Black box data management method, apparatus, and device for intelligent driving vehicle
Provided is a black box data management method and apparatus for an intelligent driving vehicle. A black box device first obtains black box data based on a black box trigger event, wherein the black box device is configured to manage the black box data in the intelligent driving vehicle. The black box device evaluates a storage level of the black box data based on an event type of the black box trigger event and a data type of the black box data. The black box device stores the black box data based on the storage level and according to a preset rule.
1. A black box data management method for an intelligent driving vehicle, wherein the method comprises:
obtaining, by a black box device, black box data based on a black box trigger event, wherein the black box device is configured to manage the black box data in the intelligent driving vehicle;
evaluating, by the black box device, a storage level of the black box data based on an event type of the black box trigger event and a data type of the black box data, wherein the data type of the black box data comprises at least one of responsibility demarcation data, or assistant demarcation data and risk data; and
storing, by the black box device, the black box data based on the storage level and according to a preset rule, wherein
when the event type of the black box trigger event is collision, classifying black box data of the responsibility demarcation data type as first-level storage data and black box data of the assistant demarcation data type as second-level storage data,
when the event type of the black box trigger event is non-collision, classifying black box data of the risk data type as third-level storage data,
when the black box data is classified as the first-level storage data, storing the black box data of the responsibility demarcation data type in a local storage of the black box device and a cloud storage, wherein the black box data of the responsibility demarcation data type is permanently stored in the local storage and the cloud storage,
when the black box data is classified as the second-level storage data, sending the black box data of the assistant demarcation data type to the cloud storage, wherein the black box data of the assistant demarcation data type is not permanently stored in the cloud storage, and
when the black box data is classified as the third-level storage data, storing the black box data of the risk data type in the local storage of the black box device and sending the black box data of the risk data type to the cloud storage, wherein the black box data of the risk data type is not permanently stored in the local storage and the cloud storage.
2. The method according to claim 1 , wherein the method further comprises:
when the black box device receives a black box trigger event notification, identifying, by the black box device, the data type of the black box data, wherein the black box trigger event notification is generated based on the black box trigger event.
3. The method according to claim 1 , wherein the black box trigger event comprises a driving mode switching event.
4. The method according to claim 3 , wherein the driving mode switching event comprises at least one of the following cases: driver switches a driving mode of the intelligent driving vehicle to an intelligent driving mode, driver actively switches the driving mode of the intelligent driving vehicle to a non-intelligent driving mode, or driver passively switches the driving mode of the intelligent driving vehicle to a non-intelligent driving mode.
5. The method according to claim 1 , wherein the black box trigger event comprises a driving risk boundary event, where the driving risk boundary event comprises at least one of the following cases:
when the intelligent driving vehicle runs in an intelligent driving mode, a collision occurs between the intelligent driving vehicle and another vehicle or object;
when the intelligent driving vehicle runs in the intelligent driving mode, a distance between the intelligent driving vehicle and another vehicle reaches a preset threshold, and a forward or lateral collision risk event occurs because of emergency braking or emergency lane change of the intelligent driving vehicle; or
when a collision occurs on the intelligent driving vehicle, there is a negative acceleration that exceeds a boundary value.
6. The method according to claim 1 , wherein the responsibility demarcation data type is used to identify data that can determine a responsibility in a collision, and the assistant demarcation data type is used to identify data that assists in determining a responsibility in a collision.
7. The method according to claim 1 , wherein when storing the black box data based on the storage level and according to the preset rule, the black box device sets a duration for storing all or a part of the black box data and the method further comprises:
deleting all or a part of the black box data stored in at least one of the local storage or the cloud storage when the duration exceeds a first duration threshold.
8. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in a non-intelligent driving mode, a driver enables an intelligent driving mode by using a human-computer interaction controller.
9. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, a driver steps on a brake pedal.
10. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, a driver turns a steering wheel.
11. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, a driver switches the intelligent driving mode to a manual driving mode by using a human-computer interaction controller.
12. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, a hardware fault occurs on the intelligent driving vehicle, wherein the hardware fault comprises a processor reset and a sensor fault.
13. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, a collision occurs between the intelligent driving vehicle and another vehicle or object.
14. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, the intelligent driving vehicle brakes emergently.
15. The method according to claim 1 , wherein the black box trigger event comprises:
when the intelligent driving vehicle is in an intelligent driving mode, an instantaneous acceleration of the intelligent driving vehicle exceeds a preset value.
16. The method according to claim 1 , wherein the method further comprises:
when a collision occurs on the intelligent driving vehicle, permanently storing the black box trigger event, a timestamp of the black box trigger event, and one or more of the following data in a preset time period before and after the black box trigger event: key demarcation data, system status, positioning and planning and control structured data, structured data of close distance traffic participants, or sensor data in the direction of the collision.
17. The method according to claim 1 , wherein the method further comprises:
when a collision occurs on the intelligent driving vehicle, storing sensor data of the intelligent driving vehicle in a preset time period before and after the black box trigger event occurs.
18. The method according to claim 1 , wherein the method further comprises:
when no collision occurs on the intelligent driving vehicle, storing one or more of the following data in a preset time period before and after the black box trigger event: sensor data in the intelligent driving vehicle, a driver status, a driving subject, or vehicle body data.
19. A black box data management apparatus for an intelligent driving vehicle, comprising:
at least one processor; and
a non-transitory computer-readable storage medium coupled to the at least one processor and storing programming instructions, the programming instructions, when executed by the at least one processor, cause the at least one processor to perform the following operations:
obtaining black box data based on a black box trigger event, wherein the management apparatus is configured to manage the black box data in the intelligent driving vehicle;
evaluating a storage level of the black box data based on an event type of the black box trigger event and a data type of the black box data, wherein the data type of the black box data comprises responsibility demarcation data, assistant demarcation data and risk data; and
storing the black box data based on the storage level and according to a preset rule, wherein
when the event type of the black box trigger event is collision, classifying black box data of the responsibility demarcation data type as first-level storage data, and black box data of the assistant demarcation data type as second-level storage data
when the event type of the black box trigger event is non-collision, classifying black box data of the risk data type as third-level storage data,
when the black box data is classified as the first-level storage data, storing the black box data of the responsibility demarcation data type in a local storage of the black box device and a cloud storage, wherein the black box data of the responsibility demarcation data type is permanently stored in the local storage and the cloud storage,
when the black box data is classified as the second-level storage data, sending the black box data of the assistant demarcation data type to the cloud storage, wherein the black box data of the assistant demarcation data type is not permanently stored in the cloud storage, and
when the black box data is classified as the third-level storage data, storing the black box data of the risk data type in the local storage of the black box device and sending the black box data of the risk data type to the cloud storage, wherein the black box data of the risk data type is not permanently stored in the local storage and the cloud storage.