Systems and methods for updating the parameters of a model predictive controller with learned operational and vehicle parameters generated using simulations and machine learning

A computer implemented method for determining optimal operational parameters for a model predictive controller for controlling a vehicle, the method comprising:

• determining by a machine learning model, an optimum value for a vehicle parameter, wherein the machine learning model is trained by:
• simulating a vehicle operation across a range of one or more operational parameters by solving a model predictive control problem,
• wherein the range of the one or more operational parameters recovers the vehicle from an unstable state during the simulation within a minimum value and a maximum value of the range,
• wherein the minimum and maximum values of the range correspond to maximum and minimum control input values associated with a performance envelope of the vehicle in performing the vehicle operation;
• determining an output of the model predictive control problem, the output based on a result for the simulated vehicle operation;
• and
• updating the machine learning model based on the output by updating training data with the optimum value for the vehicle parameter;
• and
• revising a control system for the vehicle using the optimum value for the vehicle parameter to control operation of an actuator of the vehicle in performance of the vehicle operation.