Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previous ....Active Visual Navigation in an Unexplored Environment. This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previously unseen environments, and the ability to control such agents with more human-like instructions. Such capabilities are desirable, and in some cases essential, for autonomous robots in a variety of important application areas including automated warehousing and high-level control of autonomous vehicles. 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
ARC Centre of Excellence for Robotic Vision. Robots are vital to Australia's future prosperity in the face of high relative wages, low or decreasing productivity, and impending labour shortages. However the work and workplaces of our most important industries are unstructured and changeable and current robots are challenged by their inability to quickly, safely and reliably "see" and "understand" what is around them. The Centre's research will create the fundamental science and technologies th ....ARC Centre of Excellence for Robotic Vision. Robots are vital to Australia's future prosperity in the face of high relative wages, low or decreasing productivity, and impending labour shortages. However the work and workplaces of our most important industries are unstructured and changeable and current robots are challenged by their inability to quickly, safely and reliably "see" and "understand" what is around them. The Centre's research will create the fundamental science and technologies that will allow robots to see as we do, and overcome the last barrier to the ubiquitous deployment of robots into society for the benefit of all.Read moreRead less
Detection and viability of waterborne pathogens using a gut-on-chip. This project aims to resolve a significant problem for water utilities. Microbial pathogens Cryptosporidium, norovirus and adenovirus are the main public health concern for drinking water in developed nations. Water monitoring is limited by the lack of fast, reliable detection methods and viability assays for these pathogens. This project will use a novel gut-on-a-chip to develop for the first time rapid infectivity assays for ....Detection and viability of waterborne pathogens using a gut-on-chip. This project aims to resolve a significant problem for water utilities. Microbial pathogens Cryptosporidium, norovirus and adenovirus are the main public health concern for drinking water in developed nations. Water monitoring is limited by the lack of fast, reliable detection methods and viability assays for these pathogens. This project will use a novel gut-on-a-chip to develop for the first time rapid infectivity assays for Cryptosporidium, norovirus and adenovirus. Significant benefits include improved diagnostics and water disinfection assays, improved water treatment and reduced costs with global impact.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE200100175
Funder
Australian Research Council
Funding Amount
$475,000.00
Summary
A high-payload, high-fidelity haptically-enabled motion simulation facility. An Australian-first motion simulation facility consisting of a high-payload, high-fidelity Stewart platform mounted on a dual-axis linear track is proposed. The facility will allow high acceleration and high vibration manoeuvres, and large displacements through an eight-degrees-of-freedom range of motion. It can carry the entire control compartment of a heavy vehicle, a truck, an ambulance, a train, or a multi-operator ....A high-payload, high-fidelity haptically-enabled motion simulation facility. An Australian-first motion simulation facility consisting of a high-payload, high-fidelity Stewart platform mounted on a dual-axis linear track is proposed. The facility will allow high acceleration and high vibration manoeuvres, and large displacements through an eight-degrees-of-freedom range of motion. It can carry the entire control compartment of a heavy vehicle, a truck, an ambulance, a train, or a multi-operator cockpit of a mining vehicle for simulation. The outcome will provide significant benefits for virtual vehicle prototyping and testing, driver training and behaviour modelling, motion perception and motion sickness research; therefore advancing Australia as the global leader in motion simulation and vehicular technologies.Read moreRead less
Mid-Career Industry Fellowships - Grant ID: IM230100042
Funder
Australian Research Council
Funding Amount
$980,358.00
Summary
Unlocking the full reproductive potential for hybrid wheat breeding. Globally, wheat is cultivated as an inbred self-fertile crop with yield gains stagnating over the last decades. This contrasts with unabated yield gains and yield stability achieved for rice and corn through hybrid breeding and cross-pollination. Wheat hybrids hold potential for a 10-22% yield boost, but commercial deployment is restricted due to high seed production costs, a result of wheat’s floral architecture and poor outcr ....Unlocking the full reproductive potential for hybrid wheat breeding. Globally, wheat is cultivated as an inbred self-fertile crop with yield gains stagnating over the last decades. This contrasts with unabated yield gains and yield stability achieved for rice and corn through hybrid breeding and cross-pollination. Wheat hybrids hold potential for a 10-22% yield boost, but commercial deployment is restricted due to high seed production costs, a result of wheat’s floral architecture and poor outcrossing characteristics. This project aims to reduce costs by improving wheat’s female receptivity to airborne pollen, a major bottleneck to commercial realization of hybrids globally. Higher and more stable yields from wheat hybrids will ensure food security in the face of climate uncertainty and growing population.Read moreRead less
Lizard social networks and the spread of parasites. Australian ecosystems are continually threatened by new epidemics of diseases and parasites, some local, others from overseas. Examples include the facial tumours of Tasmanian devils and the fungus that threatens many native frog species. To manage these epidemics effectively, we must understand how they spread through animal populations. This project will help to protect our fauna from invasive diseases. It contributes to sustaining the biodiv ....Lizard social networks and the spread of parasites. Australian ecosystems are continually threatened by new epidemics of diseases and parasites, some local, others from overseas. Examples include the facial tumours of Tasmanian devils and the fungus that threatens many native frog species. To manage these epidemics effectively, we must understand how they spread through animal populations. This project will help to protect our fauna from invasive diseases. It contributes to sustaining the biodiversity of the country. With better knowledge of how diseases of wildlife spread, we can develop more effective control of those diseases thereby protecting wildlife species, animal populations and, ultimately, Australian ecosystems.Read moreRead less
The study and development of a 3D real-time stockpile management system. By successfully completing this project, the efficiency of existing infrastructure investments in industries involved in bulk material handling (inclusive of minerals, grain, sugar and woodchips) will be largely improved. This will allow such industries to contain costs and thus increase international competitiveness. Efficiencies gains (in these industries) to date have been in recover and processing with little attention ....The study and development of a 3D real-time stockpile management system. By successfully completing this project, the efficiency of existing infrastructure investments in industries involved in bulk material handling (inclusive of minerals, grain, sugar and woodchips) will be largely improved. This will allow such industries to contain costs and thus increase international competitiveness. Efficiencies gains (in these industries) to date have been in recover and processing with little attention to stockyard and movement within the stockyards. The industries sectors in which will receive the greatest benefits are in rural and remote Australia. There is also the ability of the system to be exported to overseas clients, particularly in the mining sector.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE150100079
Funder
Australian Research Council
Funding Amount
$320,000.00
Summary
A haptic-based immersive motion platform for human performance evaluation. A haptic-based immersive motion platform for human performance evaluation: This project aims to establish a motion platform capable of combining continuous centrifugal rotation and large linear displacement with an additional five degrees of motion. The system will house a human subject at the end of a large serial robot similar to a human arm, which can rotate continuously about its base. The robot arm will be installed ....A haptic-based immersive motion platform for human performance evaluation. A haptic-based immersive motion platform for human performance evaluation: This project aims to establish a motion platform capable of combining continuous centrifugal rotation and large linear displacement with an additional five degrees of motion. The system will house a human subject at the end of a large serial robot similar to a human arm, which can rotate continuously about its base. The robot arm will be installed on a large linear axis enabling the simulation of movements and accelerations along a straight path as well as rotation provided by other axes of the robot. The motion platform will comprise audio and visual devices, and haptic-based control mechanisms, for example a steering wheel and pedals or a helicopter cyclic, to provide a number of human immersed scenarios for driving/flying training and human perception evaluation.Read moreRead less