Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.18215 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915634516852736 |
|---|---|
| author | Yuan, Shangyuan Fairchild, Preston Mei, Yu Zhou, Xinyu Tan, Xiaobo |
| author_facet | Yuan, Shangyuan Fairchild, Preston Mei, Yu Zhou, Xinyu Tan, Xiaobo |
| contents | Accurate shape reconstruction is essential for precise control and reliable operation of soft robots. Compared to sensor-based approaches, vision-based methods offer advantages in cost, simplicity, and ease of deployment. However, existing vision-based methods often rely on complex camera setups, specific backgrounds, or large-scale training datasets, limiting their practicality in real-world scenarios. In this work, we propose a vision-based, markerless, and training-free framework for soft robot shape reconstruction that directly leverages the robot's natural surface appearance. These surface features act as implicit visual markers, enabling a hierarchical matching strategy that decouples local partition alignment from global kinematic optimization. Requiring only an initial 3D reconstruction and kinematic alignment, our method achieves real-time shape tracking across diverse environments while maintaining robustness to occlusions and variations in camera viewpoints. Experimental validation on a continuum soft robot demonstrates an average tip error of 2.6% during real-time operation, as well as stable performance in practical closed-loop control tasks. These results highlight the potential of the proposed approach for reliable, low-cost deployment in dynamic real-world settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18215 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AFT: Appearance-Based Feature Tracking for Markerless and Training-Free Shape Reconstruction of Soft Robots Yuan, Shangyuan Fairchild, Preston Mei, Yu Zhou, Xinyu Tan, Xiaobo Robotics Accurate shape reconstruction is essential for precise control and reliable operation of soft robots. Compared to sensor-based approaches, vision-based methods offer advantages in cost, simplicity, and ease of deployment. However, existing vision-based methods often rely on complex camera setups, specific backgrounds, or large-scale training datasets, limiting their practicality in real-world scenarios. In this work, we propose a vision-based, markerless, and training-free framework for soft robot shape reconstruction that directly leverages the robot's natural surface appearance. These surface features act as implicit visual markers, enabling a hierarchical matching strategy that decouples local partition alignment from global kinematic optimization. Requiring only an initial 3D reconstruction and kinematic alignment, our method achieves real-time shape tracking across diverse environments while maintaining robustness to occlusions and variations in camera viewpoints. Experimental validation on a continuum soft robot demonstrates an average tip error of 2.6% during real-time operation, as well as stable performance in practical closed-loop control tasks. These results highlight the potential of the proposed approach for reliable, low-cost deployment in dynamic real-world settings. |
| title | AFT: Appearance-Based Feature Tracking for Markerless and Training-Free Shape Reconstruction of Soft Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.18215 |