How self-driving car works

Self-driving vehicles are cars or trucks during which human drivers are never required to require control to securely operate the vehicle.


Currently, there are not any legally operating, fully-autonomous vehicles within the us . There are, however, partially-autonomous vehicles—cars and trucks with varying amounts of self-automation, from conventional cars with brake and lane assistance to highly-independent, self-driving prototypes.

Though still in its infancy, self-driving technology is becoming increasingly common and will radically transform our transportation (and by extension, our economy and society). supported automaker and technology company estimates, level 4 self-driving cars might be purchasable within the next several years (see the callout box for details on autonomy levels).

How they work

Various self-driving car technologies are developed by Google, Uber, Tesla, Nissan, and other major automakers, researchers, and technology companies.

While design details vary, most self-driving systems create and maintain an indoor map of their surroundings, supported a good array of sensors, like radar. Uber’s self-driving prototypes use sixty-four laser beams, alongside other sensors, to construct their internal map; Google’s prototypes have, at various stages, used lasers, radar, high-powered cameras, and sonar.

Software then processes those inputs, plots a path, and sends instructions to the vehicle’s “actuators,” which control acceleration, braking, and steering. Hard-coded rules, obstacle avoidance algorithms, predictive modeling, and “smart” object discrimination (for example, knowing the difference between a bicycle and a motorcycle) help the software follow traffic rules and navigate obstacles.

Partially-autonomous vehicles may require a person's driver to intervene if the system encounters uncertainty; fully-autonomous vehicles might not even offer a wheel .

Most prototypes don't currently have this capability.