Visual Pick and Place

Suggested by Brian Jones <bdj23@cam.ac.uk>

We have a robot that picks up and places components when assembling circuit boards. It has top and bottom cameras which are used for basic placement tasks like finding holes in component tapes. There are many more tasks it could do - such as reading printed labels on parts, identifying orientations and reading the writing on components, or informing the user they made a mistake. Ideally a user would export their parts list from CAD software, print sticky labels for each part, and the vision system would identify the parts, their orientation and automatically configure the machine.