CPC B60R 21/01338 (2014.12) [G06N 3/08 (2013.01); G08G 1/0112 (2013.01); G08G 1/0133 (2013.01)] | 20 Claims |
1. A method comprising:
receiving a first set of sensor measurements from one or more sensors of a mobile device positioned within a vehicle, wherein the one or more sensors of the mobile device comprise an accelerometer sensor and a global positioning service (GPS) sensor, and wherein sensor measurements of the first set of sensor measurements are associated with a collision of the vehicle;
generating a crash feature vector from the first set of sensor measurements;
executing a machine learning model using the crash feature vector to generate one or more outputs that are partially indicative of a point-of-impact of the collision;
generating, from the one or more outputs of the machine learning model, a prediction of the point-of-impact of the collision on the vehicle; and
transmitting an indication of the point-of-impact to a remote device.
|