Four years ago, Argo AI made its first acquisition as a newly supported young autonomous vehicle start-up. Today, Argo says its acquisition of lidar company Princeton Lightwave is paying off and is poised to help provide autonomous vehicles capable of operating commercially on highways and in dense urban areas from the United States. next year.
Argo AI on Tuesday unveiled details of a long-range lidar sensor that it says has the ability to see up to 400 meters with high-resolution photorealistic quality and the ability to detect dark, distant objects with low reflectivity. The first batch of these lidar sensors are already on some of Argo’s test vehicles, which today include Ford Fusion Hybrid sedans and Ford Escape Hybrid SUVs. By the end of the year, Argo’s test fleet will grow to around 150 Ford Escape Hybrid vehicles, all of which will be equipped with the internal lidar sensor. Ford, an investor and customer of Argo, plans to deploy autonomous vehicles for transportation and delivery in 2022. Argo’s other investor and customer, Volkswagen, has said it will launch commercial operations in 2025.
It’s not just the technical capabilities of the lidar sensor that matter, Argo CEO and co-founder Bryan Salesky told TechCrunch in a recent interview. The lidar sensor was developed to be cost effective and manufactured on a large scale, two factors that matter to any company trying to bring autonomous vehicle technology to market.
“When we started, I knew the market didn’t have adequate long-range lidar,” said Salesky, who noted that although Waymo had developed its own lidar sensors with long-range capabilities, it was not. not available to other developers. . “We decided to do an acquisition focused on plugging the hole for this long-term need. This has really been a game-changer for our autonomous driving system and has allowed us to be able to move forward really fast, to the point where we are now starting to equip cars with the sensor, and it opens the tests in urban and road environments. “
Lidar, the light sensing and ranging radar that measures distance using laser light to generate a highly accurate 3D map of the world, is viewed by most industry players as a critical sensor needed for safely deploy autonomous vehicles on a commercial scale. More than 70 companies, some of which recently went public through mergers with special purpose acquisition companies, are developing lidar – all claiming technical advancements and cost advantages. And then there are AV developers like Cruise and Aurora, who just like Argo have acquired lidar companies in the hopes of developing an in-house solution that will give them an edge over the competition and free them from working with a vendor. exterior like Velodyne. .
Ford, which has invested $ 1 billion in Argo, had also backed lidar maker Velodyne, the dominant supplier in the market. But advancements within Argo have changed Ford’s stance. Veoneer, which announced in 2019 that it was leveraging Velodyne’s technology for a contract to supply the sensor to an anonymous AV customer, announced in February that it had lost its contract. It was not known exactly who the customer was, although many assumed it was Ford or Argo. That same month, Ford reported in a regulatory filing that it had dissolved its 7.6% stake in Velodyne, cementing its bet on Argo’s internal lidar.
“Assuming the sensor meets the requirements, it should provide a substantial performance advantage over Velodyne and give them the flexibility to operate more safely at highway speeds,” said Sam Abuelsamid, analyst. principal of Guidehouse Insights researcher. Abuelsamid points out a few factors, including its wavelength and sensitivity, which could give Argo an advantage.
From low-speed urban areas to high-speed boulevards
Lidar sensors send millions of beams or pulses every second to detect surrounding objects, then measure the return to create a point cloud or 3D image. This point cloud shows the objects and calculates their range.
The Argo sensor is based on what he describes as time-of-flight in Geiger lidar mode, which he says uses beam detectors capable of detecting the smallest particle of light. Argo claims its single-photon sensors are capable of creating images of low-reflectivity objects like a black-painted car at a much greater distance than a traditional linear time-of-flight lidar. Argo also said its lidar sensor operates at a wavelength greater than 1,400 nanometers, which theoretically allows more power to help range.
Abuelsamid noted that the most common 905nm lidars are largely limited to vehicles traveling around 40mph to 45mph, suggesting that Argo’s sensor could be used at highway speeds. .
“Argo lidar’s use of the Geiger mode photodiode and pixel binning also contributes to the increase in sensitivity,” he said. “The ability to detect a single photon and then use the software to perform statistical analyzes to aggregate them and reject the noise also seems useful. It is important to be able to pick up objects with low reflectivity such as truck tire treads or very dark vehicles. “
He also noted that the Argo sensor is a mechanically rotating lidar, which is a common design based on the original Velodyne HDL-64. However, Argo’s lidar rotates the exterior surface, a design decision to help flush water away from the sensor to help keep it clean.
The combination of all this will allow Argo to develop an autonomous driving system for a variety of use cases such as dense low-speed urban areas, high-speed boulevards which have a mix of pedestrians, cyclists and cars. to face as well as highways. .
Argo has spent much of its time testing in urban environments, particularly in Austin, Detroit, Miami, Palo Alto, Pittsburgh, and Washington, DC But Volkswagen, the company’s latest backer and customer, is also interested. by autonomous driving on highways. Argo plans to start testing in other cities this year, including Munich.
Manufacturing partner and future applications
Argo has been working for over a year with a contract manufacturer who has experience in optoelectronic assembly. Hundreds of sensors will be manufactured by the end of the year and will increase from there. Argo declined to name the contract manufacturer.
Argo’s autonomous driving system is designed to be independent, which means that it could be used in several commercial models. The customers of Argo, Ford and VW, will of course dictate what those commercial applications will be, and for now it’s about robotaxis and mid-range delivery. However, Salesky noted that the sensors could be applied to trucking.
“We’re sort of focused on the movement of goods and the movement of people, but I think trucking is something that we’re looking at closely,” said Salesky. “It’s not something we’ve prioritized yet, but we’re definitely keeping trucking open and I think it’s an absolutely interesting place for our technology.”
Argo also has aspirations beyond manufacturing a long-range lidar for its own needs. Salesky told TechCrunch that the underlying technology can be integrated in different ways to create different types of sensors. “This is a very interesting potential licensing opportunity,” he said, warning that priority is given to autonomous vehicle applications.
“I think it’s a little too early to start selling in the automotive business, but it’s an opportunity that’s there,” Salesky said. “I think this underlying technology can be integrated in different ways to serve other industries such as mining, agriculture, oil and gas.”