Measuring driving model coverage by microscope driving model knowledge

1. A computer-implemented method for redundancy reduction for driving test scenarios, comprising:

receiving an original test set of driving scenarios and a driving model which simulates a vehicle behavior under a driving scenario inputted to the driving model;

for each driving scenario of the original test set, obtaining vehicle dynamics timeseries data as an output of the driving model;

determining similar driving scenarios by comparing driving model outputs; and

creating a new test set of driving scenarios by discarding duplicated ones of the similar driving scenarios from the original test set.

2. The computer-implemented method of claim 1 , wherein the driving model outputs are compared according to a Dynamic Time Warp technique.

3. The computer-implemented method of claim 1 , further comprising:

creating a new entire set of driving scenarios by discarding duplicated ones of the similar driving scenarios from all driving scenarios; and

calculating a coverage of the new test set against the new entire set.

4. The computer-implemented method of claim 3 , wherein the new entire set of driving scenarios corresponds to a Lane Departure Warning System standard.

5. The computer-implemented method of claim 1 , further comprising replacing the original test set with new test set in a memory device to reduce an overall memory consumption of the memory device while still essentially covering same driving behaviors in the original test set due to scenario redundancy removal.

6. The computer-implemented method of claim 1 , further comprising executing the new test set in place of the original test set to reduce an overall memory consumption and an overall execution time while still essentially covering same driving behaviors in the original test set due to scenario redundancy removal.

7. The computer-implemented method of claim 1 , wherein the original test set comprises a plurality of tag-value pairs, each of the plurality of tag-value pairs comprising a tag for a specific topic of interest and a value corresponding to the specific topic of interest.

8. The computer-implemented method of claim 7 , wherein the plurality of tag-value pairs comprise at least time of day tags and road condition tags.

9. The computer-implemented method of claim 1 , wherein the driving model uses a driver visibility as a main factor for determining the driving behaviors, the driver visibility being calculated from values of two or more tags in the original test set comprising at least weather tags and road condition tags.

10. A computer program product for redundancy reduction for driving test scenarios, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

receiving, by a processor device, an original test set of driving scenarios and a driving model which simulates a vehicle behavior under a driving scenario inputted to the driving model;

for each driving scenario of the original test set, obtaining by the processor device vehicle dynamics timeseries data as an output of the driving model;

determining, by the processor device, similar driving scenarios by comparing driving model outputs; and

creating, by the processor device, a new test set of driving scenarios by discarding duplicated ones of the similar driving scenarios from the original test set.

11. The computer program product of claim 10 , wherein the driving model outputs are compared according to a Dynamic Time Warp technique.

12. The computer program product of claim 10 , further comprising:

creating a new entire set of driving scenarios by discarding duplicated ones of the similar driving scenarios from all driving scenarios; and

calculating a coverage of the new test set against the new entire set.

13. The computer program product of claim 12 , wherein the new entire set of driving scenarios corresponds to a Lane Departure Warning System standard.

14. The computer program product of claim 10 , further comprising replacing the original test set with new test set in a memory device to reduce an overall memory consumption of the memory device while still essentially covering same driving behaviors in the original test set due to scenario redundancy removal.

15. The computer program product of claim 10 , further comprising executing the new test set in place of the original test set to reduce an overall memory consumption and an overall execution time while still essentially covering same driving behaviors in the original test set due to scenario redundancy removal.

16. The computer program product of claim 10 , wherein the original test set comprises a plurality of tag-value pairs, each of the plurality of tag-value pairs comprising a tag for a specific topic of interest and a value corresponding to the specific topic of interest.

17. The computer program product of claim 16 , wherein the plurality of tag-value pairs comprise at least time of day tags and road condition tags.

18. The computer program product of claim 10 , wherein the driving model uses a driver visibility as a main factor for determining the driving behaviors, the driver visibility being calculated from values of two or more tags in the original test set comprising at least weather tags and road condition tags.

19. A computer processing system for redundancy reduction for driving test scenarios, comprising:

a memory device for storing program code; and

a processor device operatively coupled to the memory device for running the program code to:

receive an original test set of driving scenarios and a driving model which simulates a vehicle behavior under a driving scenario inputted to the driving model;

for each driving scenario of the original test set, obtain vehicle dynamics timeseries data as an output of the driving model;

determine similar driving scenarios by comparing driving model outputs; and

create a new test set of driving scenarios by discarding duplicated ones of the similar driving scenarios from the original test set.

20. The computer processing system of claim 19 , wherein the driving model outputs are compared according to a Dynamic Time Warp technique.