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
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
Co-design and dynamic mission optimisation of hypersonic flight vehicles. This project aims to deliver fundamental knowledge by integrating the modelling and control with the design of next generation hypersonic platforms. In an era where Australia's national security reliance on geographic isolation and support from allied forces are being challenged, the research outcomes of this project will play an important role in understanding the capabilities of hypersonic systems. The project will also ....Co-design and dynamic mission optimisation of hypersonic flight vehicles. This project aims to deliver fundamental knowledge by integrating the modelling and control with the design of next generation hypersonic platforms. In an era where Australia's national security reliance on geographic isolation and support from allied forces are being challenged, the research outcomes of this project will play an important role in understanding the capabilities of hypersonic systems. The project will also have significant spillover benefits into other complex system domains, where computational tools can be used to aid in design leading to high embedded-IP products for Australian industry. Furthermore, the proposal encompasses a strong research training aspect, with graduates exposed to leading edge industry and academia.Read moreRead less
Network-wide sewer odour and corrosion management by model predictive control. Network-wide sewer odour and corrosion management by model predictive control. This project aims to develop and demonstrate, through real-life field studies, a model predictive control approach that achieves cost-effective network-wide mitigation of hydrogen sulphide. The lack of suitable methodologies to support the control designs of chemical dosing units and sewage pumping stations makes network-wide sewer corrosio ....Network-wide sewer odour and corrosion management by model predictive control. Network-wide sewer odour and corrosion management by model predictive control. This project aims to develop and demonstrate, through real-life field studies, a model predictive control approach that achieves cost-effective network-wide mitigation of hydrogen sulphide. The lack of suitable methodologies to support the control designs of chemical dosing units and sewage pumping stations makes network-wide sewer corrosion and odour management a problem. Innovative control methodology will simultaneously manipulate chemical dosing unit(s) and selected sewage pumping station(s), based on real-time prediction of sewage flows and characteristics both at sources and across the network, to ensure optimal delivery of dosed chemicals to mitigate hydrogen sulphide.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE170100066
Funder
Australian Research Council
Funding Amount
$350,000.00
Summary
Collaborative embodied movement design network. This project aims to create a national collaborative network of arts/technology researchers to study the creative potential of movement-based human computer interaction systems. Movement-based technologies such as augmented and virtual reality, haptic and robotic interfaces form the cutting edge of human computer interaction development. This project will develop new infrastructure to enable researchers to work together to improve these systems fro ....Collaborative embodied movement design network. This project aims to create a national collaborative network of arts/technology researchers to study the creative potential of movement-based human computer interaction systems. Movement-based technologies such as augmented and virtual reality, haptic and robotic interfaces form the cutting edge of human computer interaction development. This project will develop new infrastructure to enable researchers to work together to improve these systems from an embodied perspective. This is expected to benefit industry, commerce, education, health care and the arts.Read moreRead less
Industrial Transformation Training Centres - Grant ID: IC190100017
Funder
Australian Research Council
Funding Amount
$3,703,664.00
Summary
ARC Training Centre for Integrated Operations for Complex Resources. This Training Centre aims to increase value in mining through clever applications of ‘lean processing’ and train the next generation of scientists and engineers in advanced sensors and data analytics in complex resources; knowledge priorities for the mining industry. Sensor information will be linked to the resource’s in-place knowledge to enable data analytics of all embedded knowledge. Processing can then be tuned to resource ....ARC Training Centre for Integrated Operations for Complex Resources. This Training Centre aims to increase value in mining through clever applications of ‘lean processing’ and train the next generation of scientists and engineers in advanced sensors and data analytics in complex resources; knowledge priorities for the mining industry. Sensor information will be linked to the resource’s in-place knowledge to enable data analytics of all embedded knowledge. Processing can then be tuned to resource attributes, maximising value ‘on the fly’. Benefits will include increasing certainty on product quality and maximising throughput and recovery. Outcomes will include new tools to rapidly model geological and geometallurgical uncertainty with sensor inputs, to track the resource to product and enhance interpretation.Read moreRead less