Hit enter to search or ESC to close

What to Expect When Autonomous Vehicles Come to Town

Pretty soon, on a street, highway, or roundabout near you, you might spot an autonomous test vehicle rolling by and wonder, “What is that car doing in my city? How does it work? Is it really safe?”

That’s a natural response to a very new technology, one that the general public has had very little opportunity to interact with to date. But I’d like to explain why you should feel safe and confident around our autonomous test vehicles, like the ID. Buzz AD, which was unveiled at the IAA conference this September. When they begin testing in Munich and Neufahrn this month and Hamburg later this year, our vehicles will venture into these new cities fully prepared.

The rollout of Argo’s self-driving test vehicles in our first European cities is the result of many months of collaboration, no different than our interactions with the six major U.S. cities where we launched during the past five years. There, we meet often with city and state officials, safety regulators, first responders, community groups, and advocacy organizations representing bicyclists, pedestrians, and other vulnerable road users. 

In addition to that feedback, the Argo self-driving system (SDS) is already very skilled at driving in cities based on encounters with an immense “diversity of complexity” from testing in the U.S.—meaning different driving styles, unique and rare traffic situations, and just about every unusual driver behavior you can think of. As we enter our first European markets, we will bring with us all of the technical capabilities, all of the learnings, and all of the collaborative feedback we’ve amassed through our exhaustive testing in those first six cities, and we’re adapting to the unique characteristics of European cities and traffic regulations. 

The SDS is also very mature in terms of sensor and computing hardware, especially since the ID. Buzz AD will feature our fifth-generation system that has been constantly refined over the past five years. Our vehicles come loaded with sensing technology—including lidar, radar, cameras—to anticipate the objects around the vehicles; sensors to detect emergency vehicle sirens; and a high-performance computing system to process all the data. Together, our hardware and software—developed in concert with our automaker partners at Volkswagen and Ford—give our vehicles the ability to sense and interpret the world around them in 360-degrees, with a range of more than 400 meters, by day and by night.

In some ways, it’s too limiting to think of our cars as just automobiles. In reality, they’re intelligent robots programmed to keep everyone inside and outside the vehicle safe. Our self-driving vehicles can sense both static and moving objects in a road environment, track and predict where they are going, and plan a course to safely drive to the destination. Unlike human drivers, our technology never gets tired, doesn’t drink, never gets distracted by a text message, and is always getting smarter, since important information from each individual vehicle gets shared with the whole fleet.

Safety is #1

For Argo, the foundation of our company is a dedication to safety. Our whole culture is predicated on safety as the number one priority. That’s why we use human operators, or Test Specialists, in our test vehicles throughout the development phase of our technology. So, while it may sound counterintuitive, you will first see humans behind the wheel of our autonomous test vehicles, since they are a core part of our development and testing of the technology.

Our Test Specialists have gone through extensive, weeks-long training on the operation of Argo vehicles, what to watch out for while driving, and how to conform to local driving rules and etiquette. While honing this process in our U.S. test cities, our Test Specialists have even developed a novel form of training called “commentary driving,” which is borrowed from the fast-moving world of rally-car racing. 

This process of verbalizing observations and upcoming obstacles while behind the wheel helps ensure that Test Specialists are actively engaged with the environment around them and constantly communicating with their driving partners. It’s a way of improving situational awareness and retraining the brain to drive, all of which harkens back to the same foundational value: our obsession with keeping those around us safe.

Testing, Testing, and Testing Some More

Argo engages in a continuous cycle of testing, which means that we’re never done making improvements to our self-driving system. Before our vehicles are deployed on public roads, they’re subjected to rigorous testing in the lab, in simulation, and on closed courses–and that cycle continues even as our vehicles are traveling on city streets.

To prepare for public road testing in Germany, Argo recently opened a nine-hectare test track at Munich International Airport, which is an addition to the test track we already operate near our U.S. headquarters in Pittsburgh. Building on the work completed at that facility, our test engineers in Germany expose the vehicle to a multitude of scenarios—particularly “edge cases,” or uncommon situations which nonetheless happen regularly on the road, as well as commonplace encounters with other vehicles, bicyclists, pedestrians, animals, and more. Closed-course testing is an ongoing process at Argo, with the self-driving system constantly being refined over time as we work toward the goal of driving as naturally as possible.

Of course, in a perfect world, everything on the road would follow a set of rules and predictable behaviors. The real world, however, is never this simple. In order to plan how it will get from point A to B, the Argo self-driving vehicle has to be able to do three things: sense, plan, and act. Every action the car makes requires it to answer two sets of questions as it drives down the road: What is everyone else going to do next? And how can it use this information to plan a safe, natural motion towards its destination? 

Once the system has sensed its surroundings, predicted future behavior, and planned its optimal trajectory, it’s time to act. The Argo SDS is equipped to direct the engine, braking, and steering systems as the vehicle moves along a planned path. But because the system is still learning the intricacies of the cities in which we’re testing, we also rely on our teams of Test Specialists to be on guard at all times. Argo Test Specialists are trained to monitor the vehicles in every setting and situation, and have the ability to manually take over control of the vehicle at any time.

Over time and with the help of Test Specialists within the car and engineers working on two continents, our vehicles develop a highly nuanced understanding of local road infrastructure, local driving behaviors, local pedestrian and cyclist behaviors, and the overall mobility culture of each of our test cities. In short, they learn to drive more socially.

How We Prepare to Test in New Cities

Long before our vehicles ever join the flow of traffic in a new city, we begin by engaging local stakeholders to discuss self-driving technology. After all, our vehicles utilize new technology, and trust for this technology is earned, not given. This dialogue is two-way street, with Argo learning everything we can about a city’s unique driving culture, and Argo, in turn, describing how our system works and the safety processes it utilizes.

 Once we have worked with a municipality to begin testing on public roads, we begin to map the city itself. A self-driving vehicle relies on an in-depth understanding of its surroundings, as well as the ability to predict the future actions of all other actors on the roads. For Argo, this starts by building a comprehensive 3D map of the environment in which we’ll operate. This is done with Test Specialists driving our test vehicles around a city, collecting information about the built and natural environment.

This information isn’t just a GPS map like you and I use on our smartphones—it is more like an intricate 3D model of the city. Like an ordinary map, it demarcates the intersections, avenues, and streets that we’ll be traveling on, but it also includes traffic signal locations; street signs; local laws and regulations, including speed limits; crosswalks and lane geometries; bike lanes and curbs; buildings and landmarks like statues; and even natural objects like trees and shrubs. 

Using this wealth of knowledge, an Argo self-driving vehicle then compares what it observes in real-time with the detailed 3D model of the physical space in the system. Having a complete understanding of its surroundings enhances our vehicle’s ability to move safely and naturalistically through the world. 

The Future of Autonomy

Argo continues to move forward towards the rollout of commercial ride-hail and delivery services. We are preparing to operate as part of MOIA’s ride-pooling service in Hamburg, beginning in 2025, and are currently ramping up to add Ford autonomous vehicles with the Argo self-driving system onto the Lyft ridesharing platform in two U.S. cities, Miami and Austin. New collaborations like these push us rapidly toward our goal of launching commercial services in multiple cities in the U.S. and Europe. 

But for any of these services to reach global scale, we know that we must first build trust and forge relationships on a local level. Argo AI is excited to begin this work of trust-building in the cities of Munich and Hamburg, just as we do in the U.S. 

We welcome the community’s feedback and engagement and we want everyone in our test cities to know that we’re listening. For us to reach our goal of making city-driving safe, easy, and enjoyable for everyone, we can’t operate alone. We’re dedicated to working together with you, our newest city neighbors. 

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