Physical AI Meetup

Hear 3 expert talks, take the mic for an AI/hardware demo or announcement, and connect over pizza & drinks.

Important: Please register via Eventbrite for your free ticket here – registration is required and spots are limited.

Pizza and drinks for this meetup are made possible by our sponsor, the Curtin Institute for Data Science – Australia's largest university-based data science research institute, applying data science and high-performance computing to real-world problems across government, industry, and academia.

Take the mic at our community open mic.
Share a quick demo, prototype, or announcement – whether it's AI, hardware, or something you're building. All welcome.

Agenda:

5:30 - 6:00 pm | Pizza & Networking
Enjoy pizza and drinks while connecting with other attendees.

6:00 - 6:05 pm | Welcome & Intro
Hear a short welcome from one of the meetup organisers.

6:05 - 6:30 pm | Talk 1: From Dumb Sensors to Humanoids: Our Playbook for Getting Physical AI to Revenue, Fast

• Overview: Everyone is talking about humanoids and embodied AI. Most real problems do not need one. Element Engineering Australia has built consumer electronics and IoT systems for large US customers, with over 2 million devices in the field and more than 1.5 million users on the platforms we have created. In this talk I will give away the playbook we use to take a client from idea to revenue: work out what they actually need, then find the quickest, simplest technology that gets them earning as fast as possible. I will walk the spectrum from dumb sensors through to full robotics, and how we decide where to sit on it. The honest version, including how hard it really is and where it tends to go wrong.
• Speaker: Ayrton Sue is Managing Director of Element Engineering Australia (EEA), a Perth-based engineering firm working across mechatronics, sensing, automation and product development. EEA has delivered consumer electronics and IoT systems for large US customers, with over 2 million devices deployed and more than 1.5 million users on the platforms it has built. Ayrton is also the founder of Cranio Innovations, EEA's IoT sensing and automation venture. He works with industrial and agri-food clients to take hardware from concept through to deployed product.

6:30 - 6:55 pm | Talk 2: Modelling the Black Box of Blast Movement

• Overview: On an open-pit mine, every blast moves the ore. As rock breaks and shifts across the bench, valuable material is displaced from its original position, and when that movement is not well understood, it leads directly to ore loss and dilution — good material left behind, or waste recovered in its place. Blast movement has long been treated as something of a black box: a process known to occur, but historically very difficult to observe or quantify.
  Augment is a small, remote-first company with a globally distributed team, supporting more than ten open-pit operations worldwide. The company applies physics-driven AI modelling to give mining teams a clearer understanding of how ore moves when a bench is blasted. This talk introduces the team behind the product and the problem it works on, drilling down on a recent case study on how they have helped their customer with their ore loss and dilution issues.
• Speaker: Tika Elliot is CTO and founding engineer at Augment Technologies, where she has helped shape the company since its early days, building both the product and the research that underpins it. With over a decade in product development and a background in medical science and biotechnology, Tika brings a scientific, data-driven approach to mining technology.

6:55 - 7:20 pm | Talk 3: Can AI reliably measure empathy? Trustworthy AI for empathy detection in text and video interactions

• Overview: Empathy detection is an emerging topic at the intersection of natural language processing, computer vision and psychology. In this talk, we will explore how foundation models, such as the large language model (LLM) behind ChatGPT, can address key barriers in this field. As a data-centric AI approach, we will see that LLMs can guide smaller language models for text-based empathy detection and achieve state-of-the-art results on benchmark tasks. Next, we will explore uncertainty quantification in language modelling to enable robust, trustworthy empathy computing systems. For video-based empathy detection, we will discuss how tabular foundation models achieve strong accuracy and cross-subject generalisation while preserving privacy and ensuring fairness. We will conclude with potential applications of such empathy detection systems across various real-life scenarios.
• Speaker: Dr. Rakib Hasan currently works as an Associate Lecturer at Curtin University, having recently finished his PhD in Computing. He has been a self-motivated research-and-teaching academic since 2019, with experience across five universities and three research institutes, including Curtin University, CSIRO Mineral Resources and Pawsey Supercomputing Research Centre. He has published 40 peer-reviewed papers, supervised more than 70 research students, and led cross-disciplinary projects in mineral resources and mental health, in addition to his primary research area of trustworthy computing, natural language processing and deep learning. He received multiple awards, including a finalist on the 35th INCITE Awards, Curtin EECMS HDR Forum Best Publication Award, IEEE SPS Scholarships and BRAC University Quality Journal Publication Award.

7:20 - 7:30 pm | Community Open Mic
Short informal shares – demo, prototype, or quick announcement.

7:30 pm | Wrap-Up
Any further Q&As and chats can continue here.

Last reminder: A free Eventbrite registration is required to attend – register here.