- Dr Alireza Rastegarpanah co-led research to develop an AI-based method to train robots for real-life tasks such as cutting materials or assembly
- Current training methods are fast but can fail when a robot faces real-world variations such as differences in materials
- The technique will help to make advanced robotics more practical, scalable, and deployable in a variety of industries including recycling and manufacturing
A new AI-based method co-developed by Aston University’s Dr Alireza Rastegarpanah could revolutionise the way advanced robotic systems are trained for real-life tasks, making them more practical and reliable.
Dr Rastegarpanah, assistant professor in applied AI and robotics at Aston, co-led research with Jamie Hathaway from the University of Birmingham’s Extreme Robotics Lab to overcome the ‘sim-to-real gap’. This is a longstanding challenge in robotics, referring to the difference between how robotics behave in simulation and how they behave in the real world, where there is variability, for example in materials, forces or sensor noise. This leads to unreliability.
Robots are trained for specific tasks, such as cutting, using simulation. However, collecting real-world data is expensive, slow, and sometimes unsafe, particularly for tasks involving physical interaction. The goal of the research, published in Scientific Reports, was to develop a method that combined the efficiency of simulation with the realism of physical environments, enabling robots to adapt without requiring large amounts of additional data.
By using AI to generate variations in conditions, the new training technique allows robots to transfer skills learned in simulation into the real world much more reliably, using only a small amount of real-world data. A robot can learn a complex task in a virtual environment, such as cutting or manipulating materials, and then adapt that knowledge to work effectively in real-world conditions, even when those conditions are uncertain or previously unseen.
Dr Rastegarpanah says that the method demonstrates that it is possible to achieve stable, efficient, and adaptive robot behaviour without requiring extensive real-world training. It could significantly reduce development time, cost, and risk. The impact is particularly strong in areas where robots must operate under uncertainty. This includes recycling and circular economy systems, such as battery disassembly, advanced and flexible manufacturing, and hazardous environments such as nuclear decommissioning.
The research was supported by the REBELION project, funded by UK Research and Innovation (UKRI) as part of a European collaborative research project on automated and safe lithium battery recycling.
Dr Rastegarpanah said:
“This work shows that we can move beyond purely simulation-based training and achieve reliable performance in real-world conditions with minimal additional data. Our long-term vision is to enable plug-and-play intelligent robotic systems that can be trained in simulation and rapidly deployed in new environments with minimal reconfiguration. This could significantly accelerate innovation in areas such as sustainable manufacturing, recycling, and autonomous industrial systems.”
Visit https://www.nature.com/articles/s41598-026-41735-5 to read the paper in full.
- Notes to editors
-
About Aston University
For over 130 years, Aston University has been making our world a better place through education, research and innovation. Our history is intertwined with the remarkable city of Birmingham, once the heartland of the Industrial Revolution and now the thriving base for an innovation ecosystem of global significance, which Aston is co-creating.
Our vision is to be a leading university for science, technology and enterprise, measured by the positive transformational impact we achieve for our people, students, businesses and the communities we serve.
Aston focuses on high-quality, exploitable research that has an impact on society through medical breakthroughs, advancements in engineering, policy and practice in government, and the strategies and performance of business.
The University offers a range of undergraduate and postgraduate degree programmes, as well as continuing professional development solutions.
Thanks to its focus on delivering excellent outcomes for students, Aston University's reputation continues to grow. It was recognised as the Daily Mail University of the Year for Student Success 2025, is second in England for social mobility (2023 HEPI Social Mobility Index), and is top 20 for graduate salaries (2024 Longitudinal Education Outcomes).
Aston University is now defining its place in the Fourth Industrial Revolution (and beyond) within a rapidly changing world.
For media inquiries in relation to this release, contact Helen Tunnicliffe, Press and Communications Manager, on (+44) 7827 090240 or email: h.tunnicliffe@aston.ac.uk.
Be first to get the latest news, research and expert comment from Aston by following us on X
Need an expert for your story? Browse our experts directory
About the University of Birmingham
The University of Birmingham is ranked amongst the world’s top 100 institutions. Its work brings people from across the world to Birmingham, including researchers, educators and more than 40,000 students from over 150 countries. England’s first civic university, the University of Birmingham is proud to be rooted in of one of the most dynamic and diverse cities in the country. A member of the Russell Group and a founding member of the Universitas 21 global network of research universities, the University of Birmingham has been changing the way the world works for more than a century.