用神经隐式场建模时空运动模式，更准更顺还省算力。
NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping
- 用隐式神经函数直接映射坐标到高斯混合参数，实现连续时空建模。
- 在两个真实轨迹数据集上精度更高，稀疏区域速度分布更平滑。
- 适合需要高效建模复杂人流的机器人导航与轨迹预测任务。
在复杂人机共存环境中，安全高效的机器人运行依赖于对特定场景运动模式的良好建模。动态地图（MoDs）通过在地图中编码统计运动模式来提供此类建模，但现有方法采用离散空间采样，通常需昂贵的离线构建。本文提出一种基于隐式神经函数的连续时空MoD表示，可直接将坐标映射到半包裹高斯混合模型的参数。该方法无需离散化与不规则区域插值，实现空间与时间上的平滑泛化。在两个包含真实人群轨迹数据的公开数据集上评估显示，相比现有基线，本方法在运动表征精度和稀疏区域速度分布平滑性上均表现更优，同时保持计算效率。所提方法为建模复杂人类运动模式提供了强大且高效的新途径，并在轨迹预测下游任务中展现出高性能。项目代码已开源：https://github.com/test-bai-cpu/nemo-map。
原文摘要 · Abstract (English)
Safe and efficient robot operation in complex human environments can benefit from good models of site-specific motion patterns. Maps of Dynamics (MoDs) provide such models by encoding statistical motion patterns in a map, but existing representations use discrete spatial sampling and typically require costly offline construction. We propose a continuous spatio-temporal MoD representation based on implicit neural functions that directly map coordinates to the parameters of a Semi-Wrapped Gaussian Mixture Model. This removes the need for discretization and imputation for unevenly sampled regions, enabling smooth generalization across both space and time. Evaluated on two public datasets with real-world people tracking data, our method achieves better accuracy of motion representation and smoother velocity distributions in sparse regions while still being computationally efficient, compared to available baselines. The proposed approach demonstrates a powerful and efficient way of modeling complex human motion patterns and high performance in the trajectory prediction downstream task. Project code is available at https://github.com/test-bai-cpu/nemo-map
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。