Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.12679 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910657784315904 |
|---|---|
| author | Evangelisti, Francesco Rossi, Francesco Giani, Tobia Bloise, Ilaria Varile, Mattia |
| author_facet | Evangelisti, Francesco Rossi, Francesco Giani, Tobia Bloise, Ilaria Varile, Mattia |
| contents | Accurate satellite pose estimation is crucial for autonomous guidance, navigation, and control (GNC) systems in in-orbit servicing (IOS) missions. This paper explores the impact of different tasks within a multi-task learning (MTL) framework for satellite pose estimation using monocular images. By integrating tasks such as direct pose estimation, keypoint prediction, object localization, and segmentation into a single network, the study aims to evaluate the reciprocal influence between tasks by testing different multi-task configurations thanks to the modularity of the convolutional neural network (CNN) used in this work. The trends of mutual bias between the analyzed tasks are found by employing different weighting strategies to further test the robustness of the findings. A synthetic dataset was developed to train and test the MTL network. Results indicate that direct pose estimation and heatmap-based pose estimation positively influence each other in general, while both the bounding box and segmentation tasks do not provide significant contributions and tend to degrade the overall estimation accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12679 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Multi-Task Learning for Accurate Spacecraft Pose Estimation Evangelisti, Francesco Rossi, Francesco Giani, Tobia Bloise, Ilaria Varile, Mattia Machine Learning Accurate satellite pose estimation is crucial for autonomous guidance, navigation, and control (GNC) systems in in-orbit servicing (IOS) missions. This paper explores the impact of different tasks within a multi-task learning (MTL) framework for satellite pose estimation using monocular images. By integrating tasks such as direct pose estimation, keypoint prediction, object localization, and segmentation into a single network, the study aims to evaluate the reciprocal influence between tasks by testing different multi-task configurations thanks to the modularity of the convolutional neural network (CNN) used in this work. The trends of mutual bias between the analyzed tasks are found by employing different weighting strategies to further test the robustness of the findings. A synthetic dataset was developed to train and test the MTL network. Results indicate that direct pose estimation and heatmap-based pose estimation positively influence each other in general, while both the bounding box and segmentation tasks do not provide significant contributions and tend to degrade the overall estimation accuracy. |
| title | Optimizing Multi-Task Learning for Accurate Spacecraft Pose Estimation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.12679 |