An Automatic eCall System for Two-Wheeled Vehicles via Smartphone Sensors

The automatic emergency calls (eCalls) activation plays a crucial role in increasing the speed of medical assistance intervention, hence the chances of survival of the people involved in severe accidents. This work illustrates an innovative, affordable and easy-to-use smartphone based application for automatic crash detection and eCall forwarding meant for powered two-wheeled vehicles. The proposed algorithm consists essentially in two finite state machines (FSM), that estimate the rider's state and monitor the crash occurrence, forwarding the eCall based on the accident predicted severity. The activation of the FMS different states mainly depends on the driver's torso orientation, on the three measured accelerations and on the GPS speed. The algorithm parameters have been tuned empirically and tested in different scenarios, including normal driving, simulated and real crashes, with different smartphone positions and orientations. The proposed solution proves to be very effective when the smartphone is placed in a pocket of the jacket: indeed, in the experiments carried out with this configuration, the eCall system never triggers false positives or negatives.