ROBOTS AND AUTOMATION | TECHNOLOGY
Robot and automation technology providers are developing hardware and
software that enable cells to be managed without specific skills in robotic programming. Mikell Knights reports on new developments
Machine learning: helping moulders to automate
A consensus of robotics and automation suppliers confirm that the continuing shortage of skilled workers, rising material and energy costs, increas- ingly complex part designs and higher production efficiency requirements are driving the develop- ment of new ways to automate difficult- and simple-to-automate tasks across a range of robot types and applications. Automation areas from medical packaging to palletising are benefiting from partnerships and new manufacturing facilities in which new develop- ments that integrate industrial robots with collabo- rative robots and technologies such as artificial intelligence (AI), laser light systems, vision systems, programmable logic controllers (PLCs) simplify machine learning, programming and operation. In addition, numerous robot suppliers are offering more efficiency and production through increased speed, greater payloads, higher accuracy and extended reach with new models added to existing product lines or new robot series. Fanuc has formed a strategic relationship with AI-based software maker Micropsi Industries that advances the concept of flexible, on-site machine
www.injectionworld.com
learning for robotics tasked with performing complex motorised processes. Micropsi’s Mirai AI-based robot system, com-
prised of its AI-based software and intelligent controller, allows the user to train the programming operation of the Fanuc robot by manually guiding the robot by the robot’s wrist repeatedly. The repeated guided movements are recorded by the controller and then transformed into a skill that the robot learns. The addition of a camera and its visual data gives the robot what Fanuc calls hand-eye coordination, which allows the robot to handle diffi- cult-to-automate functions such as cable plugging and assembly by combining what it sees with what it has learned to do. “Grabbing a flexible part, guiding it and placing
it accurately into a socket has been basically impossible to complete for industrial robots. The required hand-eye coordination is just not present in a robot,” says Dominik Bosl, Chief Technology Officer at Micropsi Industries. If the robot falters, due to variances or deviations, employees typically must intervene and are sometimes burdened with unergonomic tasks, which can inhibit the perfor-
April 2023 | INJECTION WORLD 15
Main image: Vision systems and AI are two of the tech- nologies that are enabling machine learning
IMAGE: SHUTTERSTOCK
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54
