Student topics

AI that is pre-programmed is limited in its tasks and human bias. Learning systems offer richer decision-making behaviors where collaborative projects have led to the following three systems that require integration:A symbolic learning system that can continually learn Boolean classification problems as they are presented to it. But this needs to be extended to real-valued, noisy and uncertain classification problems.A lateralized system that can consider an input at the constituent level and the holistic level simultaneously, which enables flexible and …

Study level

PhD

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

Making a robot understand what it sees is one of the most fascinating goals in our current research. To this end, we develop novel methods for Semantic Mapping and Semantic SLAM by combining object detection with simultaneous localisation and mapping (SLAM) techniques.We work on novel approaches to SLAM that create semantically meaningful maps by combining geometric and semantic information. Such semantically enriched maps will help robots understand our complex world and will ultimately increase the range and sophistication of interactions …

Study level

PhD

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

How can robots best learn to navigate in challenging environments and execute complex tasks, such as tidying up an apartment or assist humans in their everyday domestic chores?Often, hand-written architectures are based on complicated state machines that become intractable to design and maintain with growing task complexity. I am interested in developing learning-based approaches that are effective and efficient and scale better to complicated tasks.Especially learning based on semantic information (such as extracted by the research in semantic SLAM above), …

Study level

PhD

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

In recent years the field of robotic navigation has increasingly harnessed semantic information in order to facilitate the planning and execution of robotic tasks. The use of semantic information focuses on employing representations more understandable by humans to accomplish tasks with robustness against environmental change, limiting memory requirements and improving scalability. Contemporary computer vision algorithms extracting semantic information have continuously improved their performance on benchmark datasets, however, most computations are expensive, limiting their use for robotic platforms constrained by size, …

Study level

PhD

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

One of the remaining challenges to achieve off-road autonomous navigation for mobile robots is the accurate evaluation of vegetated environments, to determine where a robot can safely drive through. To achieve this, robots may use extra sensory modalities compared to humans, such as RADARs that can penetrate through vegetation and see behind it what is not visible to the naked eye. Another option is to physically interact with the environment to 'clear the way'.

Study level

PhD

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

Sub-Antarctic islands have unique ecosystems and landscapes under increasingly pressure from climate change. In many cases this is compounded by the introduction of invasive species since their discovery by humans in the 1800s.Understanding ecosystem and environmental responses to climate change and separating them from human-induced causes of change is essential for their future protection. To do this requires quantifying long-term, natural rates and variability of change, establishing the ‘baseline’ status of ecosystems and the environment prior to human arrival, and …

Study level

PhD

Faculty

Faculty of Science

School

School of Biology and Environmental Science

Research centre(s)

Centre for the Environment

Microfluidic devices are increasingly relied upon to address the complexity of in-vitro disease models that are intended to mimic and provide insight into in-vivo processes and reactions to novel therapies and in turn, can become powerful companion diagnostic devices essential for predicting and individual patient’s reaction to a particular treatment. However, as these microfluidic devices become more and more prominent and necessary for addressing the drug screening and disease modeling needs of the industry, we have observed a lack in …

Study level

PhD, Master of Philosophy

Faculty

Faculty of Engineering

School

School of Mechanical, Medical and Process Engineering

Research centre(s)

Centre for Biomedical Technologies

This project seeks to leverage recent advances in machine vision and natural language processing algorithms to support the design and development of knowledge-driven applications that support communication and collaborations with their users.One particular area where this will be investigated is in workplaces for supported employment, that is employment opportunities for people with intellectual disability. One of the questions to address is how machines could respond to what a user shows them in order to assist with decision making in a …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Computer Science

Outliers are anomalous observations in a data set that are "outside the norm" of what would be expected. Identifying outliers is an important part of exploratory data analysis and data analysis in general. It is often a challenging problem and calls for advanced methods and approaches, including machine learning-based tools. As methods become more and more complex, their explainability becomes more difficult and more important. This research project will look at all aspects of explainability and explore new approaches and …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre(s)

Centre for Data Science

There is a need for additional studies to monitor on-field performance parameters in female elite athletes (Meignié 2021). We know that wearable sensors can be used to monitor the physiological and biochemical profile of athletes (Seshadri 2019), and a combination of several wearables is going to be more effective for accessing all relevant parameters (Düking 2016). However, there is limited research on the effects of menstrual cycle phases on elite athlete performance (Meignié 2021).This proposed research aims to bridge the …

Study level

PhD

Faculty

Faculty of Creative Industries, Education and Social Justice

School

School of Design

Research centre(s)

Design Lab

Chronic wet cough is among the commonest symptoms of chronic lung disease. In Australia, the most common cause of childhood chronic wet cough is protracted bacterial bronchitis (PBB), a clinical entity we first described. It has now been shown to be a precursor to bronchiectasis, which causes substantial morbidity and mortality, especially from acute respiratory exacerbations. Lung inflammation in children with persistent chronic wet cough is an important driver of ongoing and progressive tissue damage, leading to bronchiectasis, highlighting the …

Study level

PhD

Faculty

Faculty of Health

School

School of Public Health and Social Work

Research centre(s)

Centre for Healthcare Transformation
Australian Centre for Health Services Innovation

Identify the specific competencies and skills that leaders need to effectively lead AI adoption initiatives in organisations. Research can focus on areas such as data literacy, AI literacy, critical thinking, decision-making, and the ability to manage and interpret AI-driven insights. Develop frameworks for assessing and developing these competencies in leaders.

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Information Systems

Research centre(s)

Centre for Behavioural Economics, Society and Technology