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
Air Series Articles II (To release)
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.

-
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

-
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

-
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.