Featuring
Professor Michael Milford
Professor in Electrical Engineering (Artificial Intelligence and Image Processing, Neurosciences) – Science and Engineering Faculty, School of Electrical Engineering & Robotics Queensland University of Technology
One of the areas I’d be interested in working on in the future is combining the navigation systems we make, which model the navigation processes in the brain, with our actual brains to see if we could create a super navigation system – you’d never be lost again!
Q. What originally got you interested in working in this field? (Emma, Babinda State School)
A. My family had a history in the space industry, robotics and maths – my father worked in the States at Grumman Aerospace during the space race, my brothers worked in robotics, astrophysics and in space launch systems at Boeing and now Virgin Orbit, and my mum is a maths teacher.
So I grew up with a lot of exposure to these fields, and science fiction movies and books also helped. I’m a massive fan of the Terminator film series.
Q. What is the main barrier preventing progress towards self-driving cars? (Allegra, Stanthorpe State High School)
A. The main barrier is making the technology good enough so they are at least as safe as human drivers. There are other barriers too – like legal regulation, societal acceptance – but the primary roadblock at this stage is the technology.
Q. As my 16th birthday approaches, I question is it worth learning to drive or will my first car be self-driving? Will a self-driving car be able to accommodate my local, rural environment of kangaroos and echidnas? (Allegra, Stanthorpe State High School)
A. I’d definitely learn to drive! Who knows when you might need to drive a car yourself, even if robot cars eventually end up everywhere!
Detecting and avoiding kangaroos and other animals safely is a challenge but it’s probably solvable. Rural environments can be a challenge since there are often roads without lane markings – but once again this is a solvable problem.
Q. Does your research also lead into wearable technologies – the advancement of prosthetics? (Bernice, Southport SHS)
A. I don’t to do a lot of research directly on wearables but the areas we work in – computer vision, artificial intelligence and robotics, as well as some computational neuroscience – can be used in the development of wearable technologies for vision-assistance type applications, for example, in technologies for people with vision impairments to help them go about their everyday lives.
Q. What is the biggest challenge with creating a robot that can function in the real world and not in a simulated lab environment? (Bernice, Southport SHS)
A. The biggest challenge is that the real world is unpredictable – and there are always unexpected things happening. In the self-driving car industry these are often called “corner-cases”. You would never expect a person in a fast food chicken suit to jump out near a car – so preparing a robot car to deal with it is challenging.
Q. What subjects did you study at school that led you to this profession in electrical engineering? (Emma, Babinda State School)
A. You can study anything and end up in electrical engineering nowadays, although typically people focus more on the mathematics and science subjects – I did Maths B, Maths C, Physics, Chemistry, English and Latin. It’s important to also study or at least take an interest in the non-technical aspects of technologies like robotics – ethics, societal impact, legal regulation to name a few, which are just as important to understand.
Q. What degrees do you have? Are you a neuroscientist or do you work with neuroscientists? (Bernice, Southport SHS)
A. My degree was a Bachelor of Mechanical and Space Engineering, and I have a PhD in Electrical Engineering (specialising in robotics). I am fortunate to work with many amazing neuroscientists from all around the world – I’ve never really had a lot of formal training in neuroscience, it’s all been picked up on the fly or taught to me by these collaborators. They’re always telling me amazing new discoveries about how we think the brain works – it’s much more complicated than even the most advanced robots!
Q. Do you plan on integrating this with computer technology inside the human brain, or is this unlikely to ever be possible? (Marni, Atherton SHS)
A. Brain-machine interface technology has huge potential possibilities but the technology is really difficult to develop. People are talking about enhancing your vision, your hearing and even your thinking capability through advanced technologies in this space – but we’re probably a fair way off any of this becoming a reality. You can read an article we wrote about this here.
One of the areas I’d be interested in working on in the future is combining the navigation systems we make, which model the navigation processes in the brain, with our actual brains to see if we could create a super navigation system – you’d never be lost again!
Q. How does your work help Australia and the world? (Emma, Babinda State School)
A. Autonomous vehicle technology isn’t just for robot taxis on the road, but also has huge potential in off-road domains like mining and agriculture.
We’ve worked with large companies in Australia to develop autonomous vehicle-related technologies for industries like mining; newer technologies can help these industries stay competitive. Researchers in our lab also work on these technologies in other domains like agriculture.
We also work with local and federal governments to help them unpack all the complex technical issues around autonomous vehicles so they can make major investment and planning decisions that might be affected by the introduction of these technologies. Because we collaborate internationally and are always talking with or visiting overseas companies and universities, one of the key things we do is bring back an understanding of what is actually happening overseas, it can be hard to get this information back in Australia.
Q. How long have you been developing self-driving cars?
A. We’ve been doing research relating to autonomous vehicles for about over a decade now, mainly mapping and navigation systems, although we’ve been increasing the amount of autonomous vehicle research specifically in the past few years.
Q. Has your research taken you overseas or somewhere you never thought you would end up?
A. A research career offers a lot of amazing travel opportunities, we travel overseas (at least pre COVID-19) regularly to meet with collaborators, attend and present our research at conferences and visit universities and companies.
In the last few years I’ve been fortunate to travel regularly to a wide variety of places for work – France, Germany, England, China, Hong Kong, Japan, Singapore, the United States, Canada, Switzerland, Norway, Portugal and more.
One highlight is getting to visit robot car companies around the world and be taken for a ride in their robot cars – a really exciting experience.
I’ve also lived overseas for an extended period of time twice for work collaborating with universities like Harvard University – once in Boston in the USA, and once in Edinburgh and London in the UK.
Living overseas was an amazing experience and really eye opening. I’d never have expected to see all these places and I’ve learnt a lot about the world outside of Australia but I’m always glad to come back home.
Professor Milford conducts interdisciplinary research at the boundary between robotics, neuroscience and computer vision and is a multi-award-winning educational entrepreneur. His research models the neural mechanisms in the brain underlying tasks like navigation and perception to develop new technologies in challenging application domains such as all-weather, anytime positioning for autonomous vehicles.
He is also one of Australia’s most in demand experts in technologies including self-driving cars, robotics and artificial intelligence, and is a passionate science communicator.
He currently holds the positions of Deputy Director at the QUT Centre for Robotics, as well as Professor of Robotics, Microsoft Research Faculty Fellow and Chief Investigator at the Australian Centre for Robotic Vision.