Like the Holy Grail in the medieval times, the GRAIL system provides a long-sought solution for deploying an intelligent and efficient interaction between vehicles and Vulnerable Road Users (VRUs), namely pedestrians and cyclists. GRAIL stands for GReen Assistant Interfacing Light, aiming at increasing road safety and reassuring VRUs when crossing the street. Let’s consider the situation depicted in figure 1, where a couple of pedestrians are standing at the curb on a pedestrian crossing while looking for eye contact with the driver of the oncoming car. Definitely, the couple will not start crossing until they observe some signal indicating that the car is giving way to them. A camera installed onboard the DRIVERTIVE car identifies the pedestrians standing at the curb and looks for their gaze direction. The system relies on a deep-learning based technique for detecting the pedestrians body parts from color images. The different key-points are detected, and the entire body skeleton is built based on those. Several deep-learning based systems have been tested, such as OpenPose and Detectron, an extension of the Faster-R-CNN model for pedestrian detection, even if they are riding on a bicycle. Thus, GRAIL has the ability to perform an analysis of the pedestrians’ dynamics, thus providing the grounds for predicting the most likely pedestrians’ trajectory and movements in the next second.
Figure 1. Pedestrians waiting to cross at a pedestrian crossing while looking for eye contact with the driver of an oncoming car.
In order to increase VRUs reassurance, the automated system developed by the University of Alcalá (UAH) performs two actions in parallel that contribute to improve the interaction between the car and the VRUs. On the one hand, the vehicle starts to decrease its speed significantly as soon as those pedestrians are detected by the on-board camera system. On the other hand, the GRAIL system, an array of green diodes located in the front of the vehicle (as shown in figure 2), is turned on.
Figure 2. GRAIL system shown in detail. An array of green diodes located in the front part of the vehicle is turned on whenever a VRU is detected on the curb.
The combination of both actions, vehicle deceleration and green light coming on, provides a distinct sign to VRUs, indicating that the situation is safe for them to start crossing the street. In this regard, GRAIL is a unique interface between vehicles and VRUs aiming at providing an advanced and intelligent interaction between them, yielding an increase in road safety. The system has been successfully tested on the Campus of the University of Alcalá (UAH), located in the city of Alcalá de Henares (Spain). Likewise, it was exhibited and demonstrated in the conference that the SEGVAUTO project organized in Madrid in November 2016. Currently, GRAIL is being adapted and fine-tuned in order to be exhaustively tested in private proving grounds. Their contribution to road safety by means of an intelligent interaction between vehicles and VRUs is expected to become really relevant in the coming years, as long as car makers decide to integrate this technology in their mass-produced models. The operation of the GRAIL system is graphically illustrated in the video that can be seen at: https://youtu.be/pfDrxVbVcto
Spanish 
English