Researchers at Universidad Carlos III de Madrid (UC3M) have developed a system to is claimed to improve the ability of a GPS to determine a vehicle’s position as compared to that of conventional GPS devices by up to 90%, and which can be installed in any vehicle at low cost.
The system, which is based on sensorial fusion, was jointly designed and developed by the Applied Artificial Intelligence Group (GIAA – Grupo de Inteligencia Aplicada Artificial) and the Systems Intelligence Laboratory (LSI – Laboratorio de Sistemas Inteligentes) at UC3M. The prototype incorporates a conventional GPS signal with those of other sensors (accelerometers and gyroscopes) in order to reduce the margin of error in establishing a location.
The margin of error of a commercial GPS, such as those that are used in cars, is about 15 metres in an open field, where the receiver has wide visibility from GPS satellites. However, in an urban setting, the determination of a vehicle’s position can be off by more than 50 metres, due to the signals bouncing off of obstacles such as buildings, trees, or narrow streets. In certain cases, such as in tunnels, communication is lost, which hinders the GPS’s applications reaching Intelligent Transport Systems.
The greatest problem presented by a commercial GPS in an urban setting is the loss of all of the satellite signals. Commercial receivers partially solve the problem by making use of the urban maps that attempt to position the vehicle approximately but with the new prototype the position is guaranteed to within 1 or 2 metres in urban settings.
A combination of sensors
The basic elements that make up this system are GPS and a low cost Inertial Measurement Unit (IMU). The latter device integrates three accelerometres and three gyroscopes to measure changes in velocity and manoeuvres performed by the vehicle. Then, everything is connected to a computer that has an application that merges the data and corrects the errors in the geographic coordinates.
This software is based on an architecture that uses context information and a powerful algorithm (called Unscented Kalman Filter) that eliminates the instantaneous deviations caused by the degradation of the signals received by the GPS receiver or the total or partial loss of signal.
Currently the researchers have a prototype that they can install in any type of vehicle, shown working on board the IVVI (Intelligent Vehicle based on Visual Information), a real car that has become a platform for research and experimentation at the University.
The objective of the researchers from LSI and UC3M who are working on this “intelligent car” is to be able to capture and interpret all of the information that is available on the road. To do this, they are using optical cameras, infrareds and lasers to detect whether it crosses the lines on the road, or whether there are pedestrians in the vehicle’s path, as well as to adapt speed to the traffic signals and even to analyse the driver’s level of sleepiness in real time.
The next step - make an app
The next step is to analyse the possibility of developing a system that makes use of the sensors that are built into smartphones, since intelligent telephones are equipped with more than ten sensors, such as an accelerometer, a gyroscope, a magnetometer, GPS and cameras, in addition to WiFi, Bluetooth or GSM communications.