Doctor of Philosophy (Australian National University), Bachelor of Engineering (Australian National University), Bachelor of Science (Australian National University)
About Jason: Jason creates decision systems for dynamic systems, including robotic and autonomous systems, that can reliably operate in the presence of uncertainty and error. Jason has over 20 years of experience developing solutions for energy, aerospace and defence industries. He has led the development of several aerial autonomous system technologies including general aviation aircraft flight control systems which are operating in Australian, European and US airspaces. Jason’s technical expertise is in the area of information-theoretic and optimisation approaches to model-based filtering, estimation, detection, decision and planning for dynamic systems and their related inverse problems. With this expertise, he is striving to understand the role of models in knowledge so that he can design more capable technology. His current research interests include aerial platform autonomy for infrastructure inspection and low signal-to-noise ratio anomalous signal detection with application in aerospace and other domains.
Academic and Professional Experience: Dr Jason J. Ford is a Professor at the Queensland University of Technology (QUT). He graduated from the Australian National University (ANU) with the B.Sc. and B.E. degrees in 1995, and a PhD degree in 1998. In 1998 Jason joined the Australian Defence Science and Technology Organisation (now called DSTG) as a Research Scientist (promoted to Senior Research Scientist in 2000). In 2004 Jason was appointed a Research Fellow at the University of New South Wales at the Australian Defence Force Academy. In 2005 Jason joined the QUT as a Research Fellow, before appointment as Lecturer in Electrical Engineering in 2007 (promoted to Senior Lecturer in 2010, to Associate Professor in 2016 and to full Professor in 2019).
Research and Industry Impact Highlights:
- Development and commercialisation of aircraft automation systems for infrastructure inspection within the ROAMES asset management system. Savings to the state of Queensland (alone) are estimated to exceed $40M/year, but ROAMES also operates in the US and UK. The impact of this rare example of an Australian developed aircraft flight technology has been acknowledged via:
- the Australian Research Council's 2018 Engagement and Impact exercise assessed the aircraft flight technology as having high impact (their highest rating).
- the ROAMES system winning a UK Network Game changer Award, a US International Edison Award, a Queensland Spatial Excellence Awards, JM (Mac) Seriser Award.
- More than a decade of sustained research activity on the extremely challenging problem of replicating the human pilot vision system to create a vision based sense and avoid technology for autonomous aerial systems. The impact of this technology has been acknowledged via collaboration project awards, other awards, and highlighted in media pieces:
- a Queensland iAward,
- a B-HERT award, and
- an Engineering Australia Excellence Award (Queensland Division).
- The 2019 Academic of the Year Award, Australian Defence Industry Awards.
Recent talks and panels:
- Bayesian Quickest Change detection and insufficiently Informative measurements STAEOnline Dec 2020
- Data Science in the News: Over the Horizon (Panel). May 2021
Recent media pieces:
- QUT develops drone collision avoidance system (2020)
- Student Findings Could Guide Vision-Based Detection Research (2020)
- Insitu Pacific readies advanced autonomous technology for real-world trials (2021)
- Bushfire Response Simulator Helps Defence With Asset Purchase Decision-Making (2021)
- Co-authored more than 100 peer reviewed research publications: PURE, Google Scholar, QUT E-prints, ORCID, and/or Publons.
- Patented flight plan and flight control technology: Method and apparatus for developing a flight path. Inventors: Troy Bruggemann and Jason Ford, Patent details can be found via the following patent numbers – Australia: 2014360672, United States: 9983584, Canada: CA2969552, Europe: EP3077881.
- Attracted over $10 million dollars in competitive research funds within Australia since 2009.
- Currently a chief investigator in QUT's Centre of Robotics (Program Lead - Decision and Control) and an Associate Investigator in QUT's Centre of Data Science.
- 8 HDR student completions since 2008.
- Taught Control System Engineering and Autonomous Systems to more than 1000 undergraduate electrical, aerospace and mechatronic engineers.
Projects (Chief investigator)
- Estimation and control of networked cyberphysical systems
- Increasing resilience of robotic systems through quickest change detection technology
- Robust Feature Selection and Correspondence for Visual Control of Robots
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- The 2019 Academic of the Year Award, Australian Defence Industry Awards.
- Ford, J., James, J. & Molloy, T. (2020). On the informativeness of measurements in Shiryaev's Bayesian quickest change detection. Automatica, 111. https://eprints.qut.edu.au/133612
- Molloy, T. & Ford, J. (2019). Minimax robust quickest change detection in systems and signals with unknown transients. IEEE Transactions on Automatic Control, 64(7), 2976–2982. https://eprints.qut.edu.au/121741
- Molloy, T., Inga, J., Flad, M., Ford, J., Perez, T. & Hohmann, S. (2020). Inverse open-loop noncooperative differential games and inverse optimal control. IEEE Transactions on Automatic Control, 65(2), 897–904. https://eprints.qut.edu.au/130720
- Molloy, T., Ford, J. & Perez, T. (2018). Finite-horizon inverse optimal control for discrete-time nonlinear systems. Automatica, 87, 442–446. https://eprints.qut.edu.au/112721
- James, J., Ford, J. & Molloy, T. (2018). Learning to detect aircraft for long range, vision-based sense and avoid systems. IEEE Robotics and Automation Letters, 3(4), 4383–4390. https://eprints.qut.edu.au/120987
- James, J., Ford, J. & Molloy, T. (2019). Quickest detection of intermittent signals with application to vision-based aircraft detection. IEEE Transactions on Control Systems Technology, 27(6), 2703– 2710. https://eprints.qut.edu.au/122352
- Molloy, T., Ford, J. & Mejias Alvarez, L. (2017). Detection of aircraft below the horizon for vision-based detect and avoid in unmanned aircraft systems. Journal of Field Robotics, 34(7), 1378–1391. https://eprints.qut.edu.au/105590
- Molloy, T. & Ford, J. (2016). Asymptotic minimax robust quickest change detection for dependent stochastic processes with parametric uncertainty. IEEE Transactions on Information Theory, 62(11), 6594–6608. https://eprints.qut.edu.au/98871
- Lai, J., Ford, J., Mejias Alvarez, L. & O'Shea, P. (2013). Characterization of sky-region morphological-temporal airborne collision detection. Journal of Field Robotics, 30(2), 171–193. https://eprints.qut.edu.au/55883
- Bruggemann, T., Ford, J. & Walker, R. (2011). Control of aircraft for inspection of linear infrastructure. IEEE Transactions on Control Systems Technology, 19(6), 1397–1409. https://eprints.qut.edu.au/40010
- Automated vision-based aircraft collision warning technologies
- Primary fund type
- CAT 1 - Australian Competitive Grant
- Project ID
- Start year
- Collision Warning; Aerial robotics; National Airspace
- isk Averse and Regulation Compliant Collision Avoidance for Uncrewed Surface Vehicles
PhD, Mentoring Supervisor
Other supervisors: Professor Matthew Dunbabin, Dr Christina Kazantzidou
- Verifiable Localisation Systems for Robots and Autonomous Vehicles
PhD, Associate Supervisor
Other supervisors: Professor Michael Milford
- Bayesian System Identification for Nonlinear Dynamical Vehicle Models (2021)
- Quickly Detecting Aircraft in Image Sequences (2019)
- Online Hidden Markov Model Parameter Estimation and Minimax Robust Quickest Change Detection in Uncertain Stochastic Processes (2015)
- Filter and control Performance Bounds in the Presence of Model Uncertainties with Aerospace Applications (2013)
- Visual Guidance for Fixed-Wing Unmanned Aerial Vehicles Using Feature Tracking: Application to Power Line Inspection (2013)
- A Hidden Markov Model and Relative Entropy Rate approach to Vision-based Dim Target Detection for UAV Sense-and-Avoid (2010)
- Robust Adaptive Control of Rigid Spacecraft Attitude Maneuvers (2008)