Adaptive and efficient robot positioning

About the Project

I am looking for highly motivated and talented PhD students to work with us on robot localisation and navigation.

Robot positioning

Where are you? This is a fundamental question to which most of us usually know the answer. And so do the birds singing in our gardens, the aeroplanes flying over our cities, and the smartphones in our pockets. But why do we need to know where we are? Primarily because we need to navigate. To buy food, to go to work, to meet friends. And to navigate, we need to know where we are. And so do the robots and augmented reality devices of the future.

In addition, positional knowledge has widespread applicability beyond navigation. For example, it can help us and artificial intelligence make better decisions. Augmented reality devices can display location-aware content, interplanetary rovers can repeatedly sample the same locations, and we can better track and respond to natural disasters.

The importance of positioning or localisation systems has long been known in robotics. When robots localise visually, the problem is often called visual place recognition (VPR). Crucially, VPR enables navigation and decision-making without risky dependence on satellites, which are unavailable indoors, unreliable in built-up areas, and over which Australia has no control.

What we offer

The QUT Centre for Robotics is Australia's top-ranked robotics research hub, dedicated to transforming groundbreaking ideas into real-world impact. The Centre embraces diversity in an innovative environment. As all PhD students are supervised by at least two experienced academics, you would collaborate with leading researchers and craft your mark in the realms of AI and robotics.

My past collaborations have included Professors Michael Milford, Niko Suenderhauf and Felipe Gonzales, Associate Professor Thierry Peynot, Dr Dimity Miller, and Dr Jesse Haviland; see the list of Centre for Robotics academics. The Gardens Point campus in Brisbane is beautifully located adjacent to Brisbane's Botanic Gardens.

There are opportunities for industry internships with our partners, such as Intel Labs, working on their new Loihi 2 processor.

Research activities

Research Program 1: Heterogeneity, Adaptability, and Federation

It has long been known that different place recognition algorithms excel in different environments, and designing a system that works well in all environments is challenging. This research program will explicitly train networks to excel in specific challenges that are complementary to those challenges learnt by the other networks. Additionally, our design will allow for dynamically changing budget and accuracy requirements. Advances will include: 1) Heterogeneous models that are trained to perform well in specific types of environments and adapt to different challenges. 2) Predicting and forecasting the best-performing subset of models over time, such that not all models need to run at each time step. 3) Solving issues around data privacy using a distributed learning strategy.

Research Program 2: It’s Not All About Positioning

Current positioning techniques typically operate in a silo, that is, in parallel to, but independent from, other algorithms that solve related tasks such as object recognition and semantic segmentation. This research program aims to incorporate prior information from other systems to simplify positioning, enabling deployment on low-cost edge devices. Similarly, we will integrate place priors into non-positioning tasks to maximise performance. The research program will develop methods that jointly learn positioning & non-positioning tasks in a multi-task learning setting, which is advantageous as some concepts are easy to learn for one task while challenging to learn for another.

Research Program 3: Neuromorphic Place Recognition

Research Programs 1 and 2 introduce high-performing and adaptive place recognition algorithms deployed on conventional hardware. The third Research Program is complementary to those and will leverage advances in neuromorphic sensing and processing hardware to reduce latencies, increase data efficiency, and express uncertainties that edge devices can use. We will devise methods that dynamically adjust the hardware parameters of event cameras to optimise task performance, develop spiking neural network ensembles, and introduce a fully neuromorphic pipeline for visual place recognition.

Outcomes

Fit-for-purpose positioning

The DECRA project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. Such positional knowledge can be used by robots to navigate, by augmented reality devices to display location-aware content and by artificial intelligence more generally to make better decisions. By using image data, this can be achieved without risky dependence on satellites, which are unavailable indoors or underwater, and unreliable in built-up areas or under the tree canopy. Using brain-inspired neuromorphic computing and novel sensor types such as event cameras, the project will provide a viable alternative for low-power edge devices with superior latencies, adaptability, and data efficiency.

Applications in underwater imagery

If you are interested in ecological applications, there is also an opportunity to join a growing area of research around underwater image segmentation with deep learning approaches as detailed at the Weakly supervised segmentation of underwater imagery project page.

Skills and experience

Qualifications

• a bachelor or master degree in robotics, computer vision, computer science, mathematics, mechatronics or related areas
• a strong background, or interest in, machine learning, deep learning, computer vision, or robotics
• proficiency in programming languages such as Python, C++, MATLAB or similar
• very good analytical and problem-solving skills
• strong written and verbal communication skills.

Diversity statement

I highly encourage applications from underrepresented groups, including Women in STEM and First Nations peoples. The QUT Centre for Robotics makes safety, inclusivity and support a priority so that staff and students have the best possible chance to succeed. Many Centre members, including myself, are part of the QUT Ally network and are trained to understand sexuality and gender issues. I am also a co-chair of the IEEE-RAS Women in Engineering Committee which envisions a vibrant community of IEEE women and men collectively using their diverse talents to innovate for the benefit of humanity.

Scholarships

You may be eligible to apply for a research scholarship.

Explore our research scholarships