Second Annual Australian School for Robotic Systems (AuSRoS25)

From 1-4 July, the QUT Gardens Point Campus in Brisbane came alive with the second Australian School of Robotic Systems (AUSROS 2025). The school welcomed participants from top universities and industry partners across Australia for four days of immersive learning, collaboration, and technical exploration in the field of robotics. 

Designed to empower graduate students, early-career researchers, and professional engineers, the program offered a comprehensive overview of robotic systems. 

Program Highlights 

Foundational Lectures
Presented by leading academics and researchers, these sessions introduced core elements of robotic systems including: 

The program was further complemented by systems and science deep dive talks that covered state-of-the-art domain of interest, drawing on the technical depth of specific topic 

Each day featured sessions that brought together experts from academia and industry to explore pressing questions in robotic systems, sparking lively debate and collaborative momentum across disciplines.  

A standout moment was the trip to CSIRO Robotics that included a Robotics tour and workshop, allowing attendees hands on learning.   

Thank you to all speakers, attendees, organisers, and partner institutions for making AuSRoS 2025 a success. The feedback has been overwhelmingly positive, and we look forward to building on this momentum as we continue advancing the robotics community in Australia and beyond. 

 

CVF Computer Vision and Pattern Recognition Conference (CVPR2025)

In June, over 10,000 computer vision experts from around the world gathered in Nashville Tennessee for 2025 IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2025). Representing QUT Centre for Robotics, ARIAM Research Hub, Australian Centre for Robotics, and Abyss Solutions Ltd, Chamuditha Jayanga presented his paper ‘Multi-View Pose-Agnostic Change Localization with Zero Labels’. Co-authored with Jason Lai, Donald Dansereau, Niko Sünderhauf, and senior lead Dimity Miller, the work introduces a powerful new method for detecting scene changes—without labels or fixed camera poses.  

Chamuditha and the team present a novel label-free, pose-agnostic method for detecting scene changes using multi-view 3D Gaussian Splatting, outperforming existing approaches and enabling accurate change localisation from as few as five images – even at unseen viewpoints – alongside releasing a new real-world benchmark dataset.  

Check out the paper here: https://arxiv.org/pdf/2412.03911