Fly0: Decoupling Semantic Grounding from Geometric Planning for Zero-Shot Aerial Navigation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910025421684736 |
|---|---|
| author | Xu, Zhenxing Lu, Brikit Bao, Weidong Zhu, Zhengqiu Zhang, Junsong Yan, Hui Lu, Wenhao Wang, Ji |
| author_facet | Xu, Zhenxing Lu, Brikit Bao, Weidong Zhu, Zhengqiu Zhang, Junsong Yan, Hui Lu, Wenhao Wang, Ji |
| contents | Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers leads to high latency, trajectory oscillations, and poor generalization due to weak geometric grounding. To address these limitations, we propose Fly0, a framework that decouples semantic reasoning from geometric planning. The proposed method operates through a three-stage pipeline: (1) an MLLM-driven module for grounding natural language instructions into 2D pixel coordinates; (2) a geometric projection module that utilizes depth data to localize targets in 3D space; and (3) a geometric planner that generates collision-free trajectories. This mechanism enables robust navigation even when visual contact is lost. By eliminating the need for continuous inference, Fly0 reduces computational overhead and improves system stability. Extensive experiments in simulation and real-world environments demonstrate that Fly0 outperforms state-of-the-art baselines, improving the Success Rate by over 20\% and reducing Navigation Error (NE) by approximately 50\% in unstructured environments. Our code is available at https://github.com/xuzhenxing1/Fly0. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15875 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fly0: Decoupling Semantic Grounding from Geometric Planning for Zero-Shot Aerial Navigation Xu, Zhenxing Lu, Brikit Bao, Weidong Zhu, Zhengqiu Zhang, Junsong Yan, Hui Lu, Wenhao Wang, Ji Robotics Artificial Intelligence Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers leads to high latency, trajectory oscillations, and poor generalization due to weak geometric grounding. To address these limitations, we propose Fly0, a framework that decouples semantic reasoning from geometric planning. The proposed method operates through a three-stage pipeline: (1) an MLLM-driven module for grounding natural language instructions into 2D pixel coordinates; (2) a geometric projection module that utilizes depth data to localize targets in 3D space; and (3) a geometric planner that generates collision-free trajectories. This mechanism enables robust navigation even when visual contact is lost. By eliminating the need for continuous inference, Fly0 reduces computational overhead and improves system stability. Extensive experiments in simulation and real-world environments demonstrate that Fly0 outperforms state-of-the-art baselines, improving the Success Rate by over 20\% and reducing Navigation Error (NE) by approximately 50\% in unstructured environments. Our code is available at https://github.com/xuzhenxing1/Fly0. |
| title | Fly0: Decoupling Semantic Grounding from Geometric Planning for Zero-Shot Aerial Navigation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.15875 |