Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.05355 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914174398889984 |
|---|---|
| author | Huang, Tzu-Yuan Lederer, Armin Wu, Dai-Jie Dai, Xiaobing Zhang, Sihua Sosnowski, Stefan Sun, Shao-Hua Hirche, Sandra |
| author_facet | Huang, Tzu-Yuan Lederer, Armin Wu, Dai-Jie Dai, Xiaobing Zhang, Sihua Sosnowski, Stefan Sun, Shao-Hua Hirche, Sandra |
| contents | Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning Huang, Tzu-Yuan Lederer, Armin Wu, Dai-Jie Dai, Xiaobing Zhang, Sihua Sosnowski, Stefan Sun, Shao-Hua Hirche, Sandra Machine Learning Robotics Systems and Control Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction. |
| title | SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning |
| topic | Machine Learning Robotics Systems and Control |
| url | https://arxiv.org/abs/2511.05355 |