Vehicle position and context detection using V2V communication with application to pre-crash detection and warning

In recent years, there has been growing interest in the design of intelligent transportation systems (ITS) using vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication technologies. These systems allow vehicles to share GPS-based information, such as latitude, longitude, speed and heading, as well as important vehicle data such as brake events, throttle position, turn signal status, etc. A pre-crash detection and warning system in a host vehicle (i.e. vehicle of interest) needs to accurately determine not only the position of each remote vehicle in its vicinity, but also the context of the driving environment because the context can provide important information about whether or not the remote vehicle poses a threat to the host. For example, remote vehicles in the same lane or one lane over typically pose more of a threat than remote vehicles two or more lanes over. In this paper, we propose a real-time algorithm that computes the relative position and driving context of all remote vehicles within a region of interest of the host vehicle. Experimental results on real-world V2V data show that the proposed method can effectively compute the position and context of remote vehicles in real time.