Skip to main content

This autonomous truck just made a cross-country grocery run

Image used with permission by copyright holder

California-based startup Plus.ai claims to have completed a cross-country trip with a prototype autonomous truck. While a human backup driver and a safety engineer were onboard for the entire 2,800-mile trip, Plus.ai claims the truck was in autonomous mode most of the time. This wasn’t just a test run, either: the truck hauled a refrigerated trailer loaded with cargo for Land O’Lakes.

Perishable cargo gave Plus.ai an added incentive to ensure its tech worked. The company couldn’t simply abort the trip, and a human driver taking over would have been a public relations nightmare. The trip was completed in three days, which was sufficient for the cargo to be delivered on time, according to Plus.ai.

The trip was made easier, in a way, because the truck drove mostly on highways between freight distribution hubs in Tulare, California, and Quakertown, Pennsylvania. This ensured the truck wouldn’t have to navigate more complex environments, like city streets. Hubs like these are typical starting and endpoints for freight hauls, so this cross-country trip could still serve as a template for future commercial autonomous truck operations.

Sticking mostly to Interstate 15 and Interstate 70, the truck still encountered varied terrain and weather conditions, including rain and snow, Plus.ai claims. The truck operated in both daytime and nighttime conditions, according to the company.

Like most other autonomous vehicle developers, Plus.ai uses a combination of cameras, radar, and lidar to let vehicles “see” their environment. The sensor suite can detect objects up to 1,600 meters (5,249 feet) in front of a vehicle, Plus.ai claims. Plus.ai will likely add its autonomous-driving system to trucks built by an existing manufacturer, rather than build vehicles itself. The company hasn’t given a timeline for a commercial launch of its tech, but claims to be working with truck manufacturers, shippers, and fleet operators on reaching that goal.

Plus.ai isn’t the first company to complete a cross-country trip with a self-driving truck. In 2018, Embark sent a truck on a successful run between California and Florida, covering 2,400 miles. Like Plus.ai, Embark kept a human driver onboard at all times for safety. However, the Embark truck didn’t haul any cargo. Another company, TuSimple, currently hauls freight for paying customers with a small fleet of prototype autonomous trucks, but it isn’t making cross-country runs.

Autonomous trucking didn’t initially attract as much attention as self-driving cars, but it’s quickly catching up. In addition to small startups, bigger companies like Waymo and truck manufacturer Scania are developing driverless trucks. As with self-driving cars, improved safety is one goal. But fleet operators may also be able to cut costs by eliminating human drivers.

Editors' Recommendations

Stephen Edelstein
Stephen is a freelance automotive journalist covering all things cars. He likes anything with four wheels, from classic cars…
Waymo’s autonomous cars steer clear of any potential election unrest
Waymo fake city test

Waymo has taken its autonomous cars off the streets of San Francisco and placed them in a secure location to ensure they don’t get caught up in any election-related unrest that may occur.

Transdev, Waymo’s fleet operations vendor, told The Verge that the company had decided to temporarily pause testing of its self-driving vehicles until Thursday.

Read more
Ford reveals the vehicle destined for its autonomous-car services
ford reveals the car destined for its autonomous services vehicle

A Fourth-Generation Self-Driving Test Vehicle from Ford and Argo AI | Innovation | Ford

Ford has unveiled its fourth-generation autonomous test vehicle as it moves toward the launch of commercial services using the technology.

Read more
New self-driving car algorithm keeps you safe by constantly predicting doom
waymo self driving car testing

Call it fatalistic, pessimistic, or just really, really, smart, but a new self-driving car algorithm developed by researchers at Germany’s Technical University of Munich (TUM) thrives on thinking about the worst thing that could happen at every moment. And then figuring out how to get out of it without endangering or obstructing traffic.

“Current autonomous driving systems usually incorporate most-likely evolutions of a traffic scenario, [such as] the preceding vehicle will most likely accelerate,” Christian Pek, a researcher in the university's researcher in the Cyber-Physical Systems Group, told Digital Trends. “However, this design might result in unsafe behaviors if traffic participants behave differently than expected -- for example, [if instead] the preceding vehicle decelerates. Our algorithm addresses this problem by computing all possible future evolutions of the scenario by considering all possible motions of other traffic participants that are compliant with traffic rules. As a result, we are able to ensure that decisions are safe regardless of the future legal motion of other traffic participants.”

Read more