Based on recent advancements put forth by companies like Google and Bosch, the dream of self-driving cars is creeping ever closer to reality. Unfortunately, the technology does still have a ways to go before being completely road ready — but a new system that leverages GPS could speed up the process significantly.
Combining conventional GPS signals with data from a variety of sensors including accelerometers and gyroscopes, this new system can increase the accuracy of in-car satellite navigation systems by 90 percent. Indeed, the system, developed at Spain's Universidad Carlos Ill de Madrid (UC3M) by the Applied Artifical Intelligence Group and the Systems Intelligence Laboratory, can determine a vehicle's position within six feet of its location, reducing the current margin of error, 50 feet, considerably. Best of all, the system can be installed at little cost in any vehicle.
"We have managed to improve the determination of a vehicle's position in critical cases by between 50 and 90 percent, depending on the degree of the signals' degradation and the time that is affecting the degradation on the GPS receiver," said David Martín, a researcher at the Systems Intelligence Laboratory, in a statement.
The biggest obstacle typically faced by conventional GPS systems is loss or disruption of satellite signal because of interference from buildings, trees and tunnels. The new system developed by the researchers at UC3M uses contextual information, as well as an algorithm designed to eliminate deviations caused by loss of signal, to fix this issue.
The researchers see their system being useful in driverless car systems in development, adding that they are currently working on applying the system in scenarios such as cooperative driving, automatic maneuvers, autonomous vehicles and cooperative collision warning systems.
Based on a recent update from Bosch, the addition of this GPS system isn't entirely necessary as the company's self-driving technology is already quite advanced. However, it never hurts to increase accuracy as much as possible.
Edited by
Brooke Neuman
