Absolutely fascnating deep dive into warehouse and logistics automation. The Symbotic section really highlights how different their approach is from Amazon. Those ten floor facilities with hundreds of fast moving robots in narrow dark corridors sound like something out of science fiction but they're operatng right now. The fact that Symbotic plans to automate all 42 of Walmart's regional distribution centers is enormous, that's basically saying the entire Walmart supply chain will be robotic. What I find intresting about the Symbotic model versus Amazon's shelf moving robots is that it's optimized for pallet level distribution to stores rather than individual package picking for homes. This makes sense for the Walmart use case where stores need pallets of goods for unpacking rather than individual customer orders. The politics section at the end is spot on, these systems create abundance by making distribution more efficient, but the pushback from dockers and truckers is totally understandable when their jobs are at stake. Great post!
Great post - I especially like the pithy way you described how deep learning is helpful in non-standardized arenas. Will almost certainly paraphrase this in conversation for a while
"It’s also a boon for robotics because, of course, these containers are standardized, which means that we can build relatively reliable systems using classical (i.e., non-deep-learning) techniques"
Small mistake in this line:
“More generally, there’s constantly a battle over port automation more generally;”
Thank you. will have to have a talk about the editorial team (also me) about their sloppiness
Absolutely fascnating deep dive into warehouse and logistics automation. The Symbotic section really highlights how different their approach is from Amazon. Those ten floor facilities with hundreds of fast moving robots in narrow dark corridors sound like something out of science fiction but they're operatng right now. The fact that Symbotic plans to automate all 42 of Walmart's regional distribution centers is enormous, that's basically saying the entire Walmart supply chain will be robotic. What I find intresting about the Symbotic model versus Amazon's shelf moving robots is that it's optimized for pallet level distribution to stores rather than individual package picking for homes. This makes sense for the Walmart use case where stores need pallets of goods for unpacking rather than individual customer orders. The politics section at the end is spot on, these systems create abundance by making distribution more efficient, but the pushback from dockers and truckers is totally understandable when their jobs are at stake. Great post!
Thanks I am glad you liked it!
It is such a strange view of the world though isn't it? These places seem very inhuman, and not in a bad way.
Great post - I especially like the pithy way you described how deep learning is helpful in non-standardized arenas. Will almost certainly paraphrase this in conversation for a while
"It’s also a boon for robotics because, of course, these containers are standardized, which means that we can build relatively reliable systems using classical (i.e., non-deep-learning) techniques"