Editor’s note: Written by Brad Rosen, chief operating officer of NODAR, an automotive sensor developer. This is one in a series of periodic guest columns by industry thought leaders.
The race to put self-driving vehicles on public roads took an unexpected turn in recent months, with autonomous trucks taking the pole position.
It was only a year ago that robotaxis were receiving more funding than any other area of autonomous innovation. However, by simplifying the problem and focusing only on highway miles where the bulk of trucking occurs, truck manufacturers and new entrants focused on autonomous trucking software have successfully driven millions of miles autonomously on public roads. As a result, funding for trucks in 2021 surpassed 2020 investments significantly. Pitchbook reported that autonomous trucks received investment upwards of $6.5 billion in 2021, up from $1.3 billion in 2020.
“The move to autonomous trucks has the potential to transform an old, stodgy, Industrial Age industry into a high-tech one,” said Greg Aimi, Research Director at Gartner. “Tomorrow’s truck drivers being hired as technology-enabled supply chain professionals could reverse the shortage problem and might also justify higher pay for a more desired job. What is certain is that autonomous trucks will become reality at some point in the future. It’s a matter of when not if.”
The trucking industry is continuing its upward climb with several recent notable deal announcements, like a new pilot with Aurora’s autonomous trucks transporting goods for Uber Freight in Texas and TuSimple integrating their technology into DHL Supply Chain’s business. In November, Waymo and UPS announced that they will be expanding their partnership to include deliveries using Alphabet’s fleet of autonomous trucks. The deliveries will be made in Texas and the companies will be collecting data to determine the efficiency and safety of using autonomous trucks for deliveries. Additionally, TuSimple recently completed its first fully unmanned test – an 80-mile highway route in Texas – on public highways.
There is a multitude of sensors that need to be integrated onto the truck and into the autonomous vehicle software to achieve accident-free driving – the ultimate goal of the autonomous vehicle industry. A unique challenge that trucks specifically face is the amount of time a truck takes to stop. Unlike passenger vehicles, a fully loaded truck can weigh as much as 80,000 pounds. Traveling at 65 mph, the vehicle requires as much as 175 meters to come to a stop. In addition to the time and distance the truck takes to stop, the automated driving system must also have time to make the decision to stop or avoid the obstruction. Together, this means that the automated system must “see” or detect the object from about 350 meters away.
Of the available sensors on the market today, only one category of sensors can accurately detect a small object in the road at that distance – multi-camera 3D sensors. Using multiple cameras placed independently on either side of the truck, these sensors are able to accurately and reliably triangulate the distance to obstructions that are between 150 meters and 1,250 meters away – even small objects such as an overturned motorcycle on the road. Not only are these sensors used in the forward-looking orientation, but the cameras can be positioned vertically on each side of the truck to provide real-time 3D perception looking rearward up to 350 meters.
This rear-facing perception is particularly important for trucks as most fatal accidents involving trucks occur while merging. This level of long-range sensing provides the vehicle with an accurate view of the road. That gives the computer more than enough lead time to make a decision on how to proceed safely. Today, this vision technology enables higher resolution, more reliable, and significantly lower cost 3D sensing as compared with sensors such as LiDAR, enabling a level of safety previously unattainable.
The development of new sensor modalities such as multi-camera vision is enabling autonomous vehicles, and the trucking industry to accelerate its approach to the market by solving blocking issues such as long-range, small object detection. As these critical-to-deployment safety issues are systematically solved, the industry as a whole comes closer to having unmanned trucks on public roads and saving billions of dollars and countless human lives. With these sensors, autonomous truck deployment will continue to surpass robotaxis and other autonomous vehicle initiatives while greatly improving safety and inching closer to the ultimate goal – Vision Zero – crash-free driving.
Editor’s note: Trucks.com welcomes divergent thoughts and opinions on transport technology and trucking industry issues. Use the comments section to cite yours. Qualified opinion leaders are welcome to offer suggestions for opinion columns. Contact email@example.com.