Four years ago, Argo AI made its first acquisition as a young, newly-backed self-driving vehicle startup. Now, Argo says the acquisition of Lidar company Princeton LightW is paying off and is set to help deliver autonomous vehicles that operate commercially on highways and in dense urban areas starting next year can do.
Argo AI on Tuesday revealed details on a long-range LIDAR sensor, which claims to have the ability to see up to 400 meters away with high-resolution photorealistic quality and detect dark and distant objects with low reflectivity Has the potential. The first batch of these LIDAR sensors are already on some of the Argo’s test vehicles, including the Ford Fusion Hybrid sedan and Ford Escape Hybrid SUV today. By the end of the year, the Argo’s test fleet will transition to about 150 Ford Escape hybrid vehicles, all equipped with in-house LIDAR sensors. Ford, an investor and customer of Argo, plans to deploy autonomous vehicles in 2022 for ride-hailing and delivery. Argo’s other investors and customers, Volkswagen, said it would begin commercial operations in 2025.
It’s not just the technical capabilities of the LIDAR sensor that matter, Argo CEO and co-founder Brian Saleski told ClearTips in a recent interview. LIDAR sensors were cost-effective and manufactured on a scale, two factors that seek to commercialize autonomous vehicle technology for any company.
“When we first started, I knew that there were not enough long-range LIDARs on the market,” said Saleski, who noted that Waymo had developed its own LIDAR sensors with long-range capabilities, which other developers Were not available to buy for. . “We decided to take the acquisition to focus on plugging holes for that long-distance need. It has really been a game-changer for our self-driving system and has enabled us to move quickly to the point that we are now starting to equip cars with sensors, and it starts testing in urban Has been doing. Highway environment. “
Lidar, the light detection and radar that measures distances using laser light to generate a highly accurate 3D map of the world, is considered one of the most important in the industry to secure commercially autonomous vehicles. Important sensors required to deploy from. More than 70 companies, some of which have recently gone public through mergers with special purpose acquisition companies, are developing LIDAR – all claiming technological breakthroughs and cost benefits. And then there are AV developers like Crew and Aurora, who, like Argo, have acquired Lidar companies in hopes of developing an in-house solution that will give them a competitive edge and free them from working with an external supplier like Velodyne do. .
Ford, which invested $ 1 billion in Argo, backed Lidar manufacturer Velodyne, the leading supplier in the market. But progress within the Argo has changed Ford’s stance. Weiner, which announced in 2019 that it was leveraging Velodyne’s technology for a contract to supply the sensor to an undisclosed AV customer, reported in February that it had lost its contract. It was not clear who the customer was, although many speculated that it was a Ford or Argo. That same month, Ford reported in a regulatory filing that it had dissolved its 7.6% stake in Velodyne, strengthening its bet on Argo’s in-house Lidar.
“Considering that the sensor lives according to the claims, it should provide substantial performance gains over velodine and allow them to operate more safely at highway speeds,” said lead analyst Sam Abelsimid, researcher Guidehouse Insights. Abulasimum indicates certain factors, including its wavelength and sensitivity, which may give the Argo an edge.
High-speed boulevards in low-speed urban areas
LIDAR sensors send millions of beams or pulses every second to detect nearby objects and then measure the return to create a point cloud or 3D image. That point shows cloud objects and calculates their range.
The Argo sensor is based on what it describes as Geiger-mode timing of flight LIDAR, which it says uses beam detectors that can detect the smallest particle of light. Argo states that its single-photon sensors are capable of producing images of low-reflectivity objects, much like the black-painted car at much greater distances than the traditional linear time of flight LIDAR. Argo also stated that its LIDAR sensor operates at wavelengths above 1400 nanometers, which theoretically provides more power to help the range.
Abulsimed said the more common 905 nm LIDARs are limited to vehicles moving at speeds of around 40 mph to 45 mph, suggesting that the Argo’s sensors can be used at high speeds.
“The use of Argo LIDAR geyser-mode photodiodes and pixel binning also contributes to increased sensitivity,” he said. “The ability to detect a single photon and then use the software to do statistical analysis to collect them and reject noise seems like it should help as well. It is important to be able to pick up objects with low reflectivity, such as truck tire tires or very dark vehicles. “
He also notes that the Argo sensor is a mechanical spinning LIDAR, a general design based on the original Velodyne HDL-64. However, Argo’s Lidar rotates the outer surface, a design decision to keep it clean to help throw water out of the sensor.
Combining all of this, Argo will allow to develop self-driving systems for a variety of use cases such as low-speed dense urban areas, high-speed boulevards that include pedestrians, cyclists and cars as well as highways. Mixing occurs. .
Argo has also taken an interest in autonomous driving on highways in its time trials in urban environments, particularly Austin, Detroit, Miami, Palo Alto, Pittsburgh and Washington, DC Butt Volkswagen, the company’s newest backers and customers . Argo plans to begin trials in additional cities this year, including Munich.
Manufacturing Partner and Future Applications
Argo has been working for over a year with a contract manufacturer that has experience assembling optoelectronics. Hundreds of sensors will be built by the end of the year and a ramp will be built from there. Argo refused to name the contract manufacturer.
The Argo’s self-driving system is designed to be agnostic, meaning it can be used in many business models. Argo’s customers Ford and VW will undoubtedly determine those commercial applications, and for now it’s robotaxis and mid-mile distribution. However, Saleski said the sensor could be applied to trucking.
“We are focused on the movement of goods and the movement of people, but I think trucking is something that we are looking at hard,” Saleski said. “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 building long-range LIDARs for its needs. Saleski told ClearTips that the underlying technology can be packaged in other ways to create different types of sensors. “This is a very interesting potential licensing opportunity,” he said, warning that the priority is on autonomous vehicle applications.
“I think it’s a little early to start selling in the automotive realm, but this is an opportunity,” Saleski said. “I think this underlying technology can be packaged into a set of methods to serve other industries such as mining, agriculture, oil and gas.”