About Self-Driving

Building a Safer Driver for Everyone

Self-driving vehicles hold the promise to improve road safety and offer new mobility options to millions of people. Whether they’re helping to make our roads safer or helping people run errands, commute to work, or drop kids off at school, fully self-driving vehicles hold enormous potential to transform people’s lives.

Self-Driving Cars And Human Drivers

Are self-driving cars safer than humans?

Distracted driving. Drunk driving. Texting and driving. The road is not as safe as it could be. Self-driving technology can address the way our roads operate and could help save thousands of lives now lost in accidents every year.

Read More FAQs

Levels of Self-Driving Systems

Not all self-driving technology is the same. SAE International, a group of automotive experts from around the world, has developed a 5-level scale to help people distinguish the different systems. This scale has been adopted by the U.S. Department of Transportation.

There is a range of autonomous systems. You might already be familiar with driver assist technology sold in cars today such as adaptive cruise-control or lane-keeping systems, which require constant monitoring by a human driver.

A fully self-driving system is designed to operate without a human driver. Fully self-driving technology includes the software and hardware that, when integrated into the vehicle, can perform all driving functions.

Driver Support: Levels 0, 1, and 2

What Does the Human in the Driver’s Seat Have to Do?
  • You are fully responsible for driving, even if there are driver support features engaged such as “adaptive cruise control” or “lane control.”
  • You must constantly supervise any support features; you must steer, brake, or accelerate as needed to maintain safety.
What Do These Driver Support Features Do?

At Level 0, features are limited to warnings and momentary assistance: blind spot warnings and lane departure warnings.

At Level 1, features provide steering OR brake/acceleration support to the driver: lane centering or adaptive cruise control.

At Level 2, features provide steering AND brake/acceleration support: lane centering and adaptive cruise control working together.

Automated Driving: Levels 3, 4, and 5

What Does the Human in the Driver’s Seat Have to Do?
  • You are not driving, even if you are in “the driver’s seat.”
  • At Level 3, when the vehicle requests, you must drive.
  • At Levels 4 and 5, these fully self-driving vehicles will not require you to take over driving.
What Do These Cars Do?

At Level 3, these vehicles can self-drive under limited conditions and will not operate unless all required conditions are met. You may sometimes be prompted to drive.

At Level 4, like Level 3, these vehicles can self-drive under limited conditions and will not operate unless all required conditions are met. Level 4 vehicles are considered fully self-driving.

At Level 5, these vehicles can self-drive under all conditions. Same as Level 4, but the vehicle can drive anywhere under all conditions.

Higher Levels of Autonomy

Waymo’s fully self-driving technology falls under the category of a Level 4 system. This means that it's fully self-driving technology only operates on roads within certain areas under certain conditions. Waymo calls these “Waymo zones”.

The Vehicle Can Transition to a Safe Stop

Unlike autonomous systems at lower levels, a Level 4 system has the ability to bring a vehicle to a safe stop without a human driver taking over.

This might include situations when:

  • The self-driving system experiences a problem
  • The vehicle is involved in a collision
  • Environmental conditions change in a way that would affect safe driving within Waymo’s zones

Waymo’s system is designed to detect each one of these scenarios automatically and determine an appropriate response, such as pulling over or coming to a safe stop.

Larger Self-Driving Frameworks

Fully self-driving vehicles will realize their potential and gain public acceptance only if they are safe. Waymo relies on data, insights, and intelligence from larger safety frameworks and guidance in order to best serve the public’s need for safer transportation.

Safety Design Elements

In 2017, the National Highway Transportation Safety Administration (NHTSA) released a policy framework, i.e. a set of voluntary recommendations, for the safe deployment of self-driving technology. The guidance, Automated Driving Systems 2.0: A Vision for Safety, outlines 12 essential safety design elements that should be rigorously tested to ensure safety. The framework also includes recommendations for guarding against cyber-attacks.

The U.S. Department of Transportation released an updated guidance in October 2018, Preparing for the Future of Transportation: Automated Vehicles 3.0. The USDOT sees AV 3.0 as a conversation starter for a national discussion about the future of on-road surface transportation system.

Self-Driving Competencies

The U.S. Department of Transportation has recommended that Level 3, Level 4, and Level 5 self-driving vehicles should be able to demonstrate at least 28 core competencies. Waymo’s safety program uses these 28 competencies and more (PDF) to rigorously test thousands of scenario variations, ensuring that Waymo can safely handle the challenges of real-world environments.

Using National Data to Enhance Safety

In 2015, NHTSA published data showing the distribution of the most common pre-crash scenarios. For example, just four crash categories accounted for 84% of all crashes: rear end crashes, vehicles turning or crossing at an intersection, vehicles running off the edge of the road, and vehicles changing lanes. Therefore, avoiding or mitigating those kinds of crashes is an important goal for Waymo’s testing program.

Waymo’s Approach to Safety

Waymo believes that the key to building a safe driver is by building an experienced driver. That’s why Waymo has put its vehicles through the world's longest and toughest ongoing driving test that includes practicing tricky scenarios on closed courses, driving millions of miles on public roads, and accelerating that learning by driving billions more miles in simulation in a virtual world. Before the launch of Waymo’s ride-hailing service in Arizona in 2018, Waymo accelerated the pace of testing at every level.

Vision

To meet the complex demands of autonomous driving, Waymo has developed an array of sensors that allow its vehicles to see 360 degrees, both in daytime and at night, and up to nearly three football fields away.

  • This multi-layered sensor suite—including cameras, radar, and lidar—works together seamlessly to paint a detailed 3D picture of the world.
  • The sensors show pedestrians, cyclists, other vehicles, traffic lights, construction cones, and other road features.

Experience

When it comes to driving, experience is the best teacher, and that experience is even more valuable when it’s varied and challenging. Waymo has more than 10 million miles of on-road experience and nearly 7 billion miles of simulated driving experience in a virtual world. Waymo's technology has been put to the test on its private test track, learning to safely navigate thousands of the most common and most challenging types of pre-crash scenarios.

Navigation

Humans need to look away from the road when using a map or GPS, distracting them from driving. Waymo’s fully self-driving vehicles cross-reference their internal, pre-built 3D maps with real-time sensor data to precisely determine its location on the road. It does all of this without taking its eyes off the road.