Enhancing Digital Twins through Reinforcement Learning

Digital Twins are core enablers of smart and autonomous manufacturing systems. Although they strive to represent their physical counterpart as accurately as possible, slight model or data errors will remain. We present an algorithm to compensate for those residual errors through Reinforcement Learning (RL) and data fed back from the manufacturing system. When learning, the Digital Twin acts as teacher and safety policy to ensure minimal performance. We test the algorithm in a sheet metal assembly context, in which locators of the fixture are optimally adjusted for individual assemblies. Our results show a fast adaption and improved performance of the autonomous system.