Air Series Articles Released

Air Series is a collection of articles that are first authored by junior researchers.

This series focuses on a wide variety of topics in robot perception.

Air Series Articles I

[1]

AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration.

Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer.

European Conference on Computer Vision (ECCV), 2022.

@inproceedings{li2021airdet,
  title = {{AirDet}: Few-Shot Detection without Fine-tuning for Autonomous Exploration},
  author = {Li, Bowen and Wang, Chen and Reddy, Pranay and Kim, Seungchan and Scherer, Sebastian},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2022},
  url = {https://arxiv.org/pdf/2112.01740},
  code = {https://github.com/sair-lab/AirDet},
  video = {https://youtu.be/n87XtKUjVbE}
}

[2]

AirObject: A Temporally Evolving Graph Embedding for Object Identification.

Nikhil Varma Keetha, Chen Wang, Yuheng Qiu, Kuan Xu, Sebastian Scherer.

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

@inproceedings{keetha2021airobject,
  title = {{AirObject}: A Temporally Evolving Graph Embedding for Object Identification},
  author = {Keetha, Nikhil Varma and Wang, Chen and Qiu, Yuheng and Xu, Kuan and Scherer, Sebastian},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
  url = {https://arxiv.org/pdf/2111.15150},
  video = {https://youtu.be/WZgn7hMZXhI},
  code = {https://github.com/sair-lab/AirObject}
}

[3]

AirLoop: Lifelong Loop Closure Detection.

Dasong Gao, Chen Wang, Sebastian Scherer.

International Conference on Robotics and Automation (ICRA), 2022.

@inproceedings{gao2021lifelong,
  title = {{AirLoop}: Lifelong Loop Closure Detection},
  author = {Gao, Dasong and Wang, Chen and Scherer, Sebastian},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  year = {2022},
  url = {https://arxiv.org/pdf/2109.08975},
  code = {https://github.com/sair-lab/AirLoop},
  video = {https://youtu.be/7uYAizKyGgE}
}

[4]

AirDOS: Dynamic SLAM benefits from Articulated Objects.

Yuheng Qiu, Chen Wang, Wenshan Wang, Mina Henein, Sebastian Scherer.

International Conference on Robotics and Automation (ICRA), 2022.

@inproceedings{qiu2021airdos,
  title = {{AirDOS}: Dynamic SLAM benefits from Articulated Objects},
  author = {Qiu, Yuheng and Wang, Chen and Wang, Wenshan and Henein, Mina and Scherer, Sebastian},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  year = {2022},
  url = {https://arxiv.org/pdf/2109.09903},
  code = {https://github.com/sair-lab/airdos},
  video = {https://youtu.be/O1mNIHcfnC0}
}

[5]

AirCode: A Robust Object Encoding Method.

Kuan Xu, Chen Wang, Chao Chen, Wei Wu, Sebastian Scherer.

IEEE Robotics and Automation Letters (RA-L), 2022.

Accepted to ICRA 2022

@article{xu2021aircode,
  title = {{AirCode}: A Robust Object Encoding Method},
  author = {Xu, Kuan and Wang, Chen and Chen, Chao and Wu, Wei and Scherer, Sebastian},
  journal = {IEEE Robotics and Automation Letters (RA-L)},
  year = {2022},
  url = {https://arxiv.org/pdf/2105.00327},
  code = {https://github.com/sair-lab/AirCode},
  video = {https://youtu.be/TsdfSVz7hks},
  addinfo = {Accepted to ICRA 2022}
}

Air Series Articles II (To release)

[1]

AirVO: An Illumination-Robust Point-Line Visual Odometry.

Kuan Xu, Yuefan Hao, Shenghai Yuan, Chen Wang, Lihua Xie.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.

SAIR Lab Recommended

@inproceedings{xu2023airvo,
  title = {{AirVO}: An Illumination-Robust Point-Line Visual Odometry},
  author = {Xu, Kuan and Hao, Yuefan and Yuan, Shenghai and Wang, Chen and Xie, Lihua},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2023},
  url = {https://arxiv.org/pdf/2212.07595.pdf},
  code = {https://github.com/sair-lab/AirVO},
  video = {https://youtu.be/YfOCLll_PfU},
  addendum = {SAIR Lab Recommended}
}

[2]

AirLine: Efficient Learnable Line Detection with Local Edge Voting.

Xiao Lin, Chen Wang.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.

@inproceedings{lin2023airline,
  title = {{AirLine}: Efficient Learnable Line Detection with Local Edge Voting},
  author = {Lin, Xiao and Wang, Chen},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2023},
  url = {https://arxiv.org/pdf/2303.16500.pdf},
  video = {https://youtu.be/EKDx3Z9qYUQ},
  code = {https://github.com/sair-lab/AirLine}
}

[3]

AirIMU: Learning Uncertainty Propagation for Inertial Odometry.

Yuheng Qiu, Chen Wang, Xunfei Zhou, Youjie Xia, Sebastian Scherer.

arXiv preprint arXiv:2310.04874, 2023.

@article{qiu2023airimu,
  title = {{AirIMU}: Learning Uncertainty Propagation for Inertial Odometry},
  author = {Qiu, Yuheng and Wang, Chen and Zhou, Xunfei and Xia, Youjie and Scherer, Sebastian},
  journal = {arXiv preprint arXiv:2310.04874},
  year = {2023},
  url = {https://arxiv.org/pdf/2310.04874.pdf},
  code = {https://pypose.org/tutorials/imu/imu_integrator_tutorial}
}

[4]

AirLoc: Object-based Indoor Relocalization.

Aryan, Bowen Li, Sebastian Scherer, Yun-Jou Lin, Chen Wang.

arXiv preprint arXiv:2304.00954, 2023.

@article{aryan2023airloc,
  title = {{AirLoc}: Object-based Indoor Relocalization},
  author = {Aryan and Li, Bowen and Scherer, Sebastian and Lin, Yun-Jou and Wang, Chen},
  journal = {arXiv preprint arXiv:2304.00954},
  year = {2023},
  url = {https://arxiv.org/pdf/2304.00954},
  video = {https://youtu.be/n6mp6KzGPgs},
  code = {https://github.com/sair-lab/AirLoc}
}

First Author Information (When work was done)

Bowen Li
- Junior student at Tongji University, China.
- Now: PhD student of CMU RI.
Nikhil Varma Keetha
- Junior student at Indian Institute of Technology Dhanbad.
- Now: Master student of CMU RI.
Dasong Gao
- Master student at Carnegie Mellon University.
- Now: PhD student of MIT EECS.
Yuheng Qiu
- Undergraduate of Chinese University of Hong Kong.
- Now: PhD student of CMU ME.
Kuan Xu
- Master Graduate of Harbin Institute of Technology, China.
- Now: PhD student of NTU EEE.
Xiao Lin
- Freshman at Georgia Institute of Technology.
- Now: Sophomore at Georgia Institute of Technology.
Aryan
- Junior student at Delhi Technological University.
- Now: Master student of CMU RI.

Contribution

AirDet: Few-shot Detection without Fine-tunning
- The first practical few-shot object detection method that requires no fine-tunning.
- It achieves even better results than the exhaustively fine-tuned methods (up to 60% improvements).
- Validated on real world sequences from DARPA Subterranean (SubT) challenge.

Only three examples are given for novel object detection without fine-tunning.

AirObject: Temporal Object Embedding
- The first temporal object embedding method.
- It achieves the state-of-the-art performance for video object identification.
- Robust to severe occlusion, perceptual aliasing, viewpoint shift, deformation, and scale transform.
- Project Page: https://sairlab.org/airobject

AirDOS: Dynamic Object-aware SLAM (DOS) system
- The first DOS system showing that camera pose estimation can be improved by incorporating dynamic articulated objects.
- Establish 4-D dynamic object maps.
- Project Page: https://sairlab.org/airdos

Dynamic Objects can correct the camera pose estimation.

AirLoop: Lifelong Learning for Robots
- The first lifelong learning method for loop closure detection.
- Model incremental improvement even after deployment.
- Project Page: https://sairlab.org/airloop

The model is able to correct previously made mistakes after learning more environments.

AirCode: Robust Object Encoding
- The first deep point-based object encoding for single image.
- It achieves the state-of-the-art performance for object re-identification.
- Robust to viewpoint shift, object deformation, and scale transform.
- Project Page: https://sairlab.org/aircode

More information can be found at the research page.