Human models for accelerated robot learning and human-robot interaction. This project aims to develop novel approaches to teach robots to proficiently interact with humans in a safe and low-cost manner. To achieve this aim, this project will develop novel models from which various human behaviours can be generated and used to train human-robot interaction policies in simulation. Expected outcomes of this project include new computational models of human behaviour built using cognitive science th ....Human models for accelerated robot learning and human-robot interaction. This project aims to develop novel approaches to teach robots to proficiently interact with humans in a safe and low-cost manner. To achieve this aim, this project will develop novel models from which various human behaviours can be generated and used to train human-robot interaction policies in simulation. Expected outcomes of this project include new computational models of human behaviour built using cognitive science theories and limited data and new training schemes for robot learning in simulation. By training robots in simulation with accurate human models, this research will enable fast and safe robot training to support the deployment and adoption of robots in human contexts such as healthcare facilities, homes, and workplaces.Read moreRead less
Congestion control in complex networks with higher-order interactions. Traffic congestion significantly costs the Australian economy and environment. This project aims to develop ground-breaking network models of urban traffic systems to build a new congestion control framework. The purpose of network modelling is to capture the interdependence between different parts of traffic systems, which facilitates studying congestion cascade within the network. The project expects to generate next genera ....Congestion control in complex networks with higher-order interactions. Traffic congestion significantly costs the Australian economy and environment. This project aims to develop ground-breaking network models of urban traffic systems to build a new congestion control framework. The purpose of network modelling is to capture the interdependence between different parts of traffic systems, which facilitates studying congestion cascade within the network. The project expects to generate next generation of network models for more effective congestion control. Expected outcomes include novel congestion control technologies that adjust traffic signals in real-time to optimally utilise the available road space. This should provide significant economic and environmental benefits to Australians by easing traffic jams.Read moreRead less
An explainability oriented approach to manage dependent supply chain risks. This project aims to help supply chain companies model the impact on their operations by capturing the uncertainties impacting their upstream suppliers. In the current uncertain business environment, the project's outcome will benefit service-based industries to have an enhanced understanding of their operating environment and take decisions accordingly to avoid failures. This will significantly increase the productivity ....An explainability oriented approach to manage dependent supply chain risks. This project aims to help supply chain companies model the impact on their operations by capturing the uncertainties impacting their upstream suppliers. In the current uncertain business environment, the project's outcome will benefit service-based industries to have an enhanced understanding of their operating environment and take decisions accordingly to avoid failures. This will significantly increase the productivity of Australian service-based industries across different domains. The expected outcome is that it generates new knowledge by which risk managers of a focal company can conjointly consider risk identification/assessment with risk management analysis to develop explainable strategies for managing uncertainties. Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100149
Funder
Australian Research Council
Funding Amount
$462,044.00
Summary
Adaptive and Efficient Robot Positioning Through Model and Task Fusion. This project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. The project expects to contribute to the knowledge across robotics, computer vision, and neuromorphic computing. Expected outcomes of this project include ground-breaking place recognition techniques that address two fundamental limitations in the state-of-the-art: continuous adaptation, critically im ....Adaptive and Efficient Robot Positioning Through Model and Task Fusion. This project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. The project expects to contribute to the knowledge across robotics, computer vision, and neuromorphic computing. Expected outcomes of this project include ground-breaking place recognition techniques that address two fundamental limitations in the state-of-the-art: continuous adaptation, critically important in safety-critical systems, and energy efficiency, critically important in resource-constrained systems. This should provide significant benefits, such as accelerated deployment of mobile robots, drones and augmented reality solutions in manufacturing, defence, healthcare, household, and space.Read moreRead less
Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowled ....Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowledge and an approach to fast-adapt bilevel optimization solutions when required computing resources change. The anticipated outcomes should significantly improve the reliability of ML with benefits for safety learning and computing resource optimisation in ML-based data analytics.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101281
Funder
Australian Research Council
Funding Amount
$329,278.00
Summary
An Efficient Computational Solver for Complex Engineering Problems. This project aims to address significant gaps in the existing knowledge about solving complex engineering problems that involve conflicting objectives and unquantifiable features. In these problems, the decision-maker is interested in knowing high-quality and dissimilar solutions that determine the trade-off between the problem objectives. The intended outcomes of this project include a novel robust computational solver that can ....An Efficient Computational Solver for Complex Engineering Problems. This project aims to address significant gaps in the existing knowledge about solving complex engineering problems that involve conflicting objectives and unquantifiable features. In these problems, the decision-maker is interested in knowing high-quality and dissimilar solutions that determine the trade-off between the problem objectives. The intended outcomes of this project include a novel robust computational solver that can automatically find such solutions. The decision-makers can then choose the final solution based on their expertise and preferences. This expects to offer significant benefits to diverse engineering disciplines by finding superior and more practical solutions to their complex multidisciplinary problems.Read moreRead less
Intelligent Robotics for Pharmaceutical Formulation Development. This project aims to transform the labour and time-intensive process of drug formulation development by optimising the process workflow, through collaboration between biochemists and the proposed intelligent and scalable robotic system. This project expects to enable the robot to leverage the expert knowledge of the biochemists while automating rote tasks. The expected outcome of this project is an intelligent robot that can collab ....Intelligent Robotics for Pharmaceutical Formulation Development. This project aims to transform the labour and time-intensive process of drug formulation development by optimising the process workflow, through collaboration between biochemists and the proposed intelligent and scalable robotic system. This project expects to enable the robot to leverage the expert knowledge of the biochemists while automating rote tasks. The expected outcome of this project is an intelligent robot that can collaborate with human coworkers to accelerate drug formulation. This should provide significant benefits by lowering drug costs and the development time of new drugs. Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100761
Funder
Australian Research Council
Funding Amount
$430,504.00
Summary
Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a ....Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a tool to highlight biases with recommendations for diverse sets of news articles. By raising awareness to biased news reporting, the project will benefit Australians through more balanced public discourse on global challenges, such as climate change and health pandemics.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240101049
Funder
Australian Research Council
Funding Amount
$432,485.00
Summary
Modeling the Diffusion of Evolving Rumours in Social Networks. This project aims to model the complex evolution and diffusion process of evolving rumours in social media. This project expects to develop new theories and associated techniques from operational research (adaptive genetic algorithms), mathematics (network theory), and machine learning (generative adversarial networks) to tackle the challenges in this project. This project aims to develop (1) novel models for the evolution of a rumou ....Modeling the Diffusion of Evolving Rumours in Social Networks. This project aims to model the complex evolution and diffusion process of evolving rumours in social media. This project expects to develop new theories and associated techniques from operational research (adaptive genetic algorithms), mathematics (network theory), and machine learning (generative adversarial networks) to tackle the challenges in this project. This project aims to develop (1) novel models for the evolution of a rumour, (2) novel models for the diffusion of an evolving rumour, and (3) techniques for detecting the diffusion sources of the original rumour and its mutations. This not only will constitute a major advancement in the theory and application of rumour study but also lead the decision-makers in debunking rumours.Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less