Self-driving cars rely on hardware and software to drive down the road without user input. The hardware collects the data; the software organizes and compiles it.This animation explains the basic operation of self-driving vehicles.
source/image(PrtSc): Thomas Schwenke
Self-driving cars combine a variety of sensors to perceive their surroundings, such as radar, lidar, sonar, GPS, odometry and inertial measurement units. Watch the video from Thomas Schwenke for more info:
The challenge for driverless car designers is to produce control systems capable of analyzing sensory data in order to provide accurate detection of other vehicles and the road ahead.
Modern self-driving cars generally use Bayesian simultaneous localization and mapping (SLAM) algorithms, which fuse data from multiple sensors and an off-line map into current location estimates and map updates.
- 1) Sensors (radar, camera, LIDAR, ultrasonic)
- 2) LIDAR as a key component (with lightrays)
- 3) Cameras for obstacle and lane recognition
- 4) GPS and digital maps
- 5) Odometric data and sensors
- 6) Processors (chips) for data fusion