How does Autonomous cars work?

Every Year 1.2 million people die on roads, and these accsident are caused by human mistakes.
So what we can do to get rid of these accsidents and create a whole new safe driving experience for our future genaration. Self driving cars are solution to those problems. Google invested $70 billion USD in a project called waymo (Google self driving car project). Tesla, BMW, Audi these companies are also making significant contribution to self driving car industry. Tesla Model S and Model X has Autonomous car feature of level 2 or 3 since 2014.

Self driving cars have these core components -

• Computer vision
• Sensor
• Localization
• Path planning
• Control

Cameras are computer vision that find lane lines and others vechiles or moving things on the road.

Sensors like radar, lasers collects data to build strong understanding of the cars enviroment.
 Localization includes our current location in the world using GPS and surrounding of the envroment. GPS are now advance enough to localize itself to 1-2 centimeters.

The vechiel’s internal map includes current and predicted location of all static and moving objects
Ob. Obstacles are categorized depending on how well they match up with a library of pre-determined shape and motion descriptors.

To make any navigation decisions, the vehicle must first build a map of its environment. The vechile uses cameras and range finders to localize it self. A laser rangefinder scans the environment using swaths and calculates the distance to nearby objects by measuring the time it takes for each laser beam to travel to the object and back. Where video from camera is ideal for extracting scene color, an advantage of laser rangefinders is that depth information is readily available to the vehicle for building a three-dimensional map. Because laser beams diverge as they travel through space, it is difficult to obtain accurate distance readings greater than 100m away using most state-of-the-art laser rangefinders, which limits the amount of reliable data that can be captured in the map. The vehicle filters and discretizes data collected from each sensor and often aggregates the information to create a comprehensive map, which can be used for path planning.

After all these steps we now move to path planning which is essential part of autonomous cars.
Computer get all data from cameras and sensors to know what are their position and predict what they will do. Finally we build a path from all those data to execute a safe journey.

Control is most important part in this list. Once we create our path to safe journey, the vechile needs   to turn the steering wheel and hit the throttle or the brake in order to follow the path.

We'll have a large number of vehicles on roads within 3 years, and be mass producing them in 5.

In an interview by Danish newspaper Borse, Tesla’s founder Elon Musk accelerates his timeline for the introduction of fully autonomous Teslas by 2 years compared to his estimate less than a year ago (October 2014). He now expects fully autonomous Teslas to be ready by 2018 but notes that regulatory approval may take 1 to 3 more years thereafter.

Nissan has publicly stated that they will have self driving cars available for purchase by the year 2020

“Audi introduce a self-driving car by 2020”. Scott Keogh, Head of Audi America announced at the CES 2017.