Dr Dimity Miller is a Postdoctoral Research Fellow with the QUT Trusted Networks Lab and School of Computer Science, and an affiliate Research Fellow with the CSIRO Machine Learning and Artificial Intelligence Future Science Platform.
Dimity graduated from QUT in 2017 with First Class Honours in a Bachelor of Mechatronics Engineering and completed her PhD on how to obtain uncertainty and robustness in deep learning for robotic vision in 2021. Her current research interests include understanding deep learning failures, uncertainty estimation for robotic vision, and spatiotemporal object detection.
- How do use robotics in your current work / research?
I’m currently working on images collected by CSIRO Data61 robots during the DARPA Subterranean Challenge – a huge challenge where a fleet of robots explored underground environments and had to localise and report the presence of certain objects.
- What are you currently working on (in the robotic space)?
I’m investigating how to prevent ‘silent’ failures in object detectors – one of the vision models often used for perception in robotics.
- What is your favourite thing about doing work in robotics?
Robotics is one of the most challenging applications for vision research, and I love working on hard problems. Also, the robots are pretty cool!
- Your best achievement (in robotics) to date is?
I was awarded my PhD about 6 months ago, that felt special.
- What is your advice to other women looking to study/work in robotics?
I don’t have any short, quick advice, but I’m always happy to talk with anyone who wants to know more.
Dimity was the recipient of the 2021 EER Women HDR student of the year award.