Current ISR satellites typically play a passive data collection and dissemination role, with processing typically done further downstream at ground stations. This “offline” processing approach introduces significant delays in converting data to actionable insights, prevents low-latency coordination between end-users (e.g., field operatives) and space-based assets, and precludes more intelligent sensing capabilities; for example, adaptive tasking of the sensor suite based on real-time data enhancement and analytics to improve intelligence gathering.

The project builds upon existing work at BAE Systems and the partner academic institutions (UoA and UNSW) on machine learning for ISR applications. The project will develop novel algorithms and workflows to enable machine learning on nanosatellites for space based ISR from multi-modal sensors. Note that the capacity of current edge computing hardware (e.g., Nvidia Jetson series) is still significantly smaller than standard hardware, thus necessitating algorithms for model pruning and data pre-processing to perform on-board machine learning. Operating in space also presents unique obstacles to updating the pre-trained on-board models, in terms of procuring data and supervisory labels for retraining, and bandwidth constraints in updating models. The project will tackle the above challenges to produce a novel space analytics engine that is reconfigurable after launch, which significantly increases the value proposition of on-board processing.

The product that I aim to produce, as a result of my research, is an enabling technology for next generation high-powered small satellites that has many applications and is very much aligned to SmartSat’s priority research areas in Advanced Communication, Advanced Satellite Systems and Next Generation Earth Observation Data Services.

The technology that I aim to develop will provide thermal management of high-powered small satellite electronics and increase their usability, improving satellite services and connectivity. Given the enabling application of my research to all small satellites, it can be applied to multiple sectors which includes Agriculture, Mining and Resources, Disaster and Emergency Management, Water and Environmental Management.

In concert with the SmartSat’s overarching strategy, the technology developed by my research is aimed to build capacity within the space sector via the: culmination of knowledge translation and creation resulting in a novel way to prevent high powered small satellites from overheating, with the ultimate aim to commercialise a product that will provide capability to the Australian space industry and manufacturing in South Australia.

The aim of this project is to establish the theoretical feasibility of Global Navigation Satellite System (GNSS) reflectometry in detecting objects of interest at sea, and defining performance characteristics associated with this technology.

In the 2010s, Global Space Governance (GSG) became an urgent issue with the growing commercialisation of outer space. Given the technical and operational complexities surrounding such enterprise, rather than adopting the traditional model of treaty making, new thinking was required to address the challenges and opportunities created by this commercialisation. In 2014, the Montreal Declaration on Global Space Governance created a Working Group to make recommendations on the peaceful and sustainable use of outer space. In 2017, the recommendations were published by the Institute and Centre of Air and Space Law at McGill University. This international study identified safety and technical gaps in the existing governance regime.

While the McGill study identifies gaps in existing space governance, it does not provide specific recommendations on how different types of technology should be regulated by the space sector. One of these technologies is Artificial Intelligence (AI). The use of AI in the space sector is both a challenge and an opportunity. Challenges include protecting the rights of all stakeholders in the harvesting of data sourced from outer space operations. Opportunities include the ability to provide control systems that enhance traffic safety in outer space.

There is therefore a need to extend existing GSGs to AI applications.

This project aims to create a field-validated AI governance framework for the Australian space sector.

Neumann Space is developing an electric propulsion system that uses plasma from a solid conductive cathode as the propellant source.

Efficient propellant utilisation requires efficient cathode erosion, where the cathode spots erode the cathode working face to produce an azimuthally smooth pattern, while keeping the working face as close to perpendicular to the thrust vector as possible.

This project shall determine the cathode spot motion, and associated erosion pattern, of the arc discharge across a range of parameters, which shall help to inform future design choices.

To allow high-resolution image capture of fast-moving objects from an orbiting camera, this project seeks to integrate a wide-field-of-view (wide-fov) conventional optical imaging sensor with a telescopic camera. Data from the wide-fov conventional optical imaging camera can be used to trigger the telescopic camera to get high resolution images of the target objects, even when there is some uncertainty around where exactly the fast-moving object will be at a given time. The process also helps reduce the bandwidth requirements for space-based sensors.

Fast-moving objects of interest include hypersonic systems, including weapons systems, as well as orbiting systems. This has applications for defence, SDA and in-orbit inspection domains.

The project will seek to develop a prototype hardware system as well as a preliminary concept-of-operations to enable the camera to perform as required.