Using Artificial Intelligence to Create a Low Cost Self-driving Car
Liceul Tehnologic Oltchim, Ramnicu Valcea, ROMANIA
The purpose is the creation of an autonomous car which should be able to drive without any driver in the urban areas. In 2004 road accidents caused 2.5 million deaths worldwide and 50 million injured. Most of the studies found that 87% of crashes were due solely to driver factors. In order to realize this, several concurrent software applications process data using Artificial Intelligence to recognize and propose a path which the car should follow.
Two years ago, Google created the world's first self-driving car. The Google self-driving car problem is caused by using a very expensive 3D radar ($75,000), with a high resolution. The 3D radar is used to create a high resolution 3D map. My solution is a minimal 3D radar that would only cost $4000 and 3 special cameras mounted to recognize from images the traffic lanes, curbs and real time position of the car instead of the 3D radar.
Parallel and distributed algorithms use AI to recognize traffic signs, demarcation lanes and to calculate exactly or using probabilities the position of the car on the road, where the roadsides are and to propose a new direction even in the absence of traffic lanes. They process the data from a 3D radar, create a 3D map using OpenGL, using GPS coordinates and particle filters, localize the car on Google Maps, the management of a common database with traffic signs, acceleration sensors, a distributed software, a supervisory system and the software which drives the stepper motor to turn the steering wheel.
A driverless car can reduce the distance between the cars, lowering the degree of road loadings, reducing the number of traffic jams, avoiding human errors, and allowing disabled people to drive. The traffic jams will be shorter and parking places will be freer. A lot of fuel will be saved.