Location-based vehicle operation

1. A method, comprising:

operating a vehicle in an identified map area;

obtaining output from a first classifier, based on input including the map area and one or more current environmental conditions detected in the map area, specifying a first probability that the map area is currently available for sensing to support input-free operation of the vehicle;

determining whether the first probability indicates that the map area is currently available for sensing to support input-free operation of the vehicle;

then, if the first probability indicates that the map area is currently available for sensing to support input-free operation of the vehicle, obtaining output from a second classifier, based on input including the map area and the one or more current environmental conditions, specifying a second probability that the vehicle will traverse the map area without a minimum risk maneuver event;

determining whether the second probability indicates that the vehicle will traverse the map area without a minimum risk maneuver event; and

then, if the second probability indicates that the vehicle will traverse the map area without a minimum risk maneuver event, operating the vehicle in an input-free mode in the map area.

2. The method of claim 1 , further comprising providing the one or more current environmental conditions to a remote server for updating the first classifier and the second classifier.

3. The method of claim 1 , further comprising providing a detected minimum risk maneuver event to a remote server for updating the first classifier and the second classifier.

4. The method of claim 1 , further comprising ending the input-free mode upon a detected minimum risk maneuver event.

5. The method of claim 1 , wherein the first classifier and the second classifier include different weights for different environmental conditions.

6. The method of claim 1 , wherein the first classifier and the second classifier accept vehicle state data as input in addition to the one or more current environmental conditions.

7. The method of claim 1 , wherein the first classifier and the second classifier accept a type of sensor as input in addition to the one or more current environmental conditions.

8. The method of claim 1 , wherein the first classifier and the second classifier are outputs from a trained neural network.

9. The method of claim 1 , wherein the one or more environmental conditions is one and only one environmental condition.

10. The method of claim 1 , wherein the one or more environmental conditions include at least one of an air temperature, a wind speed, a wind direction, an amount of ambient light, a presence or absence of precipitation, a rate of precipitation, or a presence or absence of atmospheric occlusions affecting visibility.

11. A computer comprising a processor and a memory, the memory storing instructions executable by the processor such that the computer is programmed to:

operate a vehicle in an identified map area;

obtain output from a first classifier, based on input including the map area and one or more current environmental conditions detected in the map area, specifying a first probability that the map area is currently available for sensing to support input-free operation of the vehicle;

determine whether the first probability indicates that the map area is currently available for sensing to support input-free operation of the vehicle;

then, if the first probability indicates that the map area is currently available for sensing to support input-free operation of the vehicle, obtain output from a second classifier, based on input including the map area and the one or more current environmental conditions, specifying a second probability that the vehicle will traverse the map area without a minimum risk maneuver event;

determine whether the second probability indicates that the vehicle will traverse the map area without a minimum risk maneuver event; and

then, if the second probability indicates that the vehicle will traverse the map area without a minimum risk maneuver event, operate the vehicle in an input-free mode in the map area.

12. The computer of claim 11 , the instructions further comprising instructions to provide the one or more current environmental conditions to a remote server for updating the first classifier and the second classifier.

13. The computer of claim 11 , the instructions further comprising instructions to provide a detected minimum risk maneuver event to a remote server for updating the first classifier and the second classifier.

14. The computer of claim 11 , the instructions further comprising instructions to end the input-free mode upon a detected minimum risk maneuver event.

15. The computer of claim 11 , wherein the first classifier and the second classifier include different weights for different environmental conditions.

16. The computer of claim 11 , wherein the first classifier and the second classifier accept vehicle state data as input in addition to the one or more current environmental conditions.

17. The computer of claim 11 , wherein the first classifier and the second classifier accept a type of sensor as input in addition to the one or more current environmental conditions.

18. The computer of claim 11 , wherein the first classifier and the second classifier are outputs from a trained neural network.

19. The computer of claim 11 , wherein the one or more environmental conditions is one and only one environmental condition.

20. The computer of claim 11 , wherein the one or more environmental conditions include at least one of an air temperature, a wind speed, a wind direction, an amount of ambient light, a presence or absence of precipitation, a rate of precipitation, or a presence or absence of atmospheric occlusions affecting visibility.