Method and system for risk modeling in autonomous vehicles
A method for adaptive risk modeling for an autonomous vehicle, the method comprising: retrieving parameters of an identified driving mission of the autonomous vehicle; in response to the parameters of the identified driving mission, generating values of: a comparative autonomous parameter, a mix model parameter, a surrounding risk parameter, a geographic operation parameter, and a security risk parameter upon evaluating situational inputs associated with the identified driving mission with a comparative autonomous model, a mix model, a sensor-surrounding model, a geography-dependent model, and a security risk model generated using sensor and supplementary data extraction systems associated with the autonomous vehicle; upon generating values, generating a risk analysis with a rule-based algorithm; and contemporaneously with execution of the identified driving mission, implementing a response action associated with control of the autonomous vehicle, based upon the risk analysis.
1. A method for adaptive risk modeling for a vehicle, the method comprising:
extracting a set of data features from mobile device sensor data, wherein the least one data feature of the set is associated with the vehicle, wherein at least one data feature of the set is associated with an environment of the vehicle;
determining a set of outputs with a set of one or more machine learning models by evaluating the set of extracted data features using the set of machine learning models comprising at least:
a first risk model configured to output a behavioral risk parameter value;
a second geography-dependent model, determined based on aggregated characteristics of driving-related behaviors characterized as acceptable and associated with a specific location, configured to output a geography-dependent parameter value; and
a third model associated with an environment of the vehicle which is configured to output surrounding-risk parameter value,
transforming the set of outputs, with an exposure parameter, into a risk analysis; and
implementing a response action associated with the vehicle based upon the risk analysis, and
wherein the risk analysis enables fleet-wide modifications of vehicle hardware associated with a fleet of vehicles.
2. The method of claim 1 , wherein implementing the response action comprises facilitating insurance processing based on the risk analysis.
3. The method of claim 1 , wherein at least a portion of the set of features is determined based on an onboard computing system onboard the vehicle, wherein the onboard computing system comprises a set of sensors.
4. the method of claim 3 , wherein the vehicle is a truck.
5. The method of claim 4 , wherein the onboard computing system is a mobile device.
6. The medhod of claim 1 , wherein the set of machine learning models evaluates:
a behavioral risk parameter associated with operation of the vehicle;
a traffic parameter associated with an environment of the vehicle;
a geography-dependent parameter associated with the vehicle;
a surrounding-risk parameter associated with an environment of the vehicle; and
a security risk parameter associated with the vehicle.
7. The method of claim 1 , wherein behavioral risk parameter value is determined based on an average driving behavior determined from an aggregated set of drivers.
8. The method of claim 1 , wherein implementing the response action comprises providing the risk analysis to an entity that can perform vehicle-specific modifications of vehicle hardware based on the risk analysis.
9. The method of claim 8 , wherein the vehicle is a truck.
10. The method of claim 9 , wherein the risk analysis enables fleet-wide modifications of vehicle hardware associated with a fleet of trucks, wherein the fleet of trucks comprises the vehicle.
11. The method of claim 1 , wherein the vehicle is operable by a human driver.
12. The method of claim 1 , wherein the exposure parameter is determined based on a driving load of the vehicle.
13. The method of claim 12 , wherein the load is at least one of an expected distance driven per unit time of the vehicle and a mechanical load of the vehicle.