Nadimul’s PhD research, entitled: Skill Learning and Efficient Adaptation for Robot Manipulation, focuses on how collaborative robots can safely and intelligently perform manipulation tasks in dynamic environments. His work brings together perception, planning, situational awareness, and learning‑based control to support close human‑robot interaction in settings that extend beyond fixed, highly structured factory floors.. His work has been conducted in close collaboration with InfraBuild, ensuring the research is grounded in practical challenges and delivers meaningful impact for Australian industry.
QUTie Hits the Road: Humanoid Robotics in the Real World
QUT’s newest humanoid robot, QUTie, has been stepping beyond the lab and into real-world environments—supporting research, sparking conversations, and building connections across Queensland and northern New South Wales.
As part of a broader push to explore how humanoid robots can integrate into everyday life, QUTie recently joined researchers on a regional and industry engagement tour, showcasing the role robotics can play in future communities, workplaces, and industries.
Inspiring communities across Queensland
Through outreach initiatives, including visits linked to the Country Universities Centre, QUTie has been helping engage regional communities in discussions around technology adoption and innovation. These interactions are not only inspiring curiosity but also informing future research directions—grounded in real-world perspectives on how robotics can support regional and remote Australia.
By bringing a humanoid robot directly into these settings, researchers are gaining valuable insights into how people respond to emerging technologies outside controlled environments.
Robotics meets industry and design
QUTie also joined A/Prof Müge Belek Fialho Teixeira and Prof Jonathan Roberts at the Metricon Design Summit in Byron Bay, where robotics and digital innovation took centre stage.
Müge shared insights into the future of construction, exploring how robotics and digital fabrication are transforming building practices. At the same time, Jon highlighted the growing role of humanoid robots in everyday contexts—from construction sites to domestic environments—demonstrating their potential to support a wide range of tasks.
Outside the conference, QUTie made a memorable appearance at Cape Byron Lighthouse, turning heads and drawing attention from visitors—offering a glimpse of how humanoid robots are increasingly entering public spaces.
Shaping the future of humanoid research
These real-world experiences are playing a critical role in shaping QUT’s humanoid robotics research. By combining technical development with community and industry engagement, the team is building a deeper understanding of usability, trust, and application in diverse settings.
As QUTie continues to travel, interact, and learn, it represents more than a technological milestone—it’s a step toward a future where humanoid robots are part of everyday life.
QUTie, the 130cm tall, highly agile humanoid robot, took part in the 5km run at the QUT Classic, safely and closely monitored by Jonathan Roberts, Laurianne Sitbon, and Yoann Smets. We believe this is the first time a humanoid robot has completed a race of this calibre in Australia.
Starting the race alongside everyone else at the QUT Gardens Point Campus, QUTie enjoyed a scenic run around Kangaroo Point before finishing with a final stretch through the city’s Botanic Gardens. QUTie completed the Classic in just over an hour.
Throughout the race, QUTie quickly became a crowd favourite, mingling with participants before and after the run, taking countless selfies and photos, while also showing off its amazing dance moves!
During the race, QUTie self-managed its pace and slowed down whenever its motors heated up, proving the event was not only a great photo opportunity but also an excellent way to test QUTie in the Real World.
Munia’s CA3 marks the final milestone ahead of her PhD submission.
Her PhD, undertaken within the Quality Assurance and Compliance Program, focuses on developing a structured quality assurance framework for human–robot collaborative manufacturing, with an emphasis on monitoring and automated documentation of cobot-enabled processes. Munia has worked closely with Cook Medical, ensuring her research directly addresses real-world manufacturing challenges and delivers practical value to industry.
Her work advances how manufacturers approach defect detection, classification, and prevention—bringing together human expertise and cobot precision to improve quality outcomes, reduce rework, and support more efficient production systems.
Congratulations, Munia! The whole team wishes you all the very best with your final submission — we are incredibly proud of you and look forward to seeing where you go next!
An article in The Conversation, co-authored by Centre Director Prof Jon Roberts and QUT Sport’s Marc Portus, explores the rapid rise of robots in sport, from marathon-running humanoids to robots competing with elite table tennis players.
The piece highlights that while robots can excel in precision, speed, and consistency, true sporting greatness goes beyond technical ability. Human performance is shaped by creativity, context, and decision-making under pressure, all elements that remain difficult to replicate.
They argue the real opportunity is in using robotics to enhance training and better understand human performance, positioning robots as valuable partners in the future of sport.
We’re proud to congratulate James Dwyer on winning the Robotics Australia Group Excellence in Robotics Award (Industrial Robotics – Pre‑commercial). This national recognition highlights his innovative work on the Kinematic Puppet.
Congratulations also to our outstanding finalists:
Industrial automation has traditionally been built around a fundamental limitation: robots cannot “feel”. Sensing physical interaction with a workpiece or environment has historically required expensive hardware, making such capabilities impractical for many industrial systems. As a result, conventional industrial robots typically operate in isolation, executing preprogrammed motions without direct awareness of the forces they encounter.
The development of collaborative robots (cobots) introduced the ability to sense internal forces and detect collisions, allowing for safer human-robot interaction. However, true physical awareness requires external sensors. When equipped with exteroceptive sensors, such as those that measure forces or vibrations, robots can respond to external conditions like a changing workpiece. This capability expands robotic automation into applications that require both force sensitivity and precision, including complex finishing operations such as grinding and polishing.
Grinding remains one of the most physically demanding tasks in metal fabrication. The process requires a balance between force and precision; too little pressure slows production, while too much risks damaging the part or wearing down the tool prematurely. These characteristics make grinding a promising candidate for automation. Many manufacturers pursue robotic grinding not only to address rising labour costs and workforce shortages, but also to achieve process consistency and repeatability.
However, implementing robotic grinding typically requires high-end sensing hardware. These systems often rely on force/torque sensors to measure the interaction between the tool and the workpiece, enabling robots to maintain the controlled force necessary for precision finishing. These sensors can cost upwards of $4,400 USD. For many small and medium-sized enterprises (SMEs), particularly in Australia, this cost represents a significant barrier to entry, turning automation into a financial hurdle rather than a competitive advantage.
Recent research by PhD candidate, Zongyuan Zhang and his supervisory team suggests that robots may not need expensive sensors to achieve force awareness. Human operators performing grinding tasks often rely on subtle auditory cues, like the pitch and vibration of the tool, to judge the quality of contact with the material. Experienced machinists can detect changes in force or tool wear simply by listening to the sound of the process. Inspired by this intuition, researchers have begun exploring whether similar information can be extracted using low-cost acoustic sensing combined with machine learning.
The proposed Acoustic Feedback Robotic Grinding (AFRG) system (see Figure 1) demonstrates how this approach can work in practice. Instead of measuring force directly, the system monitors the acoustic signature of the grinding process. A single contact microphone is mounted to the tool bracket, capturing vibrations transmitted through the structure of the tool while filtering out much of the ambient noise present on a factory floor.
The captured signal is processed by a specialised neural network known as PSDRegNet, a two-dimensional convolutional neural network designed to estimate the grinding force. By learning the complex relationship between acoustic patterns and grinding forces, the model can estimate the interaction force in real time. This data can then be used to adjust the robot’s behaviour online. Since the system learns this relationship directly from data, it avoids the need for rigid mathematical models that would typically govern robotic finishing processes. This flexibility allows the same system to adapt more easily to different materials, tools, and process conditions, reducing the time and engineering effort required to reconfigure robotic cells for new tasks.
Another challenge in robotic finishing is tool degradation. As grinding discs wear down or become clogged with material, their cutting efficiency declines. Robots that rely on fixed paths or constant force setpoints often struggle to compensate for this change, leading to inconsistent material removal over time. In experimental trials conducted on hardened stainless steel, a material known for accelerating tool wear, the AFRG system demonstrated a fourfold improvement in grinding consistency compared to traditional force-based control. Since the acoustic model captures tangential force information closely related to the material removal rate, the system can maintain a stable finishing process even as the physical properties of the grinding disc change.
Figure 1: The Acoustic Feedback Robotic Grinding System (AFRG) leverages acoustic signals for closed-loop force control in robotic grinding. Rather than relying on costly force sensors, AFRG uses a low-cost contact microphone to estimate the grinding force. The process involves recording audio, processing the signals, and applying regression techniques to estimate the force, which is then used to regulate the grinding process. Image courtesy of https://arxiv.org/html/2602.20596
The implications extend beyond grinding. If meaningful process information can be extracted from inexpensive sensors such as microphones, accelerometers, or cameras, machine learning may enable a new generation of low-cost perceptual capabilities for industrial robots. Instead of relying on specialised hardware for every sensing task, robots could infer key physical variables from readily available signals.
For the Australian Cobotics Centre, this approach demonstrates a cost-effective pathway for quickly upgrading existing industrial infrastructure, something important for many Australian SMEs. Many legacy robots are position-controlled, following a set of predefined positions without sensing the forces involved in the task. Retrofitting these systems with force sensors can be costly, but in contrast, an acoustic sensing system can be integrated with minimal modifications, offering closed-loop force control at a fraction of the cost.
More broadly, this work challenges the assumption that precision automation must rely on expensive hardware. By combining off-the-shelf sensors with machine learning, it becomes possible to convert robots from pre-programmed machines into adaptive systems capable of responding to their environment.
Workplace Express has recently featured a story based on Associate Professor Penny Williams’ presentation at AIRAANZ 2026, where she shared emerging insights on the rise of AI‑enabled humanoid robots — and what this means for workers, organisations and regulators.
The article highlights why now is a critical moment to consider job quality, worker voice, regulation, and ethical adoption as humanoid capabilities advance rapidly.
(Please note: the Workplace Express article is behind a paywall.)
A huge congratulations to Nisar Ahmed Channa, PhD Researcher in our Human‑Robot Workforce program, who recently delivered his final PhD seminar earlier this month!
Nisar’s project has examined the organisational and workforce factors that influence the adoption of collaborative robots in manufacturing, including developing a practical framework to help companies assess readiness, guide policy, and adapt organisational practices to support successful cobot integration.
With this milestone complete, Nisar now moves into the final stages of writing and preparing his thesis for submission.
We also extend our Congratulations to some of our Associate PhD Researchers from QUT:
A paper from our Designing Socio-Technical Robotics Systems program has been recognised with an Honourable Mention Award at ACM CHI 2026, placing it in the top 5% of accepted papers at the world’s leading conference in human–computer interaction.
Titled “The Choreography of Care: An Ethnographic Study of Human‑Robot Collaboration in Makoplasty Surgeries,” the paper was recognised by the CHI Awards Committee for its originality, methodological rigour, and potential impact. The research offers in‑depth insights into how humans and robots coordinate care in surgical settings, contributing to critical conversations in human–robot interaction and healthcare technology.
The paper will be presented at CHI in Barcelona on 17th April.
