A new AI-based method co-developed by Aston University’s Dr. Alireza Rastegalpana could revolutionize the way advanced robotic systems are trained for real-world tasks, making them more practical and reliable.
Dr Rastegalpana, assistant professor of applied AI and robotics at Aston, led the research in collaboration with Jamie Hathaway from the University of Birmingham’s Extreme Robotics Institute to overcome the ‘simulation-reality gap’. This is a long-standing challenge in robotics, and refers to the difference between how a robot behaves in a simulation and how it behaves in the real world, where there are variations in materials, forces, sensor noise, etc. This leads to reduced reliability.
Robots are trained for specific tasks, such as cutting, using simulation. However, collecting real-world data is expensive, time-consuming, and sometimes unsafe, especially for tasks that involve physical interaction. The goal of the study, published in Scientific Reports, was to develop a method that combines the efficiency of simulation with the realism of the physical environment to allow robots to adapt without requiring large amounts of additional data.
By using AI to generate changes in conditions, new training techniques allow robots to more reliably transfer skills learned in simulation to the real world using only small amounts of real-world data. Robots can learn complex tasks such as cutting and manipulating materials in a virtual environment and adapt that knowledge to function effectively in real-world situations. Even if the situation is uncertain or never seen before.
Dr. Rastegalpana said the method demonstrated that stable, efficient, and adaptive robot behavior could be achieved without the need for extensive real-world training. It has the potential to significantly reduce development time, cost, and risk. The impact is particularly strong in areas where robots have to operate under uncertainty. This includes recycling and circular economy systems such as battery disassembly, advanced flexible manufacturing, and hazardous environments such as nuclear decommissioning.
This research was supported by the REBELION project, which received funding from UK Research and Innovation (UKRI) as part of the European Collaborative Research Project on Automated and Safe Lithium Battery Recycling.
Dr. Rastegarpana said:
“Our long-term vision is to achieve plug-and-play intelligent robotic systems that can be trained in simulation and rapidly deployed to new environments with minimal reconfiguration. This could significantly accelerate innovation in areas such as sustainable manufacturing, recycling, and autonomous industrial systems.”
To read the full paper, visit https://www.nature.com/articles/s41598-026-41735-5.
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or stance, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
