cruise autonomous vehicles

Best viewed in portrait mode

How it works

Learn the basics of how a Cruise car navigates city streets safely and efficiently.

Sensors can see 360 degrees, hundreds of feet ahead, and around that double-parked car. Cruise cars make sense of this data in a split second, tracking every important object in view.

Is there room to change lanes? Is it safe to turn left here? Cruise cars consider multiple paths per second, constantly choosing the best ones for unexpected events and changes in road conditions.

Cruise cars tell their wheels and other controls how to move along the selected path and react to changes in it. The result is a ride that’s safe, efficient, and natural-looking to other drivers.

How it drives

Learn how our data visualization tool shaped the future of autonomous driving.

See how Cruise cars can make city streets safer for those on two wheels.

From our experts

Building the Most Advanced AV

Accelerating AV Development

Creating the AV Ecosystem

Mon Jul 11 2022

IEEE Spectrum: What’s the Tech Background of an Autonomous-Vehicle Engineer?

Tue Mar 08 2022

Building Continuous Integration & Continuous Delivery for Autonomous Vehicles on Google Cloud

Thu Mar 03 2022

The Robot Report: Cruise’s VP of robotics on SF robotaxi operations

Sun Jul 04 2021

VentureBeat: The lessons we learn from self-driving will drive our robotics future

Tue Feb 09 2021

@kvogt 🧵 Annual DMV report and how our ongoing SW updates help improve AV performance

Wed Sep 30 2020

How Cruise Uses Simulation To Speed Up Our Sensor Development

Cruise lays out its plan for ‘how’ it will make robotaxis a reality

The string of engineers who spoke Thursday night during a deep dive into Cruise’s autonomous vehicle technology never mentioned Tesla’s name. They didn’t have to, although the message was clear enough.

GM’s self-driving subsidiary Cruise presented a technical and deployment roadmap — at a granular level — that aimed to show how it has built autonomous vehicles that are safer and more scalable than any human-driven vehicle, including those equipped with advanced driver assistance systems.

While Cruise was clearly making a case for its own technology (not to mention trying to recruit fresh talent), the event was also an argument for autonomous vehicles in general. Each engineer or product lead who spoke Thursday presented various components, from how it uses simulations and the development of its own chips and other hardware to the design of its app and the vehicle itself.

The branded “Under the Hood” event built off of comments CEO Dan Ammann made last month during GM’s investor day, in which he laid out the company’s plan to launch a commercial robotaxi and delivery service starting with retrofitted Chevy Bolts and eventually scaling to an army of tens of thousands of purpose-built Origin AVs on the road over the next few years.

Cruise just gained approval in California to perform commercial delivery services, and is still one permit away from being able to charge for driverless ride-hailing . Still, Cruise thinks it’ll be able to drive down costs enough to scale up and out quickly.

Here’s how.

Using simulations to scale, not just verify the system

Cruise is relying on simulations not only to prove out its safety case, but also to scale to new cities without having to perform millions of miles of tests in them first.

The company will still have to map the cities it enters. But it won’t have to remap cities to track changes to the environment that inevitably happen, like lane changes or street closures. When Cruise goes to new cities, it starts with a technology it calls WorldGen, which it says does accurate, large-scale generation of entire cities, “from their quirky layouts to the smallest details,” which allows engineers to test out new operational design domains, according to Sid Gandhi, technical strategy lead of simulation at Cruise. In other words, WorldGen becomes the stage where the future simulations are set.

To ensure optimal world creation, Cruise takes into account things like lighting at 24 different unique times of day and weather conditions, even going as far as to systematically measure light from a range of street lamps in San Francisco.

“When we combine a high-fidelity environment with a procedurally generated city, that’s when we unlock the capability to efficiently scale our business to new cities,” said Gandhi.

He then laid out the technology for the “Road to Sim,” which transforms into editable simulation scenarios real events that have been collected by AVs on the road. This ensures that the AV doesn’t regress by testing against scenarios it has already seen.

“The Road to Sim combines information from perception with heuristics learned from our millions of real-world miles to recreate a full simulation environment from road data,” said Gandhi. “Once we have the simulation, we can actually create permutations of the event and change attributes like vehicle and pedestrian types. It’s a super easy and extremely powerful way to build test suites that accelerate AV development.”

For specific scenarios that Cruise hasn’t been able to collect in real-world road conditions, there’s Morpheus. Morpheus is a system that can generate simulations based on specific locations on the map. It uses machine learning to automatically enter as many parameters as it wants to generate thousands of interesting and rare scenarios against which it tests the AV.

“As we work on solving the longtail, we’ll rely less and less on real-world testing because when you have an event that happens rarely, it takes thousands of road miles to test it properly, and it’s just not scalable,” said Gandhi. “So we’re developing technology to scalably explore large-scale parameter spaces to generate test scenarios.”

Test scenarios also include simulating the way other road users react to the AV. Cruise’s system for this is called non-player character (NPC) AI, which is usually a video game term, but in this context, refers to all of the cars and pedestrians in a scene that represent complex multi-agent behaviors.

“So Morpheus, Road to Sim and NPC AI work together in this really thoughtful way to let us perform more robust testing around rare and difficult events,” said Gandhi. “And it really gives us the confidence that we can solve rare issues now and in future similar issues, as well.”

Generating synthetic data helps the Cruise AV target specific use cases, said Gandhi, pointing specifically to identifying and interacting with emergency vehicles, presumably for no other reason than to take a dig at Tesla, whose Autopilot ADAS system has come under federal scrutiny for repeated crashes into emergency vehicles .

“Emergency vehicles are rare compared to other types of vehicles, but we need to detect them with extremely high accuracy, so we use our data generation pipeline to create millions of simulation images of ambulances, fire trucks and police cars,” said Gandhi. “In our experience targeted synthetic data is about 180 times faster than collecting road data, and millions of dollars cheaper. And with the right mix of synthetic and real data, we can increase relevant data in our data sets by an order of magnitude or more.”

Two custom silicon chips developed in-house

During GM’s investor day in October, Cruise CEO Dan Ammann outlined the company’s plan to invest heavily into the compute power of the Origin in order to decrease costs by 90% over the next four generations so it can scale profitably. At the time, Ammann mentioned Cruise’s intention to manufacture custom silicon in-house to cut costs, but didn’t admit outright using that silicon to build a chip — but TechCrunch had its theories . On Thursday, Rajat Basu, chief engineer for the Origin program, validated those theories.

“Our fourth-generation compute platform will be based on our in-house custom silicon development,” said Basu. “This is purpose-built for our application. It enables focus and improves processing capability, while significantly reducing piece costs and power consumption. Compute is a critical system from a safety perspective, and has redundancy built into it. Add to that an AV system that is processing up to 10 gigabits of data every second, we end up consuming a fair amount of power. Our MLH chip allows us to run our complex machine learning pipelines in a much more focused manner, which in turn helps us to be more energy efficient without compromising on performance.”

Cruise’s AI team developed two chips: The sensor processing chip will handle edge processing for the range of sensors like cameras, radar and acoustics. The second chip, which is designed to be a dedicated neural network processor, supports and accelerates machine learning applications like those large, multitask models developed by the AI team. Basu says the machine learning accelerator (MLA) chip is just the right size to solve exactly a certain class of neural net and ML applications, and nothing more.

“This keeps the performance at an extremely high level, and it ensures that we are not wasting energy on doing anything that is not value added for us,” said Basu. “It can be paired with multiple external hosts or operate standalone. It supports single Ethernet networks up to 25G with a total bandwidth of 400G. The MLA chip we’re putting into volume production is just the start. Over time we will continue to make this even higher-performing while reducing power consumption.”

The Cruise ecosystem

One thing Cruise made clear during its event is that it hasn’t just thought of the AV tech needed to scale up successfully, but also the entire ecosystem, which includes things like remote assistance operators to validate the AV’s decision when it comes across unknown scenarios, customer service, a vehicle that people actually want to ride around in and an app that can efficiently and easily handle things like customer support and incidence response.

“To truly cross the chasm from research and development to a beloved product requires more than just artificial intelligence and robotics,” said Oliver Cameron, Cruise’s VP of product, at the event. “A safe self-driving vehicle alone is insufficient and simply the first step on a long, long journey. To truly build and scale a competitive product that is adopted by millions into their daily lives, you need to build a host of differentiated features and tools atop a safe self-driving foundation. How these features need to be implemented is non-obvious, especially if your company’s still heads-down solving safety issues.”

• Autonomous Cars /

Cruise is now testing fully driverless cars in San Francisco

The gm-backed company is one of the first to launch level 4 vehicles in a dense, complex urban setting.

By Andrew J. Hawkins , transportation editor with 10+ years of experience who covers EVs, public transportation, and aviation. His work has appeared in The New York Daily News and City & State.

Share this story

Cruise, the self-driving car company affiliated with General Motors and Honda, is testing fully driverless cars, without a human safety driver behind the steering wheel, in San Francisco. The company is among the first to test its driverless vehicles in a dense, complex urban environment.

“Getting to driverless in SF took more than five years of rigorous testing, over 2 million miles of driving in one of the craziest driving environments, together with hard work from a huge team of dedicated engineers and others across Cruise, as well as at GM,” Cruise CEO Dan Ammann said in a call with reporters. “And not to mention several billion dollars of investment along the way.”

To be sure, the vehicles are not completely alone in the wilderness. In a video released by the company, a Cruise employee is seen in the passenger seat while the car drives itself through the darkened streets of San Francisco. Cruise’s vehicles all have an emergency switch in the center channel near the gear shift in case something goes wrong, and they are also monitored remotely by Cruise employees. Asked whether remote operators are able to take control of the vehicle when needed, Ammann declined to answer.

“The safety operator has the ability to bring the vehicle to a stop in the event of an emergency, but does not have access to standard driver controls,” a spokesperson said. “Eventually, this safety operator will be fully removed.”

Cruise was approved to test fully driverless cars (also called Level 4 in industry parlance) in California on October 15th. According to the DMV, Cruise can only test five driverless vehicles “on specified streets within San Francisco.” The vehicles are not allowed to exceed 30 mph, and can’t operate during heavy fog or heavy rain.

Cruise was the fifth company to receive a driverless permit from the state’s Department of Motor Vehicles, the others being  Waymo ,  Nuro ,  Zoox , and AutoX. Currently, 60 companies have an active permit to test autonomous vehicles with a safety driver in California.

This is the first time that Cruise has demonstrated its Level 4 capabilities

This is the first time that Cruise has demonstrated its Level 4 capabilities. Its main rival, Google spinoff Waymo, has been testing its fully driverless vehicles in Phoenix for over a year, and recently announced it would be making its Level 4 taxi service available to more customers. Cruise doesn’t allow non-employees to ride in its vehicles. The company had planned to launch a commercial taxi service in 2019  but failed to do so , and it has yet to publicly commit to a new date.

Last year,  Cruise unveiled the Cruise Origin , a fully driverless prototype vehicle without a steering wheel, pedals, or any controls typically associated with human driving. The vehicle, which will go into production at GM’s Detroit-Hamtramck plant , is built to be shared by multiple passengers — though it remains to be seen how much appetite there is for shared vehicles in a post-COVID world. Cruise recently unveiled a new set of safety protocols intended to keep people socially distant during trips and the vehicle sanitized between fares.

The news that the company will be relying less on its operations staff during its testing comes after Cruise’s safety drivers have  complained about a lack of safety standards  during the pandemic and subsequent wildfires. They accuse Cruise of deploying its self-driving cars during the spring lockdown  in defiance of public health orders  banning nonessential travel. And they say Cruise isn’t doing enough to keep them safe during these public health crises.

3 Body Problem VR headset review: magical tech in need of more apps

32°n’s liquid-lens sunglasses transform into reading glasses with a swipe, the biggest new battle royale is ready for your phone, how to find any file on windows, ‘even stronger’ than imagined: doj’s sweeping apple lawsuit draws expert praise.

More from Transpo

Scout Motors wants to put the ‘mechanical’ back into electric trucks

Lucid slashes prices for its luxury EVs for the third time in seven months

GM is preparing for another major expansion of its hands-free Super Cruise system

Tesla’s latest update takes aim at cold weather woes

• Share full article

Advertisement

Supported by

G.M.’s Cruise Moved Fast in the Driverless Race. It Got Ugly.

Cruise has hired a law firm to investigate how it responded to regulators, as its cars sit idle and questions grow about its C.E.O.’s expansion plans.

By Tripp Mickle ,  Cade Metz and Yiwen Lu

Tripp Mickle, Cade Metz and Yiwen Lu have been reporting throughout the year on the rollout of robot taxis in San Francisco.

Two months ago, Kyle Vogt, the chief executive of Cruise, choked up as he recounted how a driver had killed a 4-year-old girl in a stroller at a San Francisco intersection. “It barely made the news,” he said, pausing to collect himself. “Sorry. I get emotional.”

To make streets safer, he said in an interview, cities should embrace self-driving cars like those designed by Cruise, a subsidiary of General Motors. They do not get distracted, drowsy or drunk, he said, and being programmed to put safety first meant they could substantially reduce car-related fatalities.

Now Mr. Vogt’s driverless car company faces its own safety concerns as he contends with angry regulators, anxious employees, and skepticism about his management and the viability of a business that he has often said will save lives while generating billions of dollars.

On Oct. 2, a car hit a woman in a San Francisco intersection and flung her into the path of one of Cruise’s driverless taxis . The Cruise car ran over her, briefly stopped and then dragged her some 20 feet before pulling to the curb, causing severe injuries.

California’s Department of Motor Vehicles last week accused Cruise of omitting the dragging of the woman from a video of the incident it initially provided to the agency. The D.M.V. said the company had “misrepresented” its technology and told Cruise to shut down its driverless car operations in the state.

Two days later, Cruise went further and voluntarily suspended all of its driverless operations around the country, taking 400 or so driverless cars off the road. Since then, Cruise’s board has hired the law firm Quinn Emanuel to investigate the company’s response to the incident, including its interactions with regulators, law enforcement and the media.

The board plans to evaluate the findings and any recommended changes. Exponent, a consulting firm that evaluates complex software systems, is conducting a separate review of the crash, said two people who attended a companywide meeting at Cruise on Monday.

Cruise employees worry that there is no easy way to fix the company’s problems, said five former and current employees and business partners, while its rivals fear Cruise’s issues could lead to tougher driverless car rules for all of them.

Company insiders are putting the blame for what went wrong on a tech industry culture — led by the 38-year-old Mr. Vogt — that put a priority on the speed of the program over safety. In the competition between Cruise and its top driverless car rival, Waymo, Mr. Vogt wanted to dominate in the same way Uber dominated its smaller ride-hailing competitor, Lyft.

“Kyle is a guy who is willing to take risks, and he is willing to move quickly. He is very Silicon Valley,” said Matthew Wansley, a professor at the Cardozo School of Law in New York who specializes in emerging automotive technologies. “That both explains the success of Cruise and its mistakes.”

When Mr. Vogt spoke to the company about its suspended operations on Monday, he said that he did not know when they could start again and that layoffs could be coming, according to two employees who attended the companywide meeting.

He acknowledged that Cruise had lost the public’s trust, the employees said, and outlined a plan to win it back by being more transparent and putting more emphasis on safety. He named Louise Zhang, vice president of safety, as the company’s interim chief safety officer and said she would report directly to him.

“Trust is one of those things that takes a long time to build and just seconds to lose,” Mr. Vogt said, according to attendees. “We need to get to the bottom of this and start rebuilding that trust.”

Cruise declined to make Mr. Vogt available for an interview. G.M. said in a statement that its “commitment to Cruise with the goal of commercialization remains steadfast.” It said it believed in the company’s mission and technology and supported its steps to put safety first.

Mr. Vogt began working on self-driving cars as a teenager. When he was 13, he programmed a Power Wheels ride-on toy car to follow the yellow line in a parking lot. He later participated in a government-sponsored self-driving car competition while studying at the Massachusetts Institute of Technology.

In 2013, he started Cruise Automation. The company retrofitted conventional cars with sensors and computers to operate autonomously on highways. He sold the business three years later to G.M. for $1 billion .

After the deal closed, Dan Ammann, G.M.’s president, took over as Cruise’s chief executive, and Mr. Vogt became its president and chief technology officer.

As president, Mr. Vogt built out Cruise’s engineering team while the company expanded to about 2,000 employees from 40, former employees said. He championed bringing cars to as many markets as fast as possible, believing that the speedier the company moved, the more lives it would save, former employees said.

In 2021, Mr. Vogt took over as chief executive. Mary T. Barra, G.M.’s chief executive, began including Mr. Vogt on earnings calls and presentations, where he hyped the self-driving market and predicted that Cruise would have one million cars by 2030.

Mr. Vogt pressed his company to continue its aggressive expansion, learning from problems its cars ran into while driving in San Francisco. The company charged an average of $10.50 per ride in the city.

After a Cruise vehicle collided with a Toyota Prius driving in a bus lane last summer, some people at the company proposed having its vehicles temporarily avoid streets with bus lanes, former employees said. But Mr. Vogt vetoed that idea, saying Cruise’s vehicles needed to continue to drive those streets to master their complexity. The company later changed its software to reduce the risk of similar accidents.

In August, a Cruise driverless car collided with a San Francisco fire truck that was responding to an emergency. The company later changed the way its cars detect sirens .

But after the crash, city officials and activists pressured the state to slow Cruise’s expansion. They also called on Cruise to provide more data about collisions, including documentation of unplanned stops, traffic violations and vehicle performance, said Aaron Peskin, president of San Francisco’s Board of Supervisors.

“Cruise’s corporate behavior over time has increasingly led to a lack of trust,” Mr. Peskin said.

With its business frozen, there are concerns that Cruise is becoming too much of a financial burden on G.M. and is hurting the auto giant’s reputation. Ms. Barra told investors that Cruise had “tremendous opportunity to grow” just hours before California’s D.MV. told Cruise to shut down its driverless operations.

Cruise has not collected fares or ferried riders in more than a week. In San Francisco, Phoenix, Dallas, Houston, Miami, and Austin, Texas, hundreds of Cruise’s white and orange Chevrolet Bolts sit stagnant. The shutdown complicates Cruise’s ambition of hitting its goal of $1 billion of revenue in 2025.

G.M. has spent an average of $588 million a quarter on Cruise over the past year, a 42 percent increase from a year ago. Each Chevrolet Bolt that Cruise operates costs $150,000 to $200,000, according to a person familiar with its operations.

Half of Cruise’s 400 cars were in San Francisco when the driverless operations were stopped. Those vehicles were supported by a vast operations staff, with 1.5 workers per vehicle. The workers intervened to assist the company’s vehicles every 2.5 to five miles, according to two people familiar with is operations. In other words, they frequently had to do something to remotely control a car after receiving a cellular signal that it was having problems.

To cover its spiraling costs, G.M. will need to inject or raise more funds for the business, said Chris McNally, a financial analyst at Evercore ISI. During a call with analysts in late October, Ms. Barra said G.M. would share its funding plans before the end of the year.

Tripp Mickle reports on Apple and Silicon Valley for The Times and is based in San Francisco. His focus on Apple includes product launches, manufacturing issues and political challenges. He also writes about trends across the tech industry, including layoffs, generative A.I. and robot taxis.  More about Tripp Mickle

Cade Metz is a technology reporter and the author of “Genius Makers: The Mavericks Who Brought A.I. to Google, Facebook, and The World.” He covers artificial intelligence, driverless cars, robotics, virtual reality and other emerging areas. More about Cade Metz

Yiwen Lu reports on technology for The New York Times. More about Yiwen Lu

Driverless Cars and the Future of Transportation

An Appetite for Destruction: A wave of lawsuits argue that Tesla’s Autopilot software is dangerously overhyped. What can its blind spots teach us about Elon Musk, the company’s erratic chief executive ?

Along for the Ride: Here’s what New York Times reporters experienced during test rides in driverless cars operated by Tesla , Waymo  and Cruise .

The Future of Transportation?: Driverless cars, once a Silicon Valley fantasy, have become a 24-hour-a-day reality in San Francisco . “The Daily” looked at the unique challenges of coexisting with cars that drive themselves .

Stressing Cities: In San Francisco and Austin, Texas, where passengers can hail autonomous taxis, the vehicles are starting to take a toll on city services , even slowing down emergency response times.

A Fast Rise and Fall: Cruise, a subsidiary of General Motors, wanted to grow fast. Now, the company faces safety concerns  as it contends with angry regulators, anxious employees and skepticism about the viability of the business .