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
Insect-inspired flapping wing robots: autonomous flight control systems. This project aims to design a novel control scheme for insect-inspired, flapping-wing, micro aerial vehicles. This type of micro aerial vehicle has complex, periodic, time-varying and inherently unstable dynamics, which are practically challenging to model and implement in hardware. This project will design energy-based automatic stabilization and task-dependent control, and develop the insect-inspired platform for testing ....Insect-inspired flapping wing robots: autonomous flight control systems. This project aims to design a novel control scheme for insect-inspired, flapping-wing, micro aerial vehicles. This type of micro aerial vehicle has complex, periodic, time-varying and inherently unstable dynamics, which are practically challenging to model and implement in hardware. This project will design energy-based automatic stabilization and task-dependent control, and develop the insect-inspired platform for testing nonlinear control strategies. The expected outcomes will include new system and control theories, concepts, principles and technologies in controller design that can provide reliable flight control for bio-inspired, flapping-wing systems.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
Controlling coastlines while generating power. The Project aims to produce strategies for protecting coasts from storms using farms of wave-energy machines, which also generate electricity. Increasing lengths of coast need protection as the climate changes, but conventional barriers create permanent environmental impacts and are a sunk cost usually borne by the taxpayer. The Project expects to derive a strategy for the setting of each machine in the farm, so that they collectively absorb or refl ....Controlling coastlines while generating power. The Project aims to produce strategies for protecting coasts from storms using farms of wave-energy machines, which also generate electricity. Increasing lengths of coast need protection as the climate changes, but conventional barriers create permanent environmental impacts and are a sunk cost usually borne by the taxpayer. The Project expects to derive a strategy for the setting of each machine in the farm, so that they collectively absorb or reflect damaging waves under severe conditions. Under normal conditions, enough wave energy to sustain environmental processes would pass through. Sales of electricity would help to pay back the capital cost. Outcomes would include reduced coastal-erosion costs and a low-intermittency energy supply.Read moreRead less
A Novel Inline High-Efficiency Motor/Pump System. Around 19% of the world’s and 30% of the Australia’s electric energy is consumed by pump technologies. Significant energy savings are possible if the major components of pump systems, including inverter, motor and pump, operate at their maximum possible efficiency under varying loads. A novel pump design in this project accommodates integrated electronics in a submersible housing. A seal-less design helps mitigate several aspects of pump failure ....A Novel Inline High-Efficiency Motor/Pump System. Around 19% of the world’s and 30% of the Australia’s electric energy is consumed by pump technologies. Significant energy savings are possible if the major components of pump systems, including inverter, motor and pump, operate at their maximum possible efficiency under varying loads. A novel pump design in this project accommodates integrated electronics in a submersible housing. A seal-less design helps mitigate several aspects of pump failure and its in-line structure reduces assembly cost. Accurately measured efficiency maps will be utilised to demonstrate the non-linear relationship between motor and pump quantities as well as developing models for indirectly estimating feedback quantities and achieving the highest system efficiency.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