2. Introduction
A self-driving car is a vehicle that is capable of sensing its
environment and navigating without human input. Self-driving
cars can detect surroundings, using a variety of techniques such
as radar, GPS, and computer vision.
3. Some History
▶ Experiments have been started on automating cars since 1920.
▶ First experimental vehicle took place in 1950.
▶ The first self-sufficient and truly autonomous car appeared in 1980.
5. Classifications by SAE(society of automotive engineers)
Classifications of system based on six different levels (like manually to full automated systems)was
published in 2014 by SAE International.
SAE level Name Execution of
Steering
Monitoring
of driving
Env
Fallback performance
of dynamic driving
task
System
Capability(Driving
Modes)
0 No
Automation
Human Driver Human
Driver
Human driver NA
1 Driver
Assistance
Human Driver
& system
Human
Driver
Human Driver Some driving
modes
2 Partial
Automation
System Human
Driver
Human Driver Some Driving
Modes
9. Processors
● At least 7 dual-core 2.13 Ghz processors and 2 Gb of RAM are needed to
make sense of data collected by the car’s instruments.
● Some cars run as many as 17 processors to distributes the computing
loads.
10. Algorithms: low Level
● Image Processing(Edge Detection and Image Classification).
● LIDAR Processing (a surveying method that measures distance to a target by
illuminating the target with pulsed laser light and measuring the reflected pulses
with a sensor).
● Radar Processing(its an object-detection system that uses radio waves to
determine the range, angle, or velocity of objects).
11. Algorithms: High Level
● Feature Extraction(Road markings such as lines, arrows, and crosses ).
● Object classification(classifies objects into car, pedestrian, bicyclist and background).
● Obstruction identification.(detected obstacle points can be mapped onto convenient projection planes for
motion planning)
● Mapping and localization(The Simultaneous Localization and Mapping (SLAM) techniques).
● Dynamics modelling(The model is suitable for lane-keeping control and obstacle avoidance).
● Traffic signal.
● Sign detection And Classification.
● Path planning and decision making.