Current opportunities
Please note: submitting an Expression of Interest does not guarantee a scholarship, but it is a necessary first step in the application process.
DISCOVER AVAILABLE PROJECTS
- Project
- Industry Partner
- University
This project aims to enhance the safety of autonomous robots by utilizing point cloud and image segmentation to prevent them from accidentally falling into ditches or gaps in their environment. This project will develop software and algorithms that can identify negative spaces (such as ditches, holes, or gaps) using point cloud and visual data and enable robots to make real-time navigation decisions to avoid them.
This research project aims to investigate and develop algorithms and decision-making mechanisms that enable autonomous robots to distinguish between solid damage-causing objects (such as rocks) and traversable obstacles (such as bushes or other vegetation). The primary goal is to enhance the robots’ ability to make informed navigation decisions when encountering obstacles, ultimately improving their safety and efficiency. The robot will use its on-board sensors and processing power to make these decisions in real-time.
Visual Guidance for Ship Launch and Recovery of Unmanned Aerial Vehicles
Geodrones Australia
UNSW Canberra
Current systems for landing UAVs on ships tend to be GPS or radar based and do not use passive sensing. This project aims to develop a visual guidance solution for maritime launch and recovery of UAVs which is not reliant on specialist hardware on the ship and is resilient to failed or degraded GPS. Moreover, this project will target small vessels that otherwise would not have a UAV capability owing to the lack of infrastructure that can be installed and the significant ship motion caused by operations in anything but calm seas. This will enable UAV support of operations from small uncrewed vessels as well as larger crewed vessels.
The project will investigate the best way to achieve a visually guided approach and landing on to the moving deck of a maritime vessel. It will compare classical machine vision and deep learning approaches to tracking the ship and deck markings with consideration of fusing other sensor modalities such as LiDAR. Use of ship motion prediction via machine learning will also be explored to decide the best time to conduct launch and recovery and to enhance the smoothness of the landing trajectory.
Swarms of UAVs are an effective means with which to achieve an objective requiring greater redundancy or greater area coverage than can be provided with a single UAV. However, controlling a large number of UAVs becomes problematic for the operator and places great strain on communication networks. State of the art drone shows are a good example of using large numbers of small drones to great effect but rely on preplanning the trajectories of all the drones before flight to ensure zero collisions and are also reliant on augmented GPS positioning systems to ensure drones fly precise trajectories that do not conflict with one another. This approach does not work in environments having a military context which might be highly dynamic or largely unknown prior to launch and will also not work in GPS degraded environments.
This project aims to solve these limitations by developing neural network architectures capable of outputting control actions which enable a UAV to emulate the sophisticated flocking behaviour of birds. Whilst existing approaches require relative position and velocity of neighbouring UAVs as input, we propose to replace this explicit state information using the raw camera feed from each UAV. The outcomes will contribute to the advancement of communication-free flocking behaviour and pave the way for the adoption of vision-based swarm control in real UAV systems.
Autonomous Data-Driven Modelling for Advanced Satellite Constellation Management
Nominal Systems
UNSW Canberra
The research project aims to revolutionise the management of satellite constellations by investigating methods to automate the creation of data-driven models of satellite systems based on real telemetry data to make it easy for operators to realise the true digital twins of their remote assets. This technology will simplify and secure satellite operations, enabling them to scale effectively. The project offers a unique blend of practical application and theoretical exploration in the rapidly evolving space industry.
Multistatic and Bistatic Localisation of Underwater Targets
Saab Australia
University of Adelaide
Bi-static and Multi-static localisation use time differences of arrival between multiple receivers to localise objects being tracked by active sonar. The aim of this project is to develop a multi-static deinterleaver algorithm that consistently assigns detection events to real-world tracks, in order to execute bi-static and multi-static geometric calculations. Solving this problem is expect to require a combination of tracker development, statistical methods, machine learning and hardware-accelerated brute-force computation.
Multistatic active localisation will contribute to the anti-submarine warfare capability of RAN surface combatants, particularly in the face of rapidly decreasing submarine noise levels that may soon make passive acoustic surveillance less effective.
Target Motion Analysis (TMA) is the process of estimating the two-dimensional location of a moving platform, using a temporal sequence of one-dimensional (bearing) observations from a moving sensor. Doppler (range-rate) information may also be available. TMA is used for passive acoustic surveillance and is therefore a core function in anti-submarine warfare, whether conducted by submarines or surface combatants. TMA solutions are inherently ambiguous under an assumption of straight-line movement, therefore manoeuvre is used by the sensor operator to resolve ambiguities, and by the tracked target to mislead TMA processes being conducted by adversaries.
Optimization of Superconducting Devices by Mean of Quantum Field Theories
Silanna
University of Adelaide
Leaning on the zero resistance properties of superconductors materials, superconducting technology has garnered considerable theoretical and practical interest, with applications spanning the areas of quantum computing, ultra-high precision sensing and quantum metrology. The key phenomenon underpinning these sectors is the Josephson effect, which is the ability for quantum tunnelling super-current to flow between two superconducting electrodes. This effect has been exploited to construct Superconducting Quantum Interference Devices (SQUIDs), which can be used as state-of-the-art sensors of electromagnetic (EM) signal.
More recently, several new kinds of SQUID devices have demonstrated a great potential for Defence/medical applications such as, for example, the task of capturing and analysing signals used for communications. So far, circuit models have been used to model the performances of these devices, however these are somehow limited. Hence, by using new effective field theories for superconductivity such as the phenomenological Ginzburg-Landau formalism or the non-equilibrium statistical mechanic’s approaches, this project will develop and implement a new class of microscopic models. This in turn can be used to validate the behaviour of more complicated devices.
- Academic Supervisor: Dr. Giuseppe Tettamanzi
- Email: giuseppe.tettamanzi@adelaide.edu.au
- Offered for: Doctor of Philosophy (PhD), Master of Philosophy (MPhil)
- Relevant discipline areas: Mathematics, Computational Physics, Electromagnetic Mechanics, Quantum Mechanics, Physics, Materials Engineering, Chemical Engineering
Space Domain Awareness Object Characterisation
Silentium Defence
University of Adelaide
Over the past several decades, near earth orbits have become increasingly congested as the number of space borne applications grow. There are strong national security and commercial imperatives to develop capabilities for obtaining situational awareness in space. Radar is a mature sensing techniques that can be used in the space domain. Passive radars exploit emitters of opportunity, such as terrestrial broadcasts, to provide the transmitted signals. The subsequent low probability of discovery is particularly attractive for surveillance. However, the lack of control over transmit waveform raises technical challenges for detection and classification. This project will explore novel signal processing approaches to address these challenges. Silentium Defence’s passive radar infrastructure is capable of capturing vast quantities of real data, which will serve as a critical ingredient in the research.
Development of Broadband Electronic Warfare Sensors for Signal Detection and Direction Finding
SRC Aus
University of Adelaide
In military terms, electronic support (ES) is the branch of electronic warfare (EW) related to the collection and analysis of electromagnetic signals in the environment to identify and inform decision makers/users for situational awareness.
The aim of this project is to develop a novel airborne ES sensor capable of operating in a complex congested Radio Frequency (RF) environment. The sensor will consist of a broadband antenna array, RF front end and digital backend. The candidate(s) will develop novel antenna designs with Direction Finding (DF) functionality, integrating the designs to build a complete sensor device. They will also be exposed to cutting edge algorithms for emitter DF, and signal parameterisation and characterisation.