Visual Pick and Place: Difference between revisions

From Computer Laboratory Group Design Projects
Jump to navigationJump to search
No edit summary
No edit summary
 
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
Suggested by Brian Jones <bdj23@cam.ac.uk>
Client: Theo Markettos, Computer Lab <theo.markettos@cl.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.
We have a LitePlacer robot that can automatically assemble circuit boards (https://youtu.be/t__ybwOufyg), with a machine vision system based on OpenPnP. Unlike many computer vision problems, the cameras could in principle be moved around, getting better field of view or details of specific regions. Our robot currently uses the vision capabilities for simple tasks such as recognising board features and component tapes to align components it is placing. We would like to extend the capabilities of the system to automate the setup of the machine, for instance printing part numbers from CAD data on sticky labels that the vision system reads; configuring placement of component tapes; recognising parts from their shape or markings to rotate the tape; detecting parts and boards from text printed on them; and guiding the user through setup with augmented image views.

Latest revision as of 16:50, 13 November 2018

Client: Theo Markettos, Computer Lab <theo.markettos@cl.cam.ac.uk>

We have a LitePlacer robot that can automatically assemble circuit boards (https://youtu.be/t__ybwOufyg), with a machine vision system based on OpenPnP. Unlike many computer vision problems, the cameras could in principle be moved around, getting better field of view or details of specific regions. Our robot currently uses the vision capabilities for simple tasks such as recognising board features and component tapes to align components it is placing. We would like to extend the capabilities of the system to automate the setup of the machine, for instance printing part numbers from CAD data on sticky labels that the vision system reads; configuring placement of component tapes; recognising parts from their shape or markings to rotate the tape; detecting parts and boards from text printed on them; and guiding the user through setup with augmented image views.