SmartSat is integrating the capabilities from the priority areas set in SmartSat’s Technology Roadmap across three primary research program areas as below.

The ever-increasing number of satellites being launched into space will pose significant challenges in tracing satellites, avoiding collisions in an increasingly crowded space and integrating different technologies and systems.  As satellite technology becomes physically smaller and are deployed in constellations, increased opportunities exist for significant processing and Artificial Intelligence (AI) techniques to be out on-board satellites so that some advanced analytics are carried out on-board satellites to enhance the efficiency and effectiveness of data gathering and analysis.

See projects in Advanced Satellite Systems, Sensors and Intelligence projects below:

Topics include:

  • MBSE & Digital twins of small satellite systems
  • Autonomous, cooperative satellite formations
  • Artificial Immune Systems in satellite swarms
  • Trusted Autonomous Formations
  • Self-healing satellite systems
  • Agile & resilient satellites
  • Satellite system & data security
  • Advanced pointing & maneuvering
  • On-board machine learning modules
  • Advanced adaptable payloads
  • HgCdTelR Optoelectronic sensors
  • Quantum sensors

Assessing and Enhancing Multi-Spacecraft Mission Simulation and Visualisation

Advanced Satellite Systems, Sensors and Intelligence

Astrodynamical simulations provide a crucial input to space mission planning and operations. Interactive visualisation of mission configurations, particularly for multi-spacecraft constellations or formation-flying scenarios, plays an important role in both understanding options and communicating outcomes to a variety of end users or audiences.

This project will investigate current state-of-the-art software for mission simulation and visualisation. This includes an evaluation of a suite of commercial and open-source options, considering both quantitative metrics (performance benchmarks, accuracy of orbital calculations) and qualitative factors (usability, flexibility, licensing costs and platforms for delivery).

The outcomes will comprise improved understanding of the suitability of astrodynamics simulation and visualisation software (shared as a white paper and/or research publication), identification of new opportunities for research and development, and improved understanding of the needs of end users from various SmartSat partners with the goal of advancing Australia’s capabilities in mission simulation, operations, and space situational awareness activities.

P2.39

Project Leader:
Professor Christopher Fluke, Swinburne University of Technology

Participants:

AI Architecture for Onboard Processing

Advanced Satellite Systems, Sensors and Intelligence

A literature/technology review on AI architectures for On-board Processing and related hardware aspects (GPU-based, FPGA, SoC etc).

P2.25

Project Leader:
Professor Clinton Fookes, Queensland University of Technology

Participants:

A Machine Learning Based Solution for Space Situational Awareness and Space Sustainability

Advanced Satellite Systems, Sensors and Intelligence

Currently, space situational awareness (SSA) highly depends on ground-based capabilities limiting the accuracy of tracking objects to 10cm. This project will explore possible technological demonstration that utilizes International Space Station/ CubeSat payload for SSA alongside its efficiency and need for long-term space sustainability. The capability shall be achieved through machine learning as a part of the onboard computer.

P2.16s

Project Leader:
Professor Allison Kealy, Royal Melbourne Institute of Technology (RMIT)

PhD Student:
Sai Vallapureddy, Royal Melbourne Institute of Technology (RMIT)

Participants:

A Decentralised Cognitive System for Radar Signal Recognition

Advanced Satellite Systems, Sensors and Intelligence

This project aims to develop a novel distributed radio frequency processing capability for deployment across space-based platforms. The research will focus on elaborating a machine learning (ML) model that can effectively detect and classify conventional and low-probability-of-intercept (LPI) radar signals. The model will dynamically adapt its structure to the collected signals, producing calibrated confidence estimates and learning from misclassified in-distribution samples. To enhance autonomy and resilience to mission contingencies, the neural network will perform asynchronous, distributed training featuring
interruptible and resumable cycles.

P2.20

Project Leader:
Graham Priestnall, DEWC Systems

Participants:

Using Satellite Data to Locate and Phenotype Plants from Space

Advanced Satellite Systems, Sensors and Intelligence

Satellite imagery provides immense potential for Earth observation applications. By training AI to analyse these images, we can monitor huge areas with minimal effort. However, there are many technical hurdles that need to be overcome to successfully use these images for application areas such as agriculture and ecology. Satellite imagery has much lower spatial resolution than ground-based images, and the higher resolutions satellite images (30cm) must be taken selectively as it is infeasible to capture the whole planet at that resolution. This leads to sporadic images being available for any site with only one image taken every few months, or several on the same day. To train an AI model on these images, we need to construct training sets of ground-based observations associated with positions in satellite images. The ground truth observations are also sporadic, and these combine to make training an AI algorithm on satellite images challenging due a lack of observations that are temporally aligned with images.

This project aims to develop sample efficient AI algorithms which require less ground truth observations to train accurate models. Both semi-supervised and unsupervised training methods will be adopted to train highly effective feature extractors using a minimum of labelled data. Highly successful semi-supervised learning algorithms, and unsupervised/self-supervised methods (which have achieved very high accuracy with just a few labelled examples or no labels at all (respectively) in generic image classification) will be customized and these methods extended for satellite images.

P2.18s

Project Leader:
Associate Professor Zhen He, La Trobe University

PhD Student:
Brandon Victor, La Trobe University

Participants:

Using Quantum Entanglement to Remotely Synchronise Clocks

Advanced Satellite Systems, Sensors and Intelligence

Distant clock synchronisation has many applications including telecommunications, Global Satellite Navigation Systems, emitter localisation, and phased array astronomy. Clock synchronisation requires clocks to tick at the same rate and to read the same time. Two procedures employed to ensure clocks read the same time are the Einstein method and the Eddington method.

The Einstein method involves sending a signal back and forth between two clocks and using the speed of the signal to synchronise the clocks.

The Eddington method involves synchronising the clocks next to each other prior to sending the second clock to its desired location.

Special relativity and general relativity must be accounted for in the Einstein and Eddington methods to ensure that the clocks run at the same rate. Furthermore, the Eddington method relies on the physical movement of a clock and is therefore not practical for space applications. This project will investigate the employment of entangled photon pairs in overcoming the limitations of the Einstein and Eddington methods.

P2.06s

Project Leader:
Dr James Quach, The University of Adelaide

PhD Student:
Sabrina Slimani, The University of Adelaide

Participants: