Harvesting marijuana with robots is hard. Here's how one company figured it out

As so many industries before it have found out, automation is the way of the future, and cannabis looks like it won't be any different. Cannabis was once a very expensive product but with supplies continuning to skyrocket allover the U.S. it's price is becoming more and more affordable, but that means for cannabis businesses to keep up their cashflow they need to innovate and keep down cost. Developing robotic automation to grow, harvest, and prepare cannabis for the consumer has not been a quick or cheap process, but one company thinks they're very close to setting the standard for replacing human trimmers. Automation in the cannabis industry may be closer than we realize with Bloom Automation suggesting their trimming robots will be able to replace 2 humans for 1 robot trimmer within about 8 months. 

The robotic harvester uses machine vision and path planning algorithms to isolate clusters of flowers. The system incorporates a back-lit time of flight camera, which measures depth, as well as a machine vision camera.

"The system segments the plant into three parts, the flower, branch, and leaf," explains Gowa. "We use a conventional neural network and a supervised machine learning set."

The Bloom team has marked up more than 6000 images and counting by hand to teach the system to distinguish between the segments. The algorithm is now 97 percent accurate.