Attend the Vision-based Spacecraft Pose Estimation seminar, Sept. 25
Attend the next School of Computing and Augmented Intelligence seminar hosted by Assistant Professor Hannah Kerner.
Vision-baed Spacecraft Pose Estimation
Presented by Tat-Jun Chin, University of Adelaide
Rendezvous, proximity operations and docking, or RPOD, are space operations that underpin advanced missions such as on orbit servicing and space debris removal. In RPOD operations, two or more spacecraft come into close proximity and interact with each other. Robotic vision has been identified as an important component in the onboard guidance, navigation and control, or GNC, system that enables RPOD to be accomplished safely. In particular, vision-based satellite pose estimation allows a spacecraft to gauge the position and orientation of another spacecraft in proximity, based on image observations.
This talk will provide an overview of research on vision-based satellite pose estimation at the Sentient Satellites Laboratory, University of Adelaide. Topics that will be covered include algorithms for pose estimation, data collection and testing facilities, domain adaptation and novel sensors to deal with challenging space conditions. The difficulty of executing machine learning inference on space-borne computing platforms will also be briefly discussed.
About the speaker
Tat-Jun (TJ) Chin is the Professional Chair of Sentient Satellites at the University of Adelaide. He received his doctorate in computer systems engineering from Monash University in 2007, which was partly supported by the Endeavour Australia-Asia Award, and a bachelor’s degree in mechatronics engineering from Universiti Teknologi Malaysia in 2004, where he won the Vice Chancellor’s Award.
Chin’s research interest lies in optimization for computer vision and machine learning, and their application to intelligent satellites and space robotics. He has published more than 100 research articles on the subject, and has won several awards for his research, including a CVPR award in 2015, a BMVC award in 2018, Best of ECCV in 2018, three DST Awards in 2015, 2017 and 2021, an IAPR Award in 2019 and an RAL Best Paper Award in 2021. He was a finalist in the Academic of the Year Category at the Australian Space Awards 2021.