Michael Burke headshot I am a Senior Lecturer in Robotics and AI at Monash University in Melbourne, Australia and an Honorary Fellow at the University of Edinburgh. Prior to this, I was a Research Associate at the Institute of Perception, Action and Behaviour at the University of Edinburgh, which I joined after returning to academia in 2018, following about 7 years of industry R&D. Before this, I led Robotics and AI at the Mobile Intelligent Autonomous Systems group at the Council for Scientific and Industrial Research (CSIR), South Africa. I have a PhD in statistical signal processing from the University of Cambridge (2012-2016), a Masters of Science in electronic engineering from Stellenbosch University and a Bachelors in electronic engineering from the University of Pretoria.

At Monash, I teach computer vision (ECE4076) to undergraduate and masters students, and integrated design (ECE4191) where students design and build robots to complete an annual challenge. I take on a service role in graduate student support, and play a role in policy development around AI in education.

Join us

PhD students interested in working with me on probabilistic machine learning and inference for robotics (imitation, learning from demonstration, representation learning for robotics, learning-based robot control) should follow this process to apply . My supervision load is typically quite full, but always open to discussing projects aligned with my research interests.

What I do

This website lists projects (well it used to when I had time to keep it updated) I've worked on in a variety of areas covering robotics, computer vision and machine learning, particularly the probabilistic kind. I have also been involved in a wide range of contract R&D projects covering areas ranging from agriculture to mining, but sadly I can't show these off here. My core interest is in control as inference, a field of robot learning where we frame robot control as an inference problem. A key emphasis of our work is that we view neural networks as models, and try to think deeply about the architectural choices we make when using them.