Abstract. The shift towards commercially driven space utilisation argues for space systems that are cost effective. Embracing a high degree of autonomy is necessary to improve the scalability and reusability of space missions. Robotic perception has been identified as an important component in the autonomy stack of future autonomous spacecraft. As conventional mission development principles are increasingly being eschewed to encourage leaner and fasters development cycles, the issue of safety and reliability naturally crops up. This talk discusses the challenges to safe and reliable application of robotic perception in space, in the context of the new space utilisation paradigm. While significant strides have been made towards robotic perception for autonomous systems on Earth, a different set of difficulties affect robotic perception in space-based platforms. Current progress towards addresses some of these challenges will also be presented.

Bio. Tat-Jun Chin is Professorial Chair of Sentient Satellites at The University of Adelaide. Tat-Jun Chin received his PhD in Computer Systems Engineering from Monash University in 2007, which was supported by the Endeavour Australia-Asia Award, and a Bachelor in Mechatronics Engineering from Universiti Teknologi Malaysia in 2004, where we won the Vice Chancellor's Award. He currently holds the SmartSat CRC Professorial Chair of Sentient Satellites at The University of Adelaide. He is also the Director of Machine Learning for Space at The Australian Institute for Machine Learning. Tat-Jun's research interest lies in optimisation for computer vision and machine learning, and their application to robotic vision, space and smart cities. He has published more than 100 research articles on the subject, and has won several awards for his research, including a CVPR award (2015), a BMVC award (2018), Best of ECCV (2018), two DST Awards (2015, 2017) and IAPR Award (2019).