![]() |
Quote:
Basically, a computer tries to optimize the order in which deliveries are made on a day to day basis in order to save time and distance for the driver. Anyone who majored in computer science or mathematics and actually paid attention in class knows how difficult this problem is. Optimizing a path of this type falls into a category known as an “NP-hard” problem (Nondeterministic Polynomial-time hard). Ironically, what ORION is trying to do is the literal textbook example of an NP-hard problem. It’s called the “traveling salesman” problem. They try to get around this by using AI, which can adjust and learn based on previous experience. AI has proved effective in this sort of thing in video games after enough tries (sometimes the number of tries can get very large). But even if it succeeds, optimizing route path isn’t the same thing as optimizing a delivery day. The computer doesn’t know when traffic patterns interfere, it can’t know that the load is clogged up by specific bulky packages which need to be delivered first, and it’s even shown that it can’t figure out that certain streets are one-way and you can’t take that route (add the problems associated with Google Maps, which it appears to use). For awhile, management was pushing 90% compliance with the route as dispatched by ORION (can’t decide for yourself for more than 10% of the stops). In theory, this would “train” the AI. It never worked. I’ve managed to train it some on my route by completely ignoring it and it seems to get smarter by copying my homework. But this kind of defeats the purpose of the tool, because it only starts to work if I don’t need it. Since we’re unionized, some drivers go full malicious compliance and follow ORION precisely, which results in a great deal of overtime pay. The route never gets more time efficient. In large hub operations, trailers are constantly being moved around the yard by shifter tractors after they are filled or emptied. Actual human beings used to dispatch these shifter tractors. Now, AI does it and tries to optimize for distance travelled by the shifter. Again, distance traveled doesn’t optimize for time. These are large trailers and everyone has to stop moving and wait when someone is setting up and backing a trailer into a parking spot or up to a bay door. AI keeps sending all the shifters to the same place at the same time to save distance. All this does is create massive traffic jams in a tightly packed yard with shifters, road tractors, and package cars waiting for a few units to take turns parking in the same area. A human, or collection of humans allowed a degree of autonomy, would learn how to solve this problem (and used to do so). |
Quote:
Quote:
|
Quote:
Fantastic examples--thanks! |
This company will hit the market with an IPO @$24/shs. https://www.he360.com/ My understanding is that the system incorporates AI.
|
Quote:
|
| All times are GMT -6. The time now is 11:18. |
Copyright 2004-2022 by Professional Soldiers ®