Waabi applying AI and simulations to advance autonomous trucks
Raquel Urtasun, a Toronto-headquartered business, is introducing the Waabi Driver, an automated driving school for autonomous trucks.
It combines AI and its Waabi World closed loop simulator to create computer-simulated lessons that can be integrated by truck OEMs at a factory level.
The Waabi team is testing whether tests from tracks or highway segments are truly scalable or the best way to test edge cases.
They are concerned that having large fleets that are driving many, many miles on the road is not the most sustainable solution.
AI and simulations can test how trucks would react in the face of diverse challenges, such as weather or unexpected actions by other vehicles.
Waabi's CEO suggests that everything that is seen in the world can be translated into the simulator. This is an unusual approach when autonomous vehicle developers appear hyper-focused on the test results.
Who is Utrasun?
Urtasun is a leading innovator in autonomous vehicle development who established Waabi, a business unit that was sold to Aurora Innovation.
Her work focuses on autonomous trucks rather than cars, and she believes the work has yet to experience the disruptive influence of artificial intelligence.
She also focuses on how the technology would be applied to the bigger vehicles on the road, such as robo taxis, and how hub-to-hub highway trips are better fits.
“Bringing automation to [trucking] is a must.”
– Raquel Urtasun, Waabi founder and CEO
The most important details are that Dustin Koehl, who spent four years with the autonomous vehicle development program at U.S. Xpress, and was chairman of the American Trucking Associations' (ATA's) automated truck committee.
He suggests that the business case should be made easier by adding a costly sensor kit to a truck worth $250,000 rather than the family car.
Waabi also states that drivers only realize 6.5 hours of actual utility out of a 14-hour workday, and that social factors such as social factors make a truck driver's job particularly difficult.
Applications of autonomous trucks
Koehl believes that autonomous trucks could be applied to address industry needs, but that some developers may not understand how to do so.
He gives an example of the LTL consolidated world, where running from Charlotte to Los Angeles may go through 12 to 13 terminals or gates.
He emphasizes that the length of haul matters in autonomy, and that traditional truckers understand the need for kind of meet and turns, or relays, where you could slip seat.
To ensure that we can run across I10 or 20 or 35, we must have connected the dots in these states.
“That length of haul matters. The Hours of Service, they’re going to matter.”
– Dustin Koehl, Waabi head of transportation
Koehl argues that the U.S. lacks a federal framework for rules that would allow widespread trips, but more than 40 states now allow autonomous vehicle tests of some sort, with most of those being anchored in warm southwestern states such as New Mexico, Arizona and Texas.
She believes that Texas is the lighting rod for product demonstrations and that Ontario offers the most favorable testing environment, even if the province's framework focuses more on cars than trucks. However, she predicts "hockey stick" growth for autonomous truck applications as they expand from one region to the next.
Technical and operational challenges
Koehl, Aurora Innovation, Urtasun, and the Waabi team are all important ideas in the fight against physical barriers and driver shortages.
Koehl suggests that the technology is being framed as a way to help address ongoing truck driver shortages, while Aurora Innovation suggests that drivers must be out for the technology and capital investment to see meaningful results.
Volvo Group Venture Capital has invested in autonomous vehicle systems installed as aftermarket devices, bringing excitement to the industry.