A flexible industrial robot with the decision-making capability of a human operator has been developed by robotics experts at the Coventry-based Manufacturing Technology Centre.
Using a combination of machine learning and visual recognition, the robot can be taught to make assembly decisions based on the components put in front of it, in a breakthrough development which could save manufacturers the costs of expensive fixed tooling.
Now the MTC has developed a flexible automation demonstrator to show manufacturers how the robotics can be used to create a low cost, reactive assembly system. The demonstrator mimics a typical electronic assembly using multiple components.
Most automation technology in industry is specifically programmed to a given task and is unable to accept input variations. Changing the process can require major investment in fixturing and reprogramming. The MTC system is trained to recognise components and assembly variables and retrieve solutions from its database. It combines a robot operating system with a collaborative robot and low-cost vision sensors.
In trials the MTC's system returned a 99 per cent successful detection rate and demonstrated that it was possible to swap the input tray and change the component mix with little effect on performance.
