NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910007156539392 |
|---|---|
| author | Zhu, Yufei Yang, Shih-Min Rudenko, Andrey Kucner, Tomasz P. Lilienthal, Achim J. Magnusson, Martin |
| author_facet | Zhu, Yufei Yang, Shih-Min Rudenko, Andrey Kucner, Tomasz P. Lilienthal, Achim J. Magnusson, Martin |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14827 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping Zhu, Yufei Yang, Shih-Min Rudenko, Andrey Kucner, Tomasz P. Lilienthal, Achim J. Magnusson, Martin Robotics 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 |
| title | NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.14827 |