Mechatronic engineering

Supervisor: Dr Donald Dansereau, Jesse Mehami, Jack Naylor

Eligibility:

• A basic understanding of optics and electronics
• Experience with one or more of imaging, image processing and/or computer vision and strong programming skills would be an asset

Project Description:

The escalating problem of defunct satellites and other space debris represents a growing threat to crucial spaceborne technologies, including communication infrastructure and astronomical instruments. To help deal with this problem we are developing technologies that will allow us to dock with and repair satellites in orbit.

Working with researchers at the Australian Centre for Robotics, this project will develop a physical surrogate environment and perception systems for developing satellite docking and repair technologies.

Depending on ability and interest, there are opportunities to work on physical model construction, illumination and camera characterisation and engineering, and camera development and characterisation including development of novel cameras, representations, and perception algorithms.

Requirement to be on campus: Yes, *dependent on government’s health advice.

Supervisors: Dr Donald Dansereau

Eligibility:

• A basic understanding of optics and electronics
• Experience with one or more of imaging, image processing and/or computer vision and strong programming skills would be an asset

Project Description:

What does your robotic vacuum cleaner see, and who else has access to those images? In homes, hospitals, and secure industrial sites, the uptake of autonomous robots is limited by privacy concerns.

Working with researchers at the Australian Centre for Robotics, this project will develop novel sensing technologies to enable robots to visually understand their environments without capturing privacy-revealing images.

Building on existing work in the group, you will advance the design of an opto-electronic privacy-preserving robotic vision system.

Depending on interest and ability there is also scope to advance the algorithms behind the hardware or on improving the hardware design itself.

Requirement to be on campus: Yes, *dependent on government’s health advice.

Supervisors: Dr Donald Dansereau, Jack Naylor

Eligibility: Strong programming skills. Basic understanding of Robot Operating System (ROS) is desirable. Basic understanding of optics, electronics and computer vision techniques is recommended.

Project Description:

Our understanding and monitoring of the Earth and its climate are driven by data. Information from drones, aircraft and satellites provide frequent visual imagery over large areas to inform critical environmental decisions. With this increasing demand and scale of data, we are beginning to hit fundamental limits on transmission and redundancy of information. This project will focus on developing an autonomous data capture system, closing the loop between sensors and remote sensing objectives to capture only data that is new, interesting and important.

Working with researchers at the Australian Centre for Robotics, and partners in the School of Physics, this project will develop an intelligent data capture device for on-the-fly curation of information from data-intensive sensors. It will explore the applications of traditional robotics techniques in localisation and visual understanding to independently manage imaging capture systems.

Students will have the ability to work on the following areas depending on interest: hardware integration & development, localisation methods for airborne robotic platforms, interpretation of hyperspectral remote sensing data, and semantic understanding of visual data.

Requirement to be on campus: Yes, *dependent on government’s health advice.

Supervisors: Dr Donald Dansereau, Alex Cardaillac

Eligibility:

• Programming in Python or C++
• Knowledge of the robot operating system (ROS) and experience with range-based mapping or 3D reconstruction would be an asset.

Project Description:

The seafloor remains largely unexplored. Recent advances in inexpensive and nimble underwater drones opens the possibility of observing much more.

In this project you will design and develop methods to build 3D maps from small underwater drones. You will use sonar-based ranging and methods from computational imaging and robotics to make sense of the data available from inexpensive acoustic sensing payloads.

Depending on ability and aptitude, the project could focus on low-level perception, mapping, or planning for coverage. Work will leverage existing progress on an underwater drone simulator.

Requirement to be on campus: Yes, *dependent on government’s health advice.

Supervisor: Dr Viorela Ila

Eligibility: Some understanding of computer vision, deep learning and/or robotics.

Project Description:

The project focuses on developing a robust visual odometry system utilizing stereo thermal cameras to estimate motion in environments where traditional cameras struggle, such as low-light or smoke-filled conditions.

Unlike conventional visual odometry, which relies on visible light, this project leverages thermal imaging to detect heat signatures, providing reliable motion estimation in challenging environments. The system will be designed to process stereo thermal images to accurately track the position and orientation of a stereo thermal camera rig mounted on a moving platform, such as a robot or drone, in real-time.

This technology has significant potential for applications in search and rescue, firefighting, and autonomous navigation in dark or obscured environments.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Dr Viorela Ila

Eligibility: Some understanding of computer vision, deep learning and/or robotics.

Project Description:

The project aims to develop a deep learning-based framework for accurate depth estimation in underwater environments using stereo vision. Underwater imaging is often challenged by issues such as light absorption, scattering, and distortion, which can degrade image quality and depth accuracy.

This project will focus on training deep neural networks to overcome these challenges by leveraging stereo image pairs captured underwater. The goal is to produce high-resolution depth maps that can be used in various applications such as underwater navigation, 3D reconstruction, and marine biology research.

The project seeks to enhance the reliability and precision of depth estimation in complex underwater scenes, contributing to the advancement of autonomous underwater systems and environmental monitoring.

Requirement to be on campus: Yes, *dependent on government’s health advice.

Supervisors: Prof. Stefan Williams, Dr Lachlan Toohey, Dr Gideon Billlings, Dr Jackson Shields

Eligibility: Control systems knowledge (e.g. AMME3500/AMME5520). C++, Matlab, Python recommended.  An interest in marine robotic systems, machine learning or system characterisation are desirable.

Project Description:

The marine robotics group at the Australian Centre for Robotics (ACFR) undertakes fundamental and applied research in a variety of areas related to the development and deployment of marine autonomous systems. We conduct 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.

We have up to two positions available through the VRI program.  Specific projects will be designed in collaboration with students to complement their strengths and research interests, but may include one or more of the following:

1. This project will focus on characterisation of AUV system dynamics to allow our AUV systems operate close to the seafloor over complex terrain, aiming to hold a consistent altitude of 2 meters. Optimising the AUV’s control system for both maneuverability, power efficiency and obstacle avoidance is necessary for operating in these conditions.
2. Visual scene reconstruction is important for scenarios in which AUVs need to make decisions about survey targets online or when interacting with the environment.  This project will explore the use of a embedded devices to accelerate an image feature encoding network as a backbone for visual methods, such as Simultaneous Localization and Mapping, semantic segmentation, and object detection, that will run onboard underwater vehicles.
3. 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 explore self-supervised techniques that use large amounts of unlabelled data to enhance performance.

Requirement to be on campus: Yes, *dependent on government’s health advice.