Title: From Neuroscience to Navigation for Autonomous Vehicles and Learnings Along the Way
Speaker: Michael Milford (Professor at QUT, Australia)
Time and Date: October 12, 2026 (Monday), 11:00 AM
Location: Room 101, Building 303

Abstract
For roboticists, nature is an amazing inspiration: animals, insects and humans are capable of amazing feats that are currently far beyond the capabilities of robots. Over two decades, our research group has drawn inspiration from nature’s best navigation systems to create high-performance navigation systems for robots like autonomous vehicles. Our inspiration is twofold: we work with neuroscientists who study the neural mechanisms underpinning navigation in the brain, but also look at navigation behaviours, whether it be an ant moving over a sand dune or a rat navigating a maze. But beyond natural inspiration, we also incorporate conventional and learning-based approaches, for three key reasons: 1) “Dogs don’t drive” – many of the tasks we’d like robots to do don’t have direct analogues in nature 2) “Sharks don’t have lasers on their heads” – roboticists can leverage sensing and compute capabilities that now surpass natural systems in some respects and 3) “Much is still not known” – there are still many mysteries of nature and the brain that neuroscientists and biologists are trying to solve – in the meantime, roboticists need to fill in the gaps. It has been an exciting but bumpy career journey, especially early on, moving from fundamental research inspiration to industry collaboration, and working on on-road and off-road autonomous vehicle technology for exotic locations like underground mine sites. We’ve learnt much along the way about how robotics research is performed and evaluated, and the limitations of current benchmarks and metrics for predicting the eventual utility of research that starts in the lab. In this talk, I’ll take the audience on a journey of inspiration, breakthroughs, frustration, and unsolved questions in the quest to develop better robot navigation systems and in doing so, better understand how we ourselves navigate the world.

Bio
Michael conducts interdisciplinary fundamental and applied research at the boundary between robotics, neuroscience, computer vision and machine learning, specializing in positioning and localization. From 2022–2027 he is leading a large research team combining bio-inspired and computer science-based approaches to provide a ubiquitous alternative to GPS that does not rely on satellites. His team has worked on patented, award-winning commercial autonomous vehicle navigation technology with companies like Ford and Caterpillar, and been funded by and/or collaborated with organizations like Amazon, Intel and Google Deepmind. 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 and mentor. Michael currently holds the position of Director of the QUT Centre for Robotics, Australian Research Council Laureate Fellow, Fellow of the Australian Academy of Technology and Engineering, and is one of only three Australians ever to become a Microsoft Research Faculty Fellow. He recently won the 2025 Eureka Prize for Outstanding Mentor of Researchers.