Air displacement has become a nuisance for the truck industry in recent years.
A recent industry report estimated that at one point, around 35% of all trucks on American motorways were empty of goods.
For example, a truck driver could guarantee a charge to be transported from Long Beach, California, Chicago, but once he put the charge, he will return home with a trailer full of, well, just air.
This problem is not only ineffectiveness but also cost. The time wasted and the fuel means additional expenses for sender, which ultimately causes higher prices for consumers. The problem is also linked to sustainability: additional carbon emissions and the inevitable congestion of roads undoubtedly affect our environment.
Uber Freight – A commercial unit of Uber Technologies – decided to solve this problem and do it almost exclusively with artificial intelligence. It works a lot like the Uber application on a smartphone.
With the Uber application, riders are users and request the transport of all available drivers. With Uber Freight, truckers and trucking companies are users and they can use it to align various charges so that their trucks are not empty for more than a few hundred kilometers per day.
In this way, instead of going from Long Beach to Chicago and at the back, a truck could bring new charges from Chicago to New Orleans, New Orleans in Houston and Houston in Phoenix before returning home.
The technology behind this platform uses AI to optimize shipping routes, said Lior Ron, CEO of Uber Freight, in Business Insider. He said that this technology could reduce the empty rate of a 10%truck.
“The ultimate goal is to make each kilometer of a trip to a paid mile and to bother everyone while these guys make deliveries,” said Ron. “We cannot do it yet, but we can certainly get closer.”
How Uber uses automatic learning to create more optimized truck routes
From the Uber freight platform specific to trucking launched in 2023, it has used automatic learning for pioneer an algorithm which guarantees that carriers receive initial guaranteed prices for trucking and freight.
This algorithm was used by thousands of companies, including 200 fortune 500, said Ron. He added that the system had moved more than $ 20 billion in freight.
“Looking at hundreds of parameters, we were able to make the model precise enough for this to delete all friction and back and forth to try to estimate the truck price,” said Ron. These parameters include weather and traffic conditions and road closings.
Uber Freight also uses automatic learning to resolve vehicle routing, a complex problem which consists in determining the most effective route for a vehicle to be able to deliver goods to a set of locations. Here, the problem is not so much to avoid traffic as routing trucks so that their trailers are fully full and otherwise.
By designing the optimal route for the truck driver, the company was able to reduce the empty miles between 10% and 15%, Ron said. This benefits sellers, trucking companies, engines and consumers, because lower transport costs generally result in lower product costs.
Freddie Jimenez, the owner of F & J Logistics Inc. in Kansas City, Missouri, said that Uber Freight facilitated his day’s planning, to find charges that correspond to his schedule and keep his wheels in motion.
“As a driver, the most important thing is to stay in motion. I don’t lose hours or don’t worry where the next charge comes from,” Jimenez in Bi told.
Why more efficient trucking counts
Uber Freight’s technology is part of a broader thrust among logistics companies to use AI to obtain a competitive advantage, said Jose Reyes, principal director and analyst of the Gartner supply chain division.
“AI systems can analyze the weather, traffic and road conditions to suggest optimal routes in real time,” said Reyes to Bi in an email. “This is a huge advantage not only in efficiency, but also with drivers safety, load planning and distribution. This AI application can considerably reduce manual work.”
Chris Caplice, executive director of the MIT Center for Transportation and Logistics, organized a webinar on Logistics AI with Ron at the end of last year. There, Caplice said that Uber Freight technology is an example of innovations in the trucking industry.
“By being trained continuously, the models will automatically learn better routing policies; if a policy changes, for example, the model will take it back, eliminating the need for specialized algorithms,” said Caplice during the event. He added: “AI models are well generalized to solve previously invisible problems such as vehicle capabilities.”
Taking advantage of agentic AI
Uber Freight also deploys agency AI to improve efficiency.
This IA flavor is based on the ability to use human language to imitate human interactions.
Uber Freight deploys technology in a customer support center and uses it as the first line of defense against complaints.
Ron said that by sending messages to certain surveys, the company expected to reduce its waiting time to 30 seconds, against five minutes.
These abbreviated waiting times can help efficiency by minimizing the time that drivers spend with customer service for simple tasks, such as receiving a link on their smartphone or a document.
businessinsider
