Abstract

At present, animal offal is either processed manually or left unprocessed if sufficient labor is not available. In lamb meat processing, robotic solutions have been developed for removing the pelt, the internal organs, and the bones. Traditional robotic sensing and manipulation is, however, not applicable to handling the soft, slippery, and unordered organ package. We hypothesize that the problem of automatically sorting animal offal can be solved by a soft actuation technique and industrial robotics in conjunction with machine vision. In this article, we structure the technical approach, discuss its viability based on the available literature, and point out where its challenges lie. To this end, we conceptualize a robotic sorting system in which a peristaltic table is used to order the organ package. The ordering process is controlled using visual feedback from the automatic recognition of the organs. When an organ is in optimal position, it is picked up and lifted by a soft vacuum gripper. The exposed tissue connections to the organ package are cut and the organ is removed from the table. Gripper and cutter are mounted on a bi-arm robot. The peristaltic table has a soft silicone surface with a matrix of independently inflatable cells. By controlling inflation, moving wave shapes are produced that drive the organ package on the surface. Organs are recognized from sets of neighboring local features in color-depth images. Constellations of organs will be recognized by partitioning the feature space of a spatially sensitive multiorgan descriptor. A graphical model relates peristaltic movement patterns to organ configurations.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.