ProfessorStefan Williams
Professor
Faculty of Engineering
Research projects & supervision summary
Project Opportunities
Title: Trusted Autonomous Marine Systems
Research Area:
Robotics; Autonomous Underwater Vehicles; Littoral survey
Opportunity synopsis:
The University of Sydney’s Australian Centre for Field Robotics (ACFR) is one of Australia’s leading robotics research groups and undertakes fundamental and applied research in the area of field robotics. Their marine systems group is focused on the development of novel imaging payloads, sensors and vehicle systems for marine survey, visualisation, clustering and classification of extensive marine-based image archives, characterisation of change in multi-year surveys and adaptive mission planning for multi-vehicle systems. They lead Australia’s Integrated Marine Observing System (IMOS) AUV facility and undertake marine surveys at sites around Australia and overseas. They are also a core member of the Defence Cooperative Research Centre (DCRC) in Trusted Autonomous Systems (TAS), led by Thales Australia.
The ACFR has funding available through the DCRC TAS program to support a PhD stipend to undertake fundamental and applied research related to the development, design and deployment of novel AUV systems for littoral survey. The project will explore vehicle design, navigation, perception and control systems that will allow teams of vehicles to operate in nearshore environments. Applications include rapid environmental assessment and mine counter measures operations but also extend to environmental monitoring, marine archaeology, deep-sea geology and asset inspection.
How to Apply: To apply, please email stefan.williams@sydney.edu.au the following:
- CV
- Transcripts
--------------------------------------------------
Project Opportunities
Title: Self-supervised feature learning for rapid processing of marine imagery
Summary of opportunity:
The Postgraduate Research Scholarship in Marine Robotics has been developed to support an outstanding postgraduate research student in the Faculty of Engineering at the University of Sydney to undertake research in marine robotics.
Opportunity synopsis:
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 using underwater robots and other imaging systems, but expert annotations are not keeping up meaning that insights from this data are not being realised. This project will develop Machine Learning (ML) tools that leverage an already existing, large repository of labelled and unlabelled underwater imagery to train classifiers to derive quantitative estimates of species abundance and distributions for a variety of stakeholders. The project is relatively unique in that it provides opportunities to work alongside industry partners and academic researchers, as well as a pool of expert marine scientists who have a vested interest in using machine learning tools to solve their real-world image annotation challenges. These domain experts will provide curated, standardised training data for building applied ML models, and will also provide expert validation of these models.
We are seeking outstanding candidates to join our marine robotics team and to help develop the next generation of ML tools to work with seafloor imagery. You will have a background in machine learning or computer vision and a desire to see your work integrated into existing workflows with our partner organisations. You will also have the opportunity to participate in fieldwork designed to validate the developed tools and to collect new datasets to support your work using the latest marine robotic platforms.
Offering:
A scholarship for 3.5 years at the RTP stipend rate (currently $40,109 in 2024). International applicants will have their tuition fees covered.
Successful candidates must:
- Have a Bachelors degree (1st class honours or equivalent) or a Masters degree.
- Have a background in machine learning or computer vision and desire to see your work integrated into existing workflows with our partner organisations.
How to apply: Please send the following to stefan.williams@sydney.edu.au:
- CV
- Transcripts
Applications open until 29 November at https://www.sydney.edu.au/scholarships/b/postgraduate-research-scholarship-in-marine-robotics.html
----------Current Research Projects----------
RESEARCH PROJECTS & ACTIVITIES
- RESEARCH-BASED DEGREE SUPERVISIONApplications of Autonomous Systems to Rapid Environmental Assessments
- RESEARCH-BASED DEGREE SUPERVISIONAutomated Observation of Spatial Distributions of Reef Fauna
- RESEARCH-BASED DEGREE SUPERVISIONAutomation and robust control on Surgical Robots
- RESEARCH-BASED DEGREE SUPERVISIONBenthic Visual Recognition in an Annotation-poor Domain
- RESEARCH-BASED DEGREE SUPERVISIONGeometric methods in Estimation and Control for Underwater Navigation
- RESEARCH-BASED DEGREE SUPERVISIONImproving the Capabilities of Small Underwater Vehicle Manipulator Systems
- RESEARCH-BASED DEGREE SUPERVISIONLabel-Efficient Deep Learning with the Pre-trained Models
- RESEARCH-BASED DEGREE SUPERVISIONPassive Localisation in Shallow Water Environments and Convolutional Neural Networks
- RESEARCH-BASED DEGREE SUPERVISIONPerception System For Autonomous Underwater Operation
- RESEARCH-BASED DEGREE SUPERVISIONPlanning Informative Benthic AUV Surveys
- RESEARCH-BASED DEGREE SUPERVISIONSelf-supervised feature learning and label-efficient workflows for rapid processing of marine imagery
- RESEARCH-BASED DEGREE SUPERVISIONTube Geometry Improvement for Robust Model Predictive Control
- RESEARCH-BASED DEGREE SUPERVISIONUnderwater Situational Awareness
- RESEARCH-BASED DEGREE SUPERVISIONUniting Control and Learning with Diffusion Models