Detailed Information on Talks

Please stay tuned as we will add further information in December 2024. 

 OPENING ADDRESS

TITLE: Overview of Past and Current Approaches to Decision Making Using Machine Learning
DESCRIPTION: Artificial intelligence is under this field of computer science, including optimise, reasoning planning and learning. Variety of different methods has been developed for particular applications and tasks, many of which are ideally suited to real time control systems. In this presentation we will touch on some of the dominant optimization and learning methods in this domain, and how they can be used to support automated or human-in-the-loop decision making.
Speaker: Prof Dr Amanda Barnard AM
Affiliation: Deputy Director, School of Computing, Australian National University
Biography: Professor Amanda Barnard is an acclaimed computational scientist, renowned for her expertise at the intersection of computational modeling, high-performance computing, and applied machine learning and artificial intelligence (AI). She serves on multiple institutional boards and international panels, and has earned 11 national and international awards spanning five scientific disciplines. She is a Fellow of the Australian Institute of Physics, the Royal Society of Chemistry and the Australian Computer Society, and in recognition of her contributions to science and education, Amanda was made a Member of the Order of Australia (AM) in 2022.

 KEYNOTE DOMAIN 1: ADDITIVE MANUFACTURING

TITLE: Unlocking new approaches to autonomous real-time decision-making in additive manufacturing
DESCRIPTION: Adaptive control has long been put forward as a key enabler for additive manufacturing processes to repeatably generate high-quality parts. However, closed-loop control approaches have largely focused on short-time-horizon phenomena, such as modulating laser power to control melt pool size. This keynote address reframes the control problem for additive manufacturing as an autonomous sequential decision-making problem, where each decision can have long-ranging impact on part quality. Examples from Oak Ridge National Laboratory demonstrate how advances in in-situ monitoring, simulations, and real-time digital twins open the door for autonomous real-time decision-making that operates over long time horizons.
Speaker: Dr. Stephen DeWitt
Affiliation: Computational Sciences and Engineering Division, Oak Ridge National Laboratory
Biography: Dr. Stephen DeWitt is a computational materials scientist at the United States Department of Energy’s Oak Ridge National Laboratory (ORNL). Before joining ORNL he was at the University of Michigan, where he received a BSE in Engineering Physics, a PhD in Applied Physics, and then held a research faculty position in the Department of Materials Science and Engineering. His research centers on integrating scalable, GPU-accelerated simulation tools into scientific workflows. He is particularly interested in the combination of multiscale simulations, in-situ characterization, AI/ML, optimization, and uncertainty quantification to drive innovation in materials and manufacturing.

 KEYNOTE DOMAIN 2: FLOW CHEMISTRY

TITLE: Industry 4.0: Self-optimising Reactors for Development of Sustainable Pharmaceutical Processes
DESCRIPTION: This talk will focus on the development of automated continuous flow systems. In particular, recent research on self-optimising systems, where the reactor and its process control instrumentation become an autonomous unit into which the reactants are pumped and from which products emerge with optimised conditions. These automated systems work without human intervention and are capable of very robust experimentation and rapid optimisation of challenging processes. This talk will focus on the optimisation of multiple unit operations (including optimisation of telescoped reactions) and reactions followed by continuous work-up and the use of algorithms capable of optimising the trade-off between conflicting objectives.
Speaker: Professor Richard Bourne
Affiliation: University of Leeds, UK
Biography: Richard Bourne is currently a Professor of Digital Chemical Manufacturing at the University of Leeds. He completed a PhD under the supervision of Prof. Martyn Poliakoff, CBE, FRS. He is now a Royal Academy of Engineering Research Chair working on the development of new sustainable processes with focus on continuous flow routes to pharmaceutical and fine chemical products. His group is based within the Institute of Process Research and Development (IPRD) at the University of Leeds, a joint institute between Chemical Engineering and Chemistry.

KEYNOTE DOMAIN 3: ROBOTICS

TITLE: Safe and collaboration-friendly perception and localisation for autonomous systems
DESCRIPTION: For robots and autonomous vehicles to be deployed ubiquitously, they must meet certain requirements. Firstly, they must be performant, where most research has focused on increasing so-called benchmark performance. Secondly, many robot deployments will involve some form of collaboration or supervision, bridging the gap between human-only models and fully autonomous systems. Collaboration requires key capabilities from autonomous systems, most notably introspection. Finally, they must be safe and fit for purpose, with research metrics ideally predicting these properties. In this talk, I'll highlight challenges and limitations in these areas and showcase work addressing them through applied industry and fundamental research projects.
Speaker: Professor Michael Milford
Affiliation: QUT Centre for Robotics, Queensland University of Technology
Biography: Professor Milford conducts interdisciplinary research at the boundary between robotics, neuroscience, computer vision and machine learning, and is a multi-award-winning educational entrepreneur. 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. He currently holds the position of Director of the QUT Centre for Robotics, Australian Research Council Laureate Fellow, Professor at the Queensland University of Technology, and is a Microsoft Research Faculty Fellow and Fellow of the Australian Academy of Technology and Engineering.

KEYNOTE DOMAIN 4: ENERGY

TITLE: Scientific Machine Learning for Modeling and Control of Energy Systems 
DESCRIPTION: This talk presents a scientific machine learning perspective (SciML) on modeling, optimization, and control of energy systems. Specifically, we will discuss the opportunity to develop a unified SciML framework for modeling dynamical systems, learning to optimize, and learning to control methods. We demonstrate the application of these emerging SciML methods in a range of engineering case studies, including modeling of networked dynamical systems, building control, and dynamic economic dispatch problem in power systems.
Speaker: Prof. Ján Drgoňa
Affiliation: Johns Hopkins University, Pacific Northwest National Lab
Biography: Jan is an associate professor in the Department of Civil and Systems Engineering and the Ralph S. O’Connor Sustainable Energy Institute (ROSEI) at Johns Hopkins University (JHU). Before joining JHU, Jan was a senior data scientist in the Physics and Computational Sciences Division at Pacific Northwest National Laboratory for five years and a postdoc at the mechanical engineering department at KU Leuven in Belgium for two years. Jan has a PhD in Control Engineering from the Slovak University of Technology in Bratislava, Slovakia. His current research is focused on scientific machine learning with applications in energy systems.

 KEYNOTE DOMAIN 5: SPACE/AEROSPACE

TITLE: TBA
DESCRIPTION: TBA
Speaker: Nick Mule
Affiliation: Boeing US
Biography: TBA

SHORT TALK 1: QUANTUM MACHINE LEARNING

TITLE: Quantum Machine Learning – the melding of two technologies
DESCRIPTION: TALK POINTS: 
* With a Business Focus – looking at the use of QC and AI/ML in support of the development of applications for businesses.  
* High level – D-Wave approach to AI/ML and QML
* High level – Academia approach to AI/ML and QML
* High level – Where QML could be applied and responding in the format of ISBP – Issue, Solution, Benefits, * Proof
* Where to from here – how can NEC assist you in your journey in QML?
Speaker: Mr Michael Hall
Affiliation: National Portfolio Manager - Quantum Solutions, NEC Australia.
Biography: Michael has worked for NEC Australia for over 10 years.  During this time, Michael has been NEC's Principal ICT Enterprise Architect within the Defence and Federal Government portfolios. In these roles, Michael has drawn on his extensive 21+ years of experience while a member of the Australian Defence Force (Army). Michael has been instrumental in programs of work such as the Defence CP program, JP9711 - Simulation, as a Service (Defence). Lately, Michael has been responsible for the vision, roadmap and execution strategy of NEC Australia’s Quantum Computing solution portfolio.  This portfolio is in its infancy; with Michael driving the NEC Australia business to support the creation of a new line of business – Quantum Computing application services. Michael, NEC, and NEC's technology partner, D-Wave Systems, continue to engage with and work with Academia, Government, and the Blue-Chip sector to evangelise the power of Quantum Computing.

SHORT TALK 2: INDUSTRY 4.0 APPLICATIONS

TITLE: AI in Industrial Software Development
DESCRIPTION: As AI tools emerge they are becoming part of our business world.  It makes sense then that industrial operations get on board and reap benefits such as simplified project development and input time, providing for lower cost of development and increase in available engineering hours.  This presentation will provide an overview of how Siemens are enabling programmers to utilise such tools.
Speaker: Mr Justin Farrell
Affiliation: Siemens Ltd.
Biography: Justin has a long history in Automation and Control. During the 1990’s he worked as a Service and Field Engineer, in 1999 he became a founding member at Pilz Australia in roles including Application Engineer and Product Manager.  He joined Siemens in 2005 as Safety Product Manager and in 2006 attained TUV Certification as a TUV Functional Safety Engineer. Justin has also headed a business including Automation Safety and Hazardous areas, lead a team of Automation Specialists and was the Southern Region Manager for a Global OEM. Justin was the Siemens Factory Automation General Manager from 2017 until 2022.  In his current role as Head of Sales for Digital Industries for East Coast of Australia and New Zealand, Automation, Process Control and related Software are ongoing topics.  Justin is also a member of Siemens Ltd.  Executive Leadership Team.

SHORT TALK 3: CASE STUDY

TITLE: TBA
DESCRIPTION: TBA
Speaker: Ms Emma Burns (TBC) 
Affiliation: Microsoft Australia
Biography: TBA

SHORT TALK 4: AUSTRALIAN STANDARDS THAT IMPACT AI-DRIVEN DECISION-MAKING

TITLE: TBA
DESCRIPTION: TBA
Speaker: Ms Alexandra Snelson
Affiliation: Strategic Initiatives Manager, Standards Australia
Biography: TBA

SHORT TALK 5: INDUSTRY 4.0 IN AUSTRALIA

TITLE: Overcoming the Barriers to Industrial ML
DESCRIPTION: There are always barriers to building data-driven solutions in real-world systems. Discover ARDI, a platform for taking disorganised and scattered data and turning it into detailed, consolidated, consistent information that can be used in a range of solutions, including Machine Learning. ARDI is specifically designed to fuse high-speed industrial data with unstructured information and events, without needing to replicate. Our focus on current data as well as history allows us to not only design and train ML models, but to make your models live - running alongside systems to predict, alert and optimise a system in close to real-time.
Speaker: Mr Steven Harding
Affiliation: Senior Developer, Optrix
Biography: With a deep interest in computing from an early age and through his degree in Computer Science, Steven has always been fascinated by complex systems with emergent behaviours, such as neural networks, support vector machines, generative AI and cellular automata. His current role allows him to explore how these can be applied in industrial settings – transforming raw data into genuine value through technology. Along with building ML models, much of his work focuses on removing the frustration of the large – and often artificial – complexities when using data in the Operational Technology space.