Hit enter to search or ESC to close

Seeing the Future: How Argo Lidar Changes the Self-Driving Game

It’s one of the most important puzzle pieces in the development of safe self-driving: long-range lidar.  

Lidar, which stands for “light detection and ranging,” uses laser pulses that bounce off objects around a self-driving car to create a 3D model of the vehicle’s surroundings. Long-range lidar can detect objects ahead, giving a self-driving car more time to respond smoothly to other road users and allowing it to operate safely at higher speeds. 

And why are higher speed capabilities important for self-driving vehicles? They open up trillions (yes, trillions) of miles for self-driving vehicles to operate on highways, suburban boulevards, and fast-moving urban streets, whether for purposes of delivering passengers or packages.

Argo Lidar, a proprietary sensor developed by the Argo Hardware team, will enable safe self-driving across large metropolitan areas to meet the growing demand for goods delivery and ride hailing. For Argo AI, the sensor is a significant milestone driven by breakthrough technology that offers long-range, low-reflectivity, and high-resolution detection.

Here are five ways that Argo Lidar gives us a competitive advantage in our pursuit of commercial deployment. 

1) Taking the long view

With a 400-meter range capability, Argo Lidar will provide vehicles equipped with our self-driving system (SDS) the ability to detect objects earlier so they have more time to respond to any given object’s position and movement. They will also be able to detect activity—from a speeding driver approaching hazardously from the rear to an unseen deer foraging on the side of the highway—at distances great enough to allow for safe responsive maneuvers. 

By unlocking long-range perception capabilities, we can extend self-driving services to the places where there is the most demand. For instance, with respect to ride-hail services, vehicles equipped with Argo Lidar can support passenger trips for airport pickups and dropoffs, suburb-to-suburb travel, and access to retail stores located along fast-moving boulevards. Long-range lidar also plays a crucial role for goods delivery, by connecting warehouse locations to residential neighborhoods to enable same-day delivery. It also presents the opportunity to consider long-haul trucking.

2) Black paint can’t hide from us

Did you know that black-painted vehicles account for approximately one out of every four vehicles on the roads in the U.S.? And did you know that some reflect less than 1% of light—with the darkest paints reflecting as little as 0.3%?  We know this, because we have spent lots of time researching the detection of black-painted vehicles, which can be difficult for many lidar systems, especially at longer ranges. 

Our innovative Geiger-mode lidar technology can detect a single photon, the smallest measurable unit of light, which reflects or bounces back from an object.  The term “Geiger-mode” comes from the Geiger counter, which can measure a single radioactive particle at a time. Lidar sensors without this ability need hundreds or thousands of reflected photons per pulse of light to guarantee a reliable detection.

This capability is particularly important at long distances, especially when traveling at highway speeds. In fact, the Argo SDS has the ability to see dark objects like black-painted cars or even joggers in dark clothing with more precision, from farther away. In comparison to other lidar sensors used by self-driving vehicles, Argo Lidar’s single-photon detection allows us to see black-painted cars at double the distance.

3) We mind the gap

Another benefit of Argo Lidar is its high resolution. It utilizes what’s known as “gapless” imaging capability, meaning that the data images it produces are of photorealistic quality. We can even apply computer-vision techniques to calculate the full velocity of any given object.

Argo Lidar can detect objects surrounding the self-driving vehicle with photorealistic quality.

Gapless imaging provides space-filling illumination of everything surrounding the vehicle to avoid information gaps relating to objects within view of the sensor. This produces a high resolution image that helps to better define the outline of any given object. This is particularly crucial in urban areas, with their profusion of bollards, construction areas, scooters, fencing, and countless other small and hard-to-define objects. More precise object classification creates greater clarity about the actions that should be taken to ensure the safety for everyone on the road.

4) 360 reasons why we love lidar

Argo Lidar uses a single rotating lidar sensor, which provides 360-degree awareness of the self-driving vehicle’s surroundings. There are several reasons for this single sensor design. 

First, using multiple overlapping sensors increases the cost and complexity of the whole system. Second, our single sensor has dual capabilities; for the mid-range, it has a broad field of view ideal for urban driving, and for long-range, it has dense high resolution for safe highway driving.

Furthermore, a single-sensor lidar system is easier to manufacture than one with multiple sensors. It’s easier to incorporate into vehicle design. It’s easier to clean, given that the sensor’s 10-revolutions-per-second spinning action prevents water and other substances from gathering on the sensor window. And it’s cost-effective for scaling our SDS across multiple cities in the U.S and Europe.

AI Argo self-driving test vehicle with Argo Lidar in the Strip District neighborhood Pittsburgh, Pennsylvania.

5) Time to make the…lidars

A few years ago, we decided to bring lidar development in-house. Thanks to our 2017 acquisition of long-range-lidar developer Princeton Lightwave, we have full control of our lidar development, integration, and supply chain.

Our lidar development takes place alongside our autonomous vehicle development, enabling rapid product iteration, tight software integration, and full synchronization of Argo Lidar with our SDS. Our deep mutual partnerships with Ford and Volkswagen enable ground-up product development, which fully integrates our SDS into their vehicles.

This supply-chain security not only provides us with important peace of mind—we even have control of our custom chips, a decision that has since proven invaluable—it also allows us to quickly scale to series production. We’re on target to build thousands of Argo Lidar sensors for our test fleets, thanks to our partnership with a highly experienced contract manufacturer, which already has units coming off the line to serve our test-fleet requirements.

With capabilities we haven’t seen elsewhere in the market today, Argo Lidar sets us on a course to drive autonomously safer and farther than ever before.

Choose your lane

How Autonomous Vehicles Distinguish Between Bicycles and People Who Ride Them

How Autonomous Vehicles Distinguish Between Bikes and People

When it comes to how autonomous vehicles see the world, humans come first, literally. Autonomous vehicles (AVs), like the kind operated by Pittsburgh-based Argo AI, use Machine Learning to detect and classify the objects in their surroundings, identifying people...
Why The League of American Bicyclists is optimistic about autonomous vehicles

Why a Leading Cycling Advocacy Group Is Optimistic About Autonomous Vehicles

As autonomous vehicle use grows, AV companies and the League of American Bicyclists are collaborating on how to ensure cyclists and motorists can share the roads safely, even if the “motorist” is artificial intelligence software. As part of the...

Self-Driving Is Arriving Right On Time. Just Like Ice Cream Did

Seven years ago, I was a self-driving skeptic. Not of the technology. Of all the “experts” promising autonomous vehicles would be everywhere by 2020. You didn’t need to be Nostradamus to know that was ridiculous. All you needed was...
Illustration of a futuristic parking deck turned into a mixed-use space, with AVs driving by

How Autonomous Vehicles Could Help Transform Parking Lots

Researchers say it’s likely that autonomous vehicles (AVs) can help reduce the need for parking lots, opening more room for grass and trees and other elements of nature. It may not seem like it when you’re circling the block...
An illustration of an Argo autonomous vehicle in teal against a backdrop of buildings, a bicyclist, and research papers

7 Big Breakthroughs From Argo Research at CVPR 2022

The 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022) is nearly here. Thousands of computer scientists, software engineers, and researchers from around the globe will gather in New Orleans to review and discuss their latest work in...

Researchers Predict the Future With Lidar Data

Researchers at Carnegie Mellon University’s Argo AI Center for Autonomous Vehicle Research, a private-public partnership funded by Argo for advancing the autonomous-vehicle (AV) field, say they have come up with a way to use lidar data to visualize not...

Must Reads