Adaptive vehicle control

1. A system comprising:

a controller including a processor and a memory, the memory storing instructions executable by the processor such that the processor is programmed to:

determine, for a vehicle, a first set of control inputs for the vehicle based in part on input data and one or more first reference parameters;

collect operating data from the vehicle while operating according to the first set of control inputs;

determine an estimated state of a state space model for the vehicle based on the operating data from the vehicle while operating according to the first set of control inputs;

determine, based in part on the estimated state of the state space model, a second set of control inputs for the vehicle, such that a cost of operating the vehicle according to the second set of control inputs is reduced relative to the cost of operating the vehicle based on the first set of control inputs;

specify one or more second reference parameters based in part on the second set of control inputs and the input data, such that the one or more second reference parameters, when applied to the input data, results in a third set of control inputs, wherein members of the third set of control inputs are within respective predetermined ranges of corresponding members of the second set of control inputs,

and

operate the vehicle based on at least one of the one or more second reference parameters.

2. The system of claim 1 , wherein the processor is further programmed to:

generate, based on the input data and the operating data, the state space model of the vehicle.

3. The system of claim 2 , wherein the processor is further programmed to:

generate a dynamic model for the vehicle;

estimate a set of parameters correlating individual inputs of the model to the output of the model for the operating condition; and

take into account the set of parameters correlating individual inputs of the model to the output of the model for determining the second control input.

4. The system of claim 3 , wherein the processor is further programmed to:

apply a regularized least squares method for estimating the set of parameters.

5. The system of claim 1 , wherein the processor is further programmed to:

apply a Kalman filter to estimate the state of the state space model.

6. The system of claim 1 , wherein the cost of operating the vehicle includes fuel consumption.

7. The system of claim 1 , wherein the processor is further programmed to:

determine the set of second control inputs based on a cost minimization control method.

8. The system of claim 1 , wherein the processor is further programmed to:

operating the vehicle according to the third control input.

9. The system of claim 1 , wherein the processor is further programmed to:

Adapt the one or more second reference parameters so that the set of third control inputs converges to the set of second control inputs.

10. The system of claim 1 , wherein each of the predetermined ranges is determined based in part on a relative impact on achieving cost goals.

11. A method comprising:

determining, by a processor in a vehicle, a first set of control inputs for the vehicle based in part on input data and one or more first reference parameters;

collecting operating data from the vehicle while operating according to the first set of control inputs;

determining an estimated state of a state space model for the vehicle based on the operating data from the vehicle while operating according to the first set of control inputs;

determining, based in part on the estimated state of the state space model, a second set of control inputs for the vehicle, such that a cost of operating the vehicle according to the second set of control inputs is reduced relative to the cost of operating the vehicle based on the first set of control inputs;

specifying one or more second reference parameters based in part on the second set of control inputs and the input data, such that the one or more second reference parameters, when applied to the input data, results in a third set of control inputs, wherein members of the third set of control inputs are within respective predetermined ranges of corresponding members of the second set of control inputs;

and

operating the vehicle based on at least one of the one or more second reference parameters.

12. The method of claim 11 , further comprising:

generating, based on the input data and the operating data, the state space model of the vehicle.

13. The method of claim 12 , further comprising:

generating a dynamic model for the vehicle;

estimating a set of parameters correlating individual inputs of the model to the output of the model for the operating condition; and

taking into account the set of parameters correlating individual inputs of the model to the output of the model for determining the second control input.

14. The method of claim 13 , further comprising:

applying a regularized least squares method for estimating the set of parameters.

15. The method of claim 11 , further comprising:

applying a Kalman filter to estimate the state of the state space model.

16. The method of claim 11 , wherein the cost of operating the vehicle includes fuel consumption.

17. The method of claim 11 , further comprising:

determining the set of second control inputs based on a cost minimization control method.

18. The method of claim 11 , further comprising:

operating the vehicle according to the set of third control inputs.

19. The method of claim 11 , wherein the processor is further programmed to:

adapting the one or more second reference parameters so that the third set of control inputs converges to the second set of control inputs.

20. The method of claim 11 , wherein each of the predetermined ranges is determined based in part on a relative impact on achieving cost goals.