Visual methods for advanced automation of underwater manipulation. This project will increase the autonomy of underwater robotic systems engaged in intervention and inspection tasks. Such activities are essential for the operation of subsea robotic systems used in offshore industries, scientific exploration and defence. Our approach will improve perception and situational awareness through the principled fusion of multiple navigation and camera sensors. We will use this improved scene understand ....Visual methods for advanced automation of underwater manipulation. This project will increase the autonomy of underwater robotic systems engaged in intervention and inspection tasks. Such activities are essential for the operation of subsea robotic systems used in offshore industries, scientific exploration and defence. Our approach will improve perception and situational awareness through the principled fusion of multiple navigation and camera sensors. We will use this improved scene understanding to effectively plan the motion of vehicles and manipulators through larger and more complex workspaces, enabling semi-supervised and autonomous task execution. Our project will demonstrate these capabilities in real-world deployments relevant to industry and marine science.Read moreRead less
Special Research Initiatives - Grant ID: SR0354703
Funder
Australian Research Council
Funding Amount
$20,000.00
Summary
Robotics Research Network (RRN). The RRN brings together all the best robotics research groups in Australia with the aim of fostering and coordinating cooperative research. The RRN integrates researchers from fields including machine perception, sensing, control, artificial intelligence and mechatronics. The RRN includes representation from twelve Universities, CSIRO and involvement of four ARC Centres. Programmes are proposed to share research facilities, to support training of research personn ....Robotics Research Network (RRN). The RRN brings together all the best robotics research groups in Australia with the aim of fostering and coordinating cooperative research. The RRN integrates researchers from fields including machine perception, sensing, control, artificial intelligence and mechatronics. The RRN includes representation from twelve Universities, CSIRO and involvement of four ARC Centres. Programmes are proposed to share research facilities, to support training of research personnel and promote cooperation in international research programmes. Robotics is already having a substantial impact in industries such as mining and agriculture. Robotics will, in future, offer benefits in areas such as health care, building systems, and defence.Read moreRead less
Centre for Autonomous Systems. The aim of the Centre is to research and explore intelligence in autonomous systems. The Centre will undertake fundamental research organised around four themes; perception, control, learning and systems. These themes will interact through two research demonstrators focused around a built environment and a natural outdoor environment. The Centre brings together a critical mass of over 70 staff and research students from three leading research groups. The partners a ....Centre for Autonomous Systems. The aim of the Centre is to research and explore intelligence in autonomous systems. The Centre will undertake fundamental research organised around four themes; perception, control, learning and systems. These themes will interact through two research demonstrators focused around a built environment and a natural outdoor environment. The Centre brings together a critical mass of over 70 staff and research students from three leading research groups. The partners also have substantial track record in the commercial exploitation of autonomous systems. The proposed Centre offers the potential of growing into the world's leading autonomous systems research centre.Read moreRead less
Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques ....Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques that use large amounts of unlabeled data to enhance performance. Our design takes advantage of additional information available for marine imagery such as geolocation and remote sensing context. We will explore how these representations can guide additional sampling and improve performance in classification tasks.Read moreRead less
Muscle-based Signals for Responsive Physically-Assistive Robotics. This project aims to develop a physically assistive robot for industrial use that interprets signals from the human user’s muscles during a physical activity and responds with appropriate assistance. This is significant because the robot must accommodate the complexity of movement required in industrial settings and adapt to variabilities in muscle activation signals among users that also change in time. The expected research out ....Muscle-based Signals for Responsive Physically-Assistive Robotics. This project aims to develop a physically assistive robot for industrial use that interprets signals from the human user’s muscles during a physical activity and responds with appropriate assistance. This is significant because the robot must accommodate the complexity of movement required in industrial settings and adapt to variabilities in muscle activation signals among users that also change in time. The expected research outcome is an intuitive, assistive robot worn by the human workforce that enhances their productivity and longevity, improves working conditions, lowers production costs, and increases workforce resilience. The robot’s capabilities will be demonstrated in this project through the challenging activity of sheep shearing.Read moreRead less
Next-Generation Intelligent Robotic Mobility Aid for Vision Impaired People. More than 253 million people worldwide are blind or have low vision, with over 575,000 in Australia. This research aims to develop the world's first functional robotic guide with advanced robotic sensing, navigation, control, machine learning-based decision making and user interfaces. The project will generate novel theoretical breakthroughs, produce feasible prototypes, train young researchers, innovate industry capabi ....Next-Generation Intelligent Robotic Mobility Aid for Vision Impaired People. More than 253 million people worldwide are blind or have low vision, with over 575,000 in Australia. This research aims to develop the world's first functional robotic guide with advanced robotic sensing, navigation, control, machine learning-based decision making and user interfaces. The project will generate novel theoretical breakthroughs, produce feasible prototypes, train young researchers, innovate industry capabilities and provide new research that will transform the lives of visually impaired people. The project is expected to further benefit the service and mobility aid industry, researchers and wider community in substantial social, economic and diverse terms. The mobility aid has potential for commercialisationRead moreRead less
Learning from Uncertain and Missing Labelling in Relational Data. Perceptual models for unstructured environments require complex modelling, usually specified in an ad-hoc manner. This project will substantially increase the range of robotic applications by learning more complex spatial statistical models for perception in challenging environments. Robots will be able to improve their perception capabilities with minimal human supervision.
Mining is one of the major components of the Australian ....Learning from Uncertain and Missing Labelling in Relational Data. Perceptual models for unstructured environments require complex modelling, usually specified in an ad-hoc manner. This project will substantially increase the range of robotic applications by learning more complex spatial statistical models for perception in challenging environments. Robots will be able to improve their perception capabilities with minimal human supervision.
Mining is one of the major components of the Australian economy. This project will improve mining automation and contribute to a more efficient industry, capable to compete internationally in the new globalisation context. Efficient extraction will also reduce the human impact and will be a significant factor for an environmentally sustainable development. Read moreRead less
Decision making and mission planning for Unmanned Underwater Vehicles. The work specifically addresses the National Research Priorities
in sustainable use of Australia's biodiversity, techniques for
transforming Australian industry and Safeguarding Australia.
Without a thorough understanding of processes that affect the
state of health of our oceans they will continue to be affected by
natural phenomena and stresses caused by human activity. A more
comprehensive understanding of these natu ....Decision making and mission planning for Unmanned Underwater Vehicles. The work specifically addresses the National Research Priorities
in sustainable use of Australia's biodiversity, techniques for
transforming Australian industry and Safeguarding Australia.
Without a thorough understanding of processes that affect the
state of health of our oceans they will continue to be affected by
natural phenomena and stresses caused by human activity. A more
comprehensive understanding of these natural systems and the
interplay with human activities is therefore essential.Read moreRead less
Autonomous Exploration and Characterization of Benthic Habitats Linked to Oceanographic Processes. The work specifically addresses the National Research Priorities in sustainable use of Australia's biodiversity and climate change. Without a thorough understanding of processes that affect the state of health of our oceans they will continue to be affected by natural phenomena and stresses caused by human activity. A more comprehensive understanding of these natural systems and the interplay with ....Autonomous Exploration and Characterization of Benthic Habitats Linked to Oceanographic Processes. The work specifically addresses the National Research Priorities in sustainable use of Australia's biodiversity and climate change. Without a thorough understanding of processes that affect the state of health of our oceans they will continue to be affected by natural phenomena and stresses caused by human activity. A more comprehensive understanding of these natural systems and the interplay with human activities is therefore essential.Read moreRead less