ARC Centre of Excellence - Vision Science. This Centre will generate important new knowledge of the performance, logic and stability of vision and visual behaviour. This knowledge will help reduce the burden of vision impairment in Australia, increasing productivity, promoting healthy ageing and reducing the community costs of visual impairment (ca. $9.85 billion in 2004). The knowledge produced will also make possible world-class innovations in robotics, leading to novel automated vision system ....ARC Centre of Excellence - Vision Science. This Centre will generate important new knowledge of the performance, logic and stability of vision and visual behaviour. This knowledge will help reduce the burden of vision impairment in Australia, increasing productivity, promoting healthy ageing and reducing the community costs of visual impairment (ca. $9.85 billion in 2004). The knowledge produced will also make possible world-class innovations in robotics, leading to novel automated vision systems with applications in industry and national security. Other knowledge will develop novel diagnostic technologies, for application in health delivery.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE160100090
Funder
Australian Research Council
Funding Amount
$250,000.00
Summary
Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object ....Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object recognition in images, speech recognition and automatic translation, bringing the prospect of machine intelligence closer than ever. Modern machine learning techniques have had huge impact in the last decade in fields such as robotics, computer vision and data analytics. The facility would enable Australian researchers to develop, learn and apply deep networks to problems of national importance in robotic vision and big data analytics. Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE130100203
Funder
Australian Research Council
Funding Amount
$385,000.00
Summary
Autonomous benthic observing system. This project seeks to improve our ability to monitor marine habitats and characterise their variability by enhancing the Integrated Marine Observing system (IMOS) Autonomous Underwater Vehicle (AUV) Facility. The new AUV infrastructure will reduce operating costs, increase robustness of the sampling effort and insure continued operation for the next decade.
Biomechanics Meets Robotics: Methods for Accurate and Fast Needle Targeting. This project intends to create a novel integrated framework for biomedical systems that can accurately target a needle. Accurate surgical targeting means less trauma and better patient outcomes. Needles are used in over half of all surgical procedures, but up to 38 per cent of these are affected by targeting errors. Achieving sub-millimetre accuracy is extremely difficult because inserting a needle displaces the tissue ....Biomechanics Meets Robotics: Methods for Accurate and Fast Needle Targeting. This project intends to create a novel integrated framework for biomedical systems that can accurately target a needle. Accurate surgical targeting means less trauma and better patient outcomes. Needles are used in over half of all surgical procedures, but up to 38 per cent of these are affected by targeting errors. Achieving sub-millimetre accuracy is extremely difficult because inserting a needle displaces the tissue and moves the target. How, then, can ultra-fine targeting be achieved? This project plans to integrate non-linear biomechanical models that predict tissue motion with accurate and principled motion control. It seeks to create new methods for surgical robots that will predict target motion and guide a needle to accurately intersect the target.Read moreRead less