This repository is the implementation code and video of our two paper as follows:

1) ICK-Track (IROS 2022 oral paper)

ICK-Track: A Category-level 6-DoF Pose Tracker Using Inter-frame Consistent Keypoints for Aerial Manipulation

The work is a collaborative effort between the National Engineering Research Centre for Robot Visual Perception and Control (RVC-NERC) and the Robotics ADVANCe Lab, ST Engineering-NTU Corporate Laboratory.

2) Robust6oF (TPAMI 2025)

Robust6oF: Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker.

We introduce a pose-driven servo paradigm to achieve the aerial vision guidance task for aerial manipulation, which contains a category-level 6-DoF pose tracker and a Pose-Aware Discrete Servo Policy called PAD-Servo to perform real-world vision guidance task. (https://ieeexplore.ieee.org/document/10949865)

Project Video

ICK-Track (Click to see)

Robust6DoF (Click to see)

Citation

If you find the code useful, please cite our paper.

@inproceedings{sun2022ick,
  title={ICK-Track: A Category-Level 6-DoF Pose Tracker Using Inter-Frame Consistent Keypoints for Aerial Manipulation},
  author={Sun, Jingtao and Wang, Yaonan and Feng, Mingtao and Wang, Danwei and Zhao, Jiawen and Stachniss, Cyrill and Chen, Xieyuanli},
  booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={1556--1563},
  year={2022},
  organization={IEEE}
}

@article{sun2025towards,
  title={Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker},
  author={Sun, Jingtao and Wang, Yaonan and Wang, Danwei},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025},
  publisher={IEEE}
}