FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Video
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915502989770752 |
|---|---|
| author | Serpiva, Valerii Lykov, Artem Batool, Faryal Kozlovskiy, Vladislav Cabrera, Miguel Altamirano Tsetserukou, Dzmitry |
| author_facet | Serpiva, Valerii Lykov, Artem Batool, Faryal Kozlovskiy, Vladislav Cabrera, Miguel Altamirano Tsetserukou, Dzmitry |
| contents | We present FlightDiffusion, a diffusion-model-based framework for training autonomous drones from first-person view (FPV) video. Our model generates realistic video sequences from a single frame, enriched with corresponding action spaces to enable reasoning-driven navigation in dynamic environments. Beyond direct policy learning, FlightDiffusion leverages its generative capabilities to synthesize diverse FPV trajectories and state-action pairs, facilitating the creation of large-scale training datasets without the high cost of real-world data collection. Our evaluation demonstrates that the generated trajectories are physically plausible and executable, with a mean position error of 0.25 m (RMSE 0.28 m) and a mean orientation error of 0.19 rad (RMSE 0.24 rad). This approach enables improved policy learning and dataset scalability, leading to superior performance in downstream navigation tasks. Results in simulated environments highlight enhanced robustness, smoother trajectory planning, and adaptability to unseen conditions. An ANOVA revealed no statistically significant difference between performance in simulation and reality (F(1, 16) = 0.394, p = 0.541), with success rates of M = 0.628 (SD = 0.162) and M = 0.617 (SD = 0.177), respectively, indicating strong sim-to-real transfer. The generated datasets provide a valuable resource for future UAV research. This work introduces diffusion-based reasoning as a promising paradigm for unifying navigation, action generation, and data synthesis in aerial robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Video Serpiva, Valerii Lykov, Artem Batool, Faryal Kozlovskiy, Vladislav Cabrera, Miguel Altamirano Tsetserukou, Dzmitry Robotics We present FlightDiffusion, a diffusion-model-based framework for training autonomous drones from first-person view (FPV) video. Our model generates realistic video sequences from a single frame, enriched with corresponding action spaces to enable reasoning-driven navigation in dynamic environments. Beyond direct policy learning, FlightDiffusion leverages its generative capabilities to synthesize diverse FPV trajectories and state-action pairs, facilitating the creation of large-scale training datasets without the high cost of real-world data collection. Our evaluation demonstrates that the generated trajectories are physically plausible and executable, with a mean position error of 0.25 m (RMSE 0.28 m) and a mean orientation error of 0.19 rad (RMSE 0.24 rad). This approach enables improved policy learning and dataset scalability, leading to superior performance in downstream navigation tasks. Results in simulated environments highlight enhanced robustness, smoother trajectory planning, and adaptability to unseen conditions. An ANOVA revealed no statistically significant difference between performance in simulation and reality (F(1, 16) = 0.394, p = 0.541), with success rates of M = 0.628 (SD = 0.162) and M = 0.617 (SD = 0.177), respectively, indicating strong sim-to-real transfer. The generated datasets provide a valuable resource for future UAV research. This work introduces diffusion-based reasoning as a promising paradigm for unifying navigation, action generation, and data synthesis in aerial robotics. |
| title | FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Video |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.14082 |