagate motion trends from observed history into the future. Long rollouts based on a single latent state may further attenuate useful dynamics, retain stale motion patterns, and disrupt reliable near-term plans. We introduce MomWorld, a momentum-aware latent world model for long-horizon planning. MomWorld extracts scene motion trends from historical-to-current observations and propagates latent momentum into future horizons, jointly predicting future configuration and momentum states. A learnable momentum persistence mechanism preserves stable trends, scene-conditioned momentum updates adapt future dynamics, and a scene-adaptive reset gate suppresses stale momentum under abrupt changes. We further propose MoFlow, a momentum-conditioned flow-matching module that refines a base trajectory to align with the predicted future scene evolution in only a few integration steps, with a horizon-aware residual fusion that preserves near-term planning stability while permitting stronger long-range corrections. Extensive experiments on NAVSIM, nuScenes and Bench2Drive demonstrate that MomWorld improves long-horizon planning consistency and reduces the average collision rate by 12.2% relative to MomAD over a 6-second planning horizon.
