Possibly not, right? If you don't sort but instead use the machine to do the inventory of your bins, then you could have your software tell you which bins you are going to need to fulfill your orders for the day. The big "if" in that scenario is that your machine is not categorizing anymore but identifying. I don't have the experience to assess how much harder it is.

Then you'd go and pick the bins, run them through, and the machine assembles the sets from those bins. That's similar to the way Amazon does it. Now they have the shelves on robotic trolleys that bring them directly to the packers, but that's just a required efficiency at their scale.

I guess the problem with this scheme is that you move the problem from classifying to identifying... twice. So the precision requirement goes up. I don't know how big your dataset would need to be to require minimum human intervention.