Marine Robotics Program
Welcome to the Australian Centre for Field Robotics' marine systems group. We undertake fundamental and applied research in a variety of areas related to the development and deployment of marine autonomous systems. The ACFR, as operator of a major national Autonomous Underwater Vehicle (AUV) Facility, conducts AUV-based surveys at sites around Australia and overseas. These AUV surveys are designed to collect high-resolution stereo imagery and oceanographic data to support studies in the fields of engineering science, ecology, biology, geoscience, archaeology and industrial applications.
One of the major challenges with this program is managing, searching through and visualizing the resulting data streams. Our recent research has focused on generating high-fidelity, three-dimensional models of the seafloor; precisely matching survey locations across years to allow scientists to understand variability in these environments; and identifying patterns in the data that facilitate automated classification of the resulting image sets.
Providing precise navigation and high-resolution imagery lends itself to novel methods for data discovery and visualization. As a result, we have a strong focus on methods for interacting with and discovering patterns in the data using machine learning techniques. We also have a strong record of engagement with end users in a variety of domains interested in understanding marine environments. For a more complete and up to date description of our work, follow the link to marine.acfr.usyd.edu.au.
IMOS AUV Facility
The ACFR leads Australia's Integrated Marine Observing System (IMOS) AUV Facility. IMOS is a nationally coordinated program designed to establish and maintain the research infrastructure required to support Australia's marine science research. It has, and will maintain, a strategic focus on the impact of major boundary currents on continental shelf environments, ecosystems and biodiversity. The IMOS AUV facility generates physical and biological observations of benthic variables that cannot be cost-effectively obtained by other means and this project will provide support for its fifth year of operation and into the future. We have established an Australia-wide observing program that exploits recent developments in AUV systems to deliver precisely navigated time series benthic imagery at selected reference sites on Australia's continental shelf. These AUV-based observations are providing a critical link between oceanographic and benthic processes for Australia's IMOS program. More details of this program can be found here.
Navigation and Mapping
Much of our research is focused on improved methods for navigation and mapping for Autonomous Underwater Vehicle systems. We have developed an extensive set of tools for Simultaneous Localisation and Mapping based on high resolution stereo vision information collected by our AUVs. This has allowed us to generate detailed three dimensional seafloor models by combining tens of thousands of images and exploiting the known structure derived from the stereo imagery. We have also developed methods for Bathymetric SLAM and exploiting Acoustic Doppler Current (ADCP) observations to improve the quality of navigation in the mid-water column.
Clustering in Large Image Archives
The use of robots for scientific mapping and exploration can result in large, rapidly growing data sets that make complete analysis by humans infeasible. This situation highlights the need for automated means of converting raw data into scientifically relevant information. We have developed Bayesian clustering models for the labeling of large quantities of seafloor imagery in an unsupervised manner. This approach has the attractive property that it does not require knowledge of the number of clusters a-priori, which enables truly autonomous sensor data abstraction. The underlying data representation is also learned using unsupervised feature learning techniques. This approach consistently produces easily recognisable clusters that approximately correspond to different habitat types. These clusters are useful in observing spatial patterns, focusing expert analysis on subsets of seafloor imagery, aiding mission planning, and potentially informing real time adaptive sampling.
Novel Underwater Imaging
When capturing images underwater, the water column imposes several effects on images that are negligible in air such as colour-dependant attenuation and lighting patterns. These effects cause problems for human interpretation of images and also confound computer-based techniques for clustering and classification. Our approach exploits the 3D structure of the scene generated using structure-from-motion and photogrammetry techniques accounting for distance-based attenuation, vignetting and lighting pattern, and improves the consistency of photo-textured 3D models. We have also been investigating the use of light-field, or plenoptic, imaging systems to mitigate the impact of backscatter as well as providing novel mechanisms for detecting changes and calculating optical flow in underwater scenes.
Marine Archaelogical Studies
Recent work in collaboration with our partners has focused on collecting imagery to support the study or marine archaeological sites. Examples include the survey of a Neolithic settlement site off the coast of Greece, the site of a naval battle from the first Punic war that took place off the coast of Sicily in 241BC and numerous shipwrecks and hydrothermal sites around the Black Sea and Mediterranean. These surveys have all exploited our developments of advanced AUV survey techniques together with the ability to combine the resulting imagery to yield detailed three-dimensional models of the seafloor to provide archaeologists with a unique view of these sites. Visualisation of the resulting models can provide new insights into the layout of artefacts in these underwater sites.
Program Leader: Stefan B. Williams
Research Leads: Oscar Pizarro, Mitch Bryson, Matthew Johnson-Roberson, Bertrand Douillard, Navid Nourani-Vatani
Research Students:Nasir Ahsan, Asher Bender, Michael Bewley, Daniel Bongiorno, Donal Dansereau, Ariell Friedman, Lashika Medagoda, Dushyant Rao, Daniel Steinberg
Technical Staff: Andrew Durrant, Ritesh Lal, Christian Lees, Jeremy Randle
Alumni: Stephen Barkby (Dyson UK), Michael Jakuba (WHOI), Ian Mahon (Google), Paul Rigby (AIMS)
Collaboration and Support
We work closely in collaboration with institutions around Australia and overseas including the University of Tasmania, the University of Western Australia, the University of New South Wales, James Cook University, AIMS, CSIRO, the Woods Hole Oceanographic Institution, the University of Rhode Island, the University of Michigan and the University of Nottingham.
The research of the ACFR marine robotics group is supported by the Australian Research Council (ARC) Discovery, Linkage, Super Science Fellowship and Centre of Excellence programmes, funded by the ARC and the New South Wales State Government and the Integrated Marine Observing System (IMOS) through the Department of Innovation, Industry, Science and Research (DIISR) National Collaborative Research Infrastructure Scheme.