Intelligent vehicle action decisions

A computer program product comprising:

• a computer readable storage medium readable by one or more processing circuit and storing instructions for execution by one or more processor for performing a method comprising:
• obtaining sensor data from sensors disposed to output data indicative of vehicle driver performance of a first vehicle, the first vehicle having for a first trip an associated first driver user who drives the first vehicle during the first trip;
• processing the sensor data to return error event flags that indicate errors of the first driver user when driving the first vehicle during the first trip;
• recording for respective event flags of the error event flags values of a first driving environment classification parameter and values of a second driving environment classification parameter;
• predicting a driving performance of the first driver user for a second trip, the second trip being a proposed trip to occur after the first trip, the predicting being in dependence on the error event flags, the values of a first driving environment classification parameter and the values of a second driving environment classification parameter, wherein the error event flags, the values of a first driving environment classification parameter and the values of a second driving environment classification parameter define historical driving performance data of the first driver user, wherein the second trip is proposed for performance by a motor vehicle being driven by the first driver user;
• and
• returning an action decision in dependence on the predicting, wherein the action decision includes an action decision to limit performance of the motor vehicle so that performance of the motor vehicle is modified when driven by the first driver user.

A system comprising:

• a memory;
• at least one processor in communication with memory;
• and
• program instructions executable by one or more processor via the memory to perform a method comprising:
• obtaining sensor data from sensors disposed to output data indicative of vehicle driver performance of a first vehicle, the first vehicle having for a first trip an associated first driver user who drives the first vehicle during the first trip;
• processing the sensor data to return error event flags that indicate errors of the first driver user when driving the first vehicle during the first trip;
• recording for respective event flags of the error event flags values of a first driving environment classification parameter and values of a second driving environment classification parameter;
• predicting a driving performance of the first driver user for a second trip, the second trip being a proposed trip to occur after the first trip, the predicting being in dependence on the error event flags, the values of a first driving environment classification parameter and the values of a second driving environment classification parameter, wherein the error event flags, the values of a first driving environment classification parameter and the values of a second driving environment classification parameter define historical driving performance data of the first driver user, wherein performing the predicting includes using a predictive model that has been trained by machine learning processes including application of iteratively applied sets of training data, wherein respective applied sets of training data for respective iteration of the iteratively applied set of training data include (a) an environment condition values dataset specifying environmental conditions for the first vehicle for a time segment of the first trip;
• and (b) an error event flag dataset specifying error events of the first driver user during the time segment of the first trip;
• and
• returning an action decision in dependence on the predicting.