Real-Time Navigation for Autonomous Aerial Vehicles Using Video
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915224662048768 |
|---|---|
| author | Anjum, Khizar Pandey, Parul Sadhu, Vidyasagar Tron, Roberto Pompili, Dario |
| author_facet | Anjum, Khizar Pandey, Parul Sadhu, Vidyasagar Tron, Roberto Pompili, Dario |
| contents | Most applications in autonomous navigation using mounted cameras rely on the construction and processing of geometric 3D point clouds, which is an expensive process. However, there is another simpler way to make a space navigable quickly: to use semantic information (e.g., traffic signs) to guide the agent. However, detecting and acting on semantic information involves Computer Vision~(CV) algorithms such as object detection, which themselves are demanding for agents such as aerial drones with limited onboard resources. To solve this problem, we introduce a novel Markov Decision Process~(MDP) framework to reduce the workload of these CV approaches. We apply our proposed framework to both feature-based and neural-network-based object-detection tasks, using open-loop and closed-loop simulations as well as hardware-in-the-loop emulations. These holistic tests show significant benefits in energy consumption and speed with only a limited loss in accuracy compared to models based on static features and neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01996 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Navigation for Autonomous Aerial Vehicles Using Video Anjum, Khizar Pandey, Parul Sadhu, Vidyasagar Tron, Roberto Pompili, Dario Robotics Computer Vision and Pattern Recognition Image and Video Processing Most applications in autonomous navigation using mounted cameras rely on the construction and processing of geometric 3D point clouds, which is an expensive process. However, there is another simpler way to make a space navigable quickly: to use semantic information (e.g., traffic signs) to guide the agent. However, detecting and acting on semantic information involves Computer Vision~(CV) algorithms such as object detection, which themselves are demanding for agents such as aerial drones with limited onboard resources. To solve this problem, we introduce a novel Markov Decision Process~(MDP) framework to reduce the workload of these CV approaches. We apply our proposed framework to both feature-based and neural-network-based object-detection tasks, using open-loop and closed-loop simulations as well as hardware-in-the-loop emulations. These holistic tests show significant benefits in energy consumption and speed with only a limited loss in accuracy compared to models based on static features and neural networks. |
| title | Real-Time Navigation for Autonomous Aerial Vehicles Using Video |
| topic | Robotics Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2504.01996 |