February 2021

TECHNOLOGY n ROBOTICS EXPECTS at the Manufacturing Technology Centre (MTC) in Coventry have developed a flexible industrial robot with the decision-making capabilities of a human operator. Using a combination of machine learning and visual recognition, the robot can be taught to make assembly decisions based on components put in front of it. The MTC is hailing it as“a breakthrough development”that could save manufacturers the costs of expensive fixed tooling. In trials, the MTC's system achieved a 99% detection rate and demonstrated that it was possible to swap an input tray and change the component mix with little effect on its performance. “We now have a blueprint for developing and implementing intelligent vision systems for industrial problems in an effective way, opening up potential applications in human- robot collaboration,”says the MTC's chief automation officer, MikeWilson.“We have eliminated the need for part fixtures as this system can adapt to new layouts without reprogramming. Completely traceable decision-making allows errors to be addressed quickly and effectively, and the system can be trained to apply to any new assembly process.” Most automation technology is programmed to perform a given task and is unable to accept input variations. Changing the process can require a major investment in fixturing and reprogramming. The new system is trained to recognise components and assembly variables and to retrieve appropriate parameters from a database. It combines a robot operating systemwith a collaborative robot and low-cost vision sensors. The MTC has developed a demonstrator to showmanufacturers how its new technology can be used to create low-cost, reactive assembly systems. The demonstrator mimics a typical electronic assembly operation involving multiple components. “Giving robots the decision-making capability of a human operator can dramatically improve their productivity and flexibility in variable conditions,”explains senior MTC research engineer, Mark Robson. “Our demonstrator shows howmachine learning can be applied to achieve this. “This work has shown that deep-learning- based vision can provide robots with a robust ability to find and work with objects,” he adds.“The MTC has demonstrated methods to overcome the challenges in translating this ability into the physical domain of robotics which will enable the use of other machine-learning algorithms in industrial solutions." www.the-mtc.org ‘Breakthrough’ UK robot system makes decisions based on what it sees The MTC's intelligent robotic assembly system in action