Method, electronic device and storage medium for testing autonomous driving system

1. A method for testing an autonomous driving system, comprising:

obtaining scenario description information of a testing scenario;

analyzing the scenario description information, and determining a scenario risk, a scenario probability and a scenario complexity corresponding to the testing scenario;

obtaining a scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity; and

determining a number of testing times corresponding to the scenario weight, wherein the autonomous driving system is to be tested in the testing scenario for the number of testing times, and wherein the number of testing time increases as the scenario weights increases,

wherein obtaining the scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity comprises:

determining a risk level according to the scenario risk, determining a probability level according to the scenario probability, and determining a complexity level according to the scenario complexity; and

obtaining the scenario weight of the testing scenario, according to a summing result of weight values corresponding respectively to the risk level, the probability level and the complexity level.

2. The method according to claim 1 , wherein the scenario complexity includes an environment complexity and a mission complexity corresponding to the testing scenario.

3. The method according to claim 1 , wherein determining the complexity level according to the scenario complexity comprises:

obtaining a standard complexity corresponding to a standard scenario;

comparing the scenario complexity with the standard complexity to determine differed attributes, and obtaining level up values corresponding respectively to the differed attributes; and

determining the complexity level according to a summing result between the obtained level up values and an initial level.

4. The method according to claim 1 , further comprising:

obtaining problems occurring in the autonomous driving system being tested in the testing scenario; and

determining a degree of importance of the problems occurring in the autonomous driving system, according to the scenario weight corresponding to the testing scenario.

5. The method according to claim 1 , further comprising:

obtaining, respectively, driving scores for the autonomous driving system being tested in a plurality of testing scenarios; and

performing weighted averaging for the driving scores according to the scenario weights corresponding respectively to the plurality of testing scenarios, and taking a calculation result as a final score of the autonomous driving system.

6. An electronic device, comprising:

at least one processor; and

a storage communicatively connected with the at least one processor; wherein,

the storage stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method for testing an autonomous driving system, wherein the method comprises:

obtaining scenario description information of a testing scenario;

analyzing the scenario description information, and determining a scenario risk, a scenario probability and a scenario complexity corresponding to the testing scenario;

obtaining a scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity; and

determining a number of testing times corresponding to the scenario weight, wherein the autonomous driving system is to be tested in the testing scenario for the number of testing times, and wherein the number of testing time increases as the scenario weights increases,

wherein obtaining the scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity comprises:

determining a risk level according to the scenario risk, determining a probability level according to the scenario probability, and determining a complexity level according to the scenario complexity; and

obtaining the scenario weight of the testing scenario, according to a summing result of weight values corresponding respectively to the risk level, the probability level and the complexity level.

7. The electronic device according to claim 6 , wherein the scenario complexity includes an environment complexity and a mission complexity corresponding to the testing scenario.

8. The electronic device according to claim 6 , wherein determining the complexity level according to the scenario complexity comprises:

obtaining a standard complexity corresponding to a standard scenario;

comparing the scenario complexity with the standard complexity to determine differed attributes, and obtaining level up values corresponding respectively to the differed attributes; and

determining the complexity level according to a summing result between the obtained level up values and an initial level.

9. The electronic device according to claim 6 , wherein the method further comprises:

obtaining problems occurring in the autonomous driving system being tested in the testing scenario; and

determining a degree of importance of the problems occurring in the autonomous driving system, according to the scenario weight corresponding to the testing scenario.

10. The electronic device according to claim 6 , wherein the method further comprises:

obtaining, respectively, driving scores for the autonomous driving system being tested in a plurality of testing scenarios; and

performing weighted averaging for the driving scores according to the scenario weights corresponding respectively to the plurality of testing scenarios, and taking a calculation result as a final score of the autonomous driving system.

11. A non-transitory computer-readable storage medium storing computer instructions therein, wherein the computer instructions are used to cause the computer to perform a method for testing an autonomous driving system, wherein the method comprises:

obtaining scenario description information of a testing scenario;

analyzing the scenario description information, and determining a scenario risk, a scenario probability and a scenario complexity corresponding to the testing scenario;

obtaining a scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity; and

determining a number of testing times corresponding to the scenario weight, wherein the autonomous driving system is to be tested in the testing scenario for the number of testing times, and wherein the number of testing time increases as the scenario weights increases,

wherein obtaining the scenario weight of the testing scenario according to the scenario risk, the scenario probability and the scenario complexity comprises:

determining a risk level according to the scenario risk, determining a probability level according to the scenario probability, and determining a complexity level according to the scenario complexity; and

obtaining the scenario weight of the testing scenario, according to a summing result of weight values corresponding respectively to the risk level, the probability level and the complexity level.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein the scenario complexity includes an environment complexity and a mission complexity corresponding to the testing scenario.

13. The non-transitory computer-readable storage medium according to claim 11 , wherein determining the complexity level according to the scenario complexity comprises:

obtaining a standard complexity corresponding to a standard scenario;

comparing the scenario complexity with the standard complexity to determine differed attributes, and obtaining level up values corresponding respectively to the differed attributes; and

determining the complexity level according to a summing result between the obtained level up values and an initial level.

14. The non-transitory computer-readable storage medium according to claim 11 , wherein the method further comprises:

obtaining problems occurring in the autonomous driving system being tested in the testing scenario; and

determining a degree of importance of the problems occurring in the autonomous driving system, according to the scenario weight corresponding to the testing scenario.

15. The non-transitory computer-readable storage medium according to claim 11 , wherein the method further comprises:

obtaining, respectively, driving scores for the autonomous driving system being tested in a plurality of testing scenarios; and

performing weighted averaging for the driving scores according to the scenario weights corresponding respectively to the plurality of testing scenarios, and taking a calculation result as a final score of the autonomous driving system.