Self-driving car (known also as an autonomous car, driverless car, robotic car) is a vehicle that is capable of sensing its environment and navigating without human input.
Self-driving cars detect surroundings using radar, lidar, GPS, Odometry, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage.
Autonomous cars have control systems that are capable of analyzing sensory data to distinguish between different cars on the road, which is very useful in planning a path to the desired destination.
There is a classification systems for the self-driving cars, adopted in the United States, based on the parameters:
- Level 0: The driver completely controls the vehicle at all times.
- Level 1: Individual vehicle controls are automated, such as electronic stability control or automatic braking.
- Level 2: At least two controls can be automated in unison, such as adaptive cruise control in combination with lane keeping.
- Level 3: The driver can fully cede control of all safety-critical functions in certain conditions.
- Level 4: The vehicle performs all safety-critical functions for the entire trip, with the driver not expected to control the vehicle at any time.
General Principles
Some of the robot cars are not equipped with a steering wheel or pedals. This is a 100% self-driven vehicle and is 100% independent from a human influence. So the human effect on the driving is practically zero.
But the most of the existed autonomous cars are equipped with a steering wheel and pedals as an additional safety tools. In this type of cars human is able to take control on the car at any time, for example to prevent the traffic accident or just to enjoy the driving.
Technology used
These type of cars are equipped with lots of sensitive sensors and special smart software for collecting and analysing the received data and monitoring and management of the self-driving car movement or „reaction“ on the road. The software is able to take decisions and start the relevant safety procedure for time less than a second (which is not possible for the human brain).
Image source: www.economist.com
The main compulsory tools and gadgets in each self-driving cars are:
- Laser sensors – they help the cars to receive a 360 degree information about the environment, so the car can sense objects in front of the car, behind the car or beside the car (including information about objects in the blind spots in a traditional cars).
- Position sensors – usually they are located in the wheels. Base on these sensors car can detects the rotation and understand what is the car actual position on the road and according the other objects on the road.
- Orientation sensors – they are about motion and balance and gave additional information of the car about it orientation. So the car receive something like 3D model of the environment and the exact car position at any time and coordination.
- Processor – this is a brain of the car. It’s a smart computer brain (specially developed sftware) that collect and analyse all data received from the sensors. The processor takes decision what, when and how the car do just to be safe, follow the traffic regulation, communicate with the rest of the vehicles or pedestrians and reach the final destination at time.
- Radar sensors detect cars far ahead and calculates their speed of movement, so the can can slow down its speed or stop on time if it is needed.
- GPS system is accurate to within a few meters, so it’s remarkable the car can even stay in the right lane, let alone avoid collisions.
How self-driving cars detect and avoid obstacles
Lots of additional tools helps these smart cars to receive data from the traffic lights to understand if there is a traffic jam, so they can pre calculate their speed of movement (or even the direction) just to select the best time to reach the junction (for example second before the green light is on).
Image source: www.sharpheels.com
Some of them are equipped even with sonar devices and stereo cameras (additional to the mentioned above systems). All these components have different ranges and fields of view, so the combination of all of them give the car perfect orientation in the environment.
Google car, for example use LIDAR system bolted to the top of Google’s self-driving car. This is highly accurate system with a range up to 100 meters. There are a few detection technologies on the car that work at greater distances, but not with the kind of accuracy you get from a laser.