Our Research

Type

Research project

Program

Program 2: Advanced Satellite Systems, Sensors and Intelligence

Abstract

This project seeks to automate the identification of higher order patterns in ISR (Intelligence, Surveillance and Reconnaissance) sensed detections along with establishing normalcy. The intention is for significant changes from normalcy – anomalies – to be reported to operators as alerts requiring human assessment, decision, and action. In addition, the rationale of the alerts will also be computed and presented in a transparent way to instil user confidence in the results.

Two novel aspects for this project are: (1) the use of multiple strategies for pattern detection, including deep learning and advanced statistical modelling (e.g., Bayesian Computation); and (2) the incorporation of a Pattern Question Answering (PQA) capability to enable intuitive interaction and interrogation of the reported patterns for their rationale. PQA will build on and generalise existing capabilities in Visual Question Answering (VQA) in the fields of Artificial Intelligence and Machine Learning.

Specific application domains will be considered to support the development and demonstration of capability, including domains such as maritime traffic, space situational patterns, and land use patterns.

Investigators

• Professor Matthew Roughan (Lead), Dr Melissa Humphreys (The University of Adelaide), Dr Giang Nguyen (The University of Adelaide), Dr Jonathan Tuke (The University of Adelaide), Dr Lewis Mitchell (The University of Adelaide), Prof Tat-Jun Chin (The University of Adelaide)
• Brenton Whitington (BAE Systems Australia), Will Heyne (BAE Systems Australia)

Total funding

$440,778

Duration

2021-2023

Type

Research project

Program

Program 2: Advanced Satellite Systems, Sensors and Intelligence

Abstract

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

Investigators

• Prof Tat-Jun Chin (Lead), Assoc Prof Brian Ng  (The University of Adelaide), Prof Michael Webb (The University of Adelaide), Dr Alvaro Parra Bustos (The University of Adelaide)
• Prof Gustavo Batista (UNSW), Prof Claude Sammut (UNSW), Prof Arcot Sowmya (UNSW), Dr Yang Song (UNSW)
• Brenton Whitington (BAE Systems Australia), Will Heyne (BAE Systems Australia)

Total funding

$500,000

Duration

2021-2023

Type

Research project

Program

Program 2: Advanced Satellite Systems, Sensors and Intelligence

Abstract

Precision timing is of vital importance to our modern society. Its most high-profile application is seen in daily use by most of the world’s population though Global Navigation Satellite Systems (e.g. GPS, Galileo), which generates trillions of dollars each year in economic benefits around the globe.

Other applications for precision timing are emerging within satellite constellations where highly accurate satellite position and timing information may be required. Such information is crucial for: intelligent space systems that aim to produce high-resolution monitoring of Earth by combining data from multiple low-resolution sensors, or next-generation GNSS and satellite communication constellations which are more immune to spoofing, offer higher accuracy, and could lead to a sovereign capability for Australia.

This project aims to demonstrate a next generation timing reference for spaced-based applications. The project will focus on design optimisation for small satellites (typically about 1m3, 100-200kg) as well as initiating an understanding of the trade-space between performance and SWaP for satellite clock designs.

Investigators

• Professor Andre Luiten (Lead), Dr Chris Perrella (The University of Adelaide)
• CryoClock Pty Ltd

Total funding

$344,330

Duration

2020-2023

Type

HDR scholarship top-up

Program

Program 1: Advanced Communications, Connectivity & IoT Technologies

Abstract

This project proposes to adopt and investigate the potentials and challenges of employing the PHY layer of the IEEE 802.15.3d Standard for inter/intra-satellite communications over the low terahertz band.

Investigators

• Mohamed Shehata, Withawat Withayachumnankul (The University of Adelaide).
• Ke (Desmond) Wang (RMIT)

Total funding

$45,000

Duration

2021-2023

Type

HDR scholarship

Program

Program 1: Advanced Communications, Connectivity & IoT Technologies

Abstract

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.

Investigators

• Sabrina Slimani, James Quach (The University of Adelaide).
• Samuel Drake (DST Group)

Total funding

$105,000

Duration

2020-2023

Type

Research project

Program

Program 2: Advanced Satellite Systems, Sensors and Intelligence

Abstract

To fulfil mission objectives satisfactorily, many CubeSat-based applications require precise stabilisation of the CubeSat platform during orbit. For example, observing a small distant space object, (re)detecting small targets or fine-grain changes over a large terrain of the Earth’s surface, and establishing long-range communication links. However, in part due to their small size, CubeSats inevitably suffer from jitter during orbit, which prevents a high degree of stability.

This project seeks to research and develop an ultra-fine attitude determination and control system (ADACs) for optical remote sensing (Earth Observation and Space Situational Awareness) and optical communications from small satellite platforms.

Investigators

• Tat-Jun Chin (Lead), Tien-Fu Lu, Nataliia Sergiienko, Michael Webb (University of Adelaide)
• Matthew Tetlow (Inovor Technologies)
• Anders Eriksson (University of Queensland)
• Rober Mahony (Australian National University)

Total funding

$600,000

Duration

2020-2023

Type

Professorial chair

Program

Program 2: Advanced Satellite Systems, Sensors and Intelligence

Abstract

Artificial Intelligence (AI) will transform the way we explore and utilise space. An exciting potential of AI is enabling sentient satellites – these are satellites that are able to develop self-awareness of their environment and other resident space objects, and use that understanding to autonomously complete mission objectives with only high-level human command. Underpinning sentient satellites is machine learning to extract knowledge from sensors and accumulated data.

AI-enabled sentient satellites will create important new commercial applications: satellites that can autonomously rendezvous with a target satellite and perform on-orbit servicing; satellite formations that can cooperatively monitor a target region to maximise intelligence; and satellites that can self-defend by detecting and evading attacks from hostile satellites. While current systems are automated in isolated parts, building sentient satellites requires a comprehensive rethink of satellite engineering and AI technology for space.

The proposed Chair will foster the paradigm shift through a research program on sentient satellites. Fundamental questions will be tackled: how to enable a satellite to reason about its environment, its present state and the states of other satellites, using on-board sensors and algorithms; given understanding of the environment and adversary, how to plan a sequence of actions to achieve the mission objectives. To answer the questions, new AI techniques will be developed, such as deep networks for perception in space and reinforcement learning for flight optimisation.

A key research dimension is to surmount the practical challenges to AI in space, e.g., SWaP constraints and insufficient training data. This will require innovations on multiple fronts of AI and satellite technology, including algorithms, hardware, data and mission planning. The potential of AI to enhance the broader space industry will also be explored. The ambition is to fundamentally disrupt the space industry using AI, much like how self-driving vehicles have disrupted the automotive industry.

Investigator

Tat-Jun Chin (The University of Adelaide)

Total funding

$1.5 Million

Duration

2020-2025