Waabi Unveils Adaptable Autonomous Driving System for Trucking

By Seth Clevenger, Transport Topics

Self-driving truck startup Waabi has unveiled its core product, the Waabi Driver, an autonomous driving system for commercial trucks designed to learn and adapt to new routes and driving scenarios at a faster pace and lower development cost.

The Waabi Driver combines the company’s autonomous driving software with onboard computing hardware and multiple lidar, camera and radar sensors to monitor the vehicle’s surroundings, the company announced Nov. 16.

Waabi has been utilizing artificial intelligence and simulation to streamline development of the autonomous driving system, which it intends to bring to market in the future through partnerships with fleets and truck manufacturers.

The company is building its virtual driver with the goal of enabling fully autonomous heavy-duty trucks to haul freight in hub-to-hub operations that mainly involve highway driving.

 “The Waabi Driver is the next generation of autonomous driving technology that is built for trucking,” said Waabi’s founder and CEO, Raquel Urtasun. “It’s been purposely built for OEM integration and larger scale commercialization.”

In its first public unveiling, Waabi showcased its system installed on a Peterbilt tractor, but Urtasun said the hardware is designed to be compatible with a range of truck makes.

“It’s highly flexible, meaning that it’s very easy for us to empower the different OEM platforms with our technology so you can potentially serve the entire market,” Urtasun said.

The company said it has been refining the Waabi Driver through an “AI-first” approach designed to improve its flexibility and adaptability.

The virtual driver automatically learns from data and can apply its “learned” skills to new situations and geographies that it has not encountered before, thus accelerating the system’s ability to expand to new routes, Urtasun said.

Waabi has built a simulator to train its autonomous driving system how to navigate “edge cases” — very rare events or situations the vehicle might encounter on the road.

That simulator, dubbed Waabi World, functions as a digital twin of the real world through which the company can more quickly and more safely test the system’s performance against a range of challenging driving scenarios.

“Now I can feed to the autonomy system all those very rare cases in a very frequent manner so that I can understand whether it can handle those or not,” Urtasun said.

By front-loading the development of its self-driving system through simulation, Waabi also has reduced the need for expensive on-road testing, she said.

The company is still conducting on-road tests, but that work is “mostly validation and verification,” Urtasun said, so the company will deploy a “much smaller” test fleet than other developers of self-driving technology for commercial trucks.

While Waabi sees hub-to-hub routes as the first use case for its autonomous driving technology, the company later intends to expand across more geographical regions and to different use cases that include more surface street driving, Urtasun said.

Founded in 2021, Waabi is a relatively new player in the autonomous trucking space.

More than a dozen other technology companies and startups — the majority of which were founded 4-7 years ago — also have been working to bring various forms of highly automated driving to the trucking industry.

Urtasun sees Waabi as part of a “second wave” of autonomous vehicle development focused on bringing this technology to market sooner, and with less capital.

“We represent the next generation,” she said. “We represent a different way to tackle this.”

 The trucking industry is more ready for self-driving technology than in the past, said Vivian Sun, chief commercial officer at Waabi.

Several years ago, fleet executives were asking “if” it’s going to happen, but more recently the conversations have shifted to “when” and “where” it will happen, Sun said.

Waabi, based in Toronto with U.S. headquarters in San Francisco, has been ramping up hiring and assembling a leadership team that includes Dustin Koehl as its head of transportation and Jur van den Berg as principal software engineer.

While Waabi is working to make unmanned trucking a reality in certain applications, the company does not see its technology displacing the industry’s workforce.

Instead, Sun said Waabi’s goal is to supplement drivers and help fill the labor gap for trucking companies struggling with recruiting challenges and high turnover rates.

A new truck driver that enters the industry today will be able to retire as a driver in the future, she said.

In some cases, automation could help improve those jobs.

Sun said self-driving technology could automate driving on long, tedious stretches of highway while professional drivers shift more toward local pickup and delivery jobs that provide more home time.

“We see a hybrid network for a very, very long time,” Urtasun added.

The Road Ahead for Autonomous Vehicles: Aurora CEO Chris Urmson on the Future of Cars and Trucks

By Todd Bishop, GeekWire

Fully autonomous vehicles are closer to commonplace than you might expect, as cars and big rigs gain the ability to operate safely on our streets and highways.

As one of the pioneers in the field, Chris Urmson has been there almost from the beginning, competing in the landmark DARPA Grand Challenge before leading Google’s self-driving car initiative. Now he’s following through on the vision as CEO of Aurora, which is developing self-driving technology for car and truck makers.

On this episode of the GeekWire Podcast, we’re playing highlights from our conversation with Urmson at the recent GeekWire Summit.

Listen below, or subscribe in any podcast app, and keep reading for excerpts. 

Aurora’s approach: We founded Aurora about six years ago with the mission to deliver the benefits of self-driving technology safely, quickly and broadly. We’re building the driver technology. We don’t want to build trucks or cars. There’s people who do that really well. We don’t want to build Uber or FedEx or any of the carriers. We want to build the driving technology to power those businesses.

Underlying technology: The driver we’ve built uses a combination of sensors: LIDAR, radar, cameras, our special high-definition maps. We’ve got our proprietary FirstLight LIDAR, which allows us to see further than others can. And we have a lot of computing onboard. It’s this common architecture, common hardware and software that runs everything from the Toyota Sienna through vehicles from PACCAR and Volvo.

Current state of operations: Today we have trucks on the road in Texas pulling loads for customers every day, with people on board, with operators on board. … The vast majority of the time, it’s driving itself. And it’s doing this on the freeway. And it is a very smooth, capable driver at this point. It does the things that you’d want other drivers to do. So if it sees vehicles trying to merge … it will make space and move over. When it sees a vehicle stuck on the side of the road, it’ll slow down, it’ll make space, and do all the things that a good conscientious driver would do.

Why start with big rigs? For a bunch of reasons:

  • There’s just an incredible need for this technology in the U.S. We’re short 80,000 drivers today; we expect to be short 160,000 drivers by the end of the decade. It is one of the contributing factors to the supply chain challenge.
  • Safety is profoundly important. There are about a half-million heavy truck accidents per year. That’s something we can do something about.
  • As a business, the economic opportunity is even better. Trucking today in the U.S. is about a $700 billion industry; ride-hailing is about a $35 billion industry. And so from an addressable market, it’s profound.
  • When we look at the opportunity to build the business and scale it, unit economics are stronger. Said simply, we pay truck drivers three times as much as we pay ride-hailing drivers. And so if you think about introducing a technology, that makes it easier to start to scale the business and then move into other spaces.
  • Finally, from a technology point of view, we expect to be able to scale more rapidly. If you think about what a mile of freeway in Texas looks like, versus a mile of freeway in Minnesota, versus a mile of freeway in California, they’re all basically the same. Whereas, with an intersection in San Francisco, you go five blocks away, and it’s different people, different behavior, different geometry.

What do you say to people who are concerned about safety? First, this is a new technology. It is very rational and reasonable to have concerns and questions and really want to understand it better. That’s perfectly normal and healthy.

Safety is core to the DNA of the company. It’s why we’re as transparent as we are about how we do safety at the company. We’ve shared our framework for how we’re going to convince ourselves and others that the vehicle is safe.

The technology is magical in some ways. It can look in all directions at once. And it doesn’t have the human response of foveation that happens. … There’s an incredible opportunity here for safety.

If you had the option to drive I-5 from the Bay Area to Seattle yourself or have the Aurora Driver drive, which would you choose, safety-wise?

We’re not quite there yet with the Aurora Driver. But we are making really good progress. There’s a lot of the time where I would certainly trust it. Where we’re at with the Aurora Driver is driving up reliability … but we haven’t quite finished yet. If we had, we would be operating without drivers today.

What’s next: We are working to be feature complete at the end of Q1. At that point, the Aurora Driver does everything it’ll need to be part of a product out in the world. But it doesn’t yet do it quite well enough. We’re working towards the end of next year to be ready.

Future of Mobility: MSU Taking the Wheel with R&D, Educating Talent

By MLive, Michigan State University

Sparked by the Curved Dash Oldsmobile in 1901 and accelerated by Ford’s pioneering assembly lines, automotive production in Michigan has been at the forefront of the mobility industry for more than a century. Still today, there are more than two dozen original equipment manufacturers in our state supplying automakers worldwide.

For Michigan to remain the trailblazer in travel and transportation into the next generation of self-driving cars, it’s going to require two of the same ingredients that put the state on the map in the early 1900s: innovation and talent. Fortunately, Michigan’s mobility industry has a strategic partner in Michigan State University.

MSU is conducting cutting-edge research and educating students who are shaping the future of mobility, both in Michigan and across the globe, by creating integrated systems of communication and control that enable automated vehicles to understand their environment and navigate it safely and efficiently.

“Michigan State plays an absolutely vital role in the growth of the companies that are here and the companies that might want to move here,” said Glenn Stevens Jr., executive director of MICHauto and the Detroit Regional Chamber’s vice president of automotive and mobility initiatives.

“There really isn’t any cluster in the world like the one that exists in Michigan with regard to automotive and next-generation mobility technology. It’s the sum of the parts, and Michigan State is one of those very significant parts that make up that unique ecosystem.”

Stevens is a member of the MSU Mobility Advisory Council, a public-private partnership created to strengthen the connection between Michigan’s mobility industry and MSU’s academic and research excellence. The council members come from academia, the auto industry, economic development, technology and beyond to help inform MSU’s vital contributions to mobility research and talent development.

First, let’s look at some of the groundbreaking mobility research underway at MSU:

  • MSU has nearly 50 experts and their connected staff researching autonomous and connected vehicle technology. MSU has a long history of working with the mobility industry and is continuing to do so through nearly $75 million of research and development in autonomous and connected vehicle technology over the past five years alone. That research is focused on making vehicles and roadways safer and more efficient for the future by reducing accidents, saving lives and improving mobility and productivity. MSU is doing this by developing a variety of new technologies, from algorithms that autonomous vehicles use to understand and navigate the driving environment in any weather conditions to sensors that foster communication between the vehicle and the streetscape and even pedestrians via their phones. “We are trying to build a smart city,” said Satish Udpa, interim director of MSU Mobility.
  • MSU’s campus is the perfect test bed for autonomous and connected vehicle systems. With a self-contained mix of urban, suburban and rural areas, the 5,200-acre East Lansing campus offers an unrivaled real-world ecosystem for testing the autonomous and connected vehicle tools that are revolutionizing the way people and goods move around. A self-driving electric bus and two autonomous test cars are collecting reams of data through cameras, lidar and other technology and using it to understand the surrounding environment that features 60 lane-miles of road, nearly 40 traffic signals, more than 100 miles of pedestrian walkways and 30,000 other vehicles per day. MSU researchers are using that data to fine-tune and validate autonomous and connected vehicle technologies. “The biggest challenges lie in the interface between man and machine,” Udpa said. “Our test bed happens to be in a setting where it comes across real human beings. It’s a living, breathing test track.”
  • MSU is researching the best ways to implement large-scale electric vehicle use. As the internal combustion engine begins phasing out in favor of electric vehicles, there are many things to consider, from improving battery performance so people can drive farther before recharging to enhancing charging capacity so that everyone in town for a game at Spartan Stadium can charge up for the ride home. “The challenge is how do we manage things like that,” said John Verboncoeur, associate dean for research in MSU’s College of Engineering. “The infrastructure support is absolutely critical and will become more critical as we move away from internal combustion engines to plug and play.” MSU is currently adding nearly 370 electric vehicles on campus and offers more than 60 EV charging stations.

Combined with the unique test bed that is the MSU campus, the abundance of research expertise among faculty in a range of disciplines makes MSU the perfect partner for the mobility industry in Michigan. In turn, ensuring that Michigan remains at the epicenter of mobility going forward is a worthy cause for a leading research university tasked with education and economic development in our home state.

As a result, next-generation mobility technology is now one of MSU’s principal areas of research and innovation.

“We look to Michigan State from an industry perspective as one of the leaders working on next-generation mobility solutions, and that’s everything from materials science to road infrastructure to engineering for autonomous and connected vehicles,” Stevens said.

Now, for the talent side of the equation:

  • MSU is a leading producer of mobility talent in Michigan. Nine out of every 10 MSU engineering students complete internships with companies in Michigan, and two-thirds of engineering graduates go on to work in Michigan. That’s a much higher ratio than peer universities elsewhere in the state. Since MSU provides so much of the engineering talent in Michigan, and because the automotive industry has called Michigan home for more than 100 years, the university is uniquely positioned to turn out graduates prepared to drive the future of mobility. “We really are the plurality supplier of talent in Michigan,” Verboncoeur said. “The mobility industry is the largest industry by far in the state of Michigan. The state thrives with that industry, and we have a responsibility to make sure we provide the best and brightest for that.” Moreover, MSU is a major part of the state’s University Research Corridor, which is the nation’s top university innovation cluster in preparing students for careers in the mobility industry.
  • MSU is preparing mobility talent in a wide range of areas. It’s not only MSU engineering graduates who are making an impact in the mobility industry, of course. Mobility has become increasingly multidisciplinary, with students in computer science, data science, social science and many other fields playing a big role as vehicles evolve. For example, whereas electronics accounted for about 5% of a car’s cost just a few decades ago, that share will soar to 50% by 2030 as vehicle connectivity increases. “There really is a blur between the auto industry and the tech industry,” Stevens said. Through partnerships such as the MSU Mobility Advisory Council, MSU better understands the industry’s needs and is bringing its academic and research excellence to bear in a variety of fields through interdisciplinary collaboration between about 50 researchers within seven different colleges. That all creates frontline training opportunities for students. “When you look at mobility, there has to be an interaction between engineering and business but also social sciences and other parts of the university,” Stevens said. “Michigan State is advancing all types of degrees that the mobility industry needs. Michigan State plays a really important role as part of the development of our talent pipeline.”

Automotive infrastructure has built up in Michigan over the past 100-plus years, and the industry continues to be central to our state’s well-being. Now, as the industry evolves, MSU continues to move in step with the needs and opportunities in Michigan through pioneering research and talent development, as well as new investments that will mold mobility going forward. For example, a new Engineering and Digital Innovation building in the planning stages would further accelerate MSU’s innovative R&D and reinforce the talent pipeline that fuels the heart of the mobility industry in Michigan.

Looking back over the past century of mobility, it was perhaps a happenstance of history that Detroit became the Motor City and Michigan became the hub of automobile manufacturing. But it’s no accident that our state is fast becoming the mobility mecca of the future, too. It’s happening in part because MSU is taking the wheel.

Now is a golden age of opportunity for MSU mobility researchers and students alike.

“The future of mobility is so closely tied to our future in Michigan, what better way to serve the citizens of this state than to make sure we never ever lose our leadership position?” Udpa said.

“Mobility is going to define ways in which we as a society will live for the next 20, 30, 50 years. That technology is happening now.”