WO2021022818A1 - 智能驾驶汽车中黑匣子数据的管理方法、装置和设备 - Google Patents

智能驾驶汽车中黑匣子数据的管理方法、装置和设备 Download PDF

Info

Publication number
WO2021022818A1
WO2021022818A1 PCT/CN2020/081534 CN2020081534W WO2021022818A1 WO 2021022818 A1 WO2021022818 A1 WO 2021022818A1 CN 2020081534 W CN2020081534 W CN 2020081534W WO 2021022818 A1 WO2021022818 A1 WO 2021022818A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
black box
storage
smart
smart driving
Prior art date
Application number
PCT/CN2020/081534
Other languages
English (en)
French (fr)
Inventor
贾晓林
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP20849244.7A priority Critical patent/EP4009291A4/en
Publication of WO2021022818A1 publication Critical patent/WO2021022818A1/zh
Priority to US17/665,143 priority patent/US20220157092A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/02—Registering or indicating driving, working, idle, or waiting time only
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/082—Selecting or switching between different modes of propelling
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/005—Handover processes
    • B60W60/0051—Handover processes from occupants to vehicle
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/005—Handover processes
    • B60W60/0053—Handover processes from vehicle to occupant
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G07C5/085—Registering performance data using electronic data carriers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W2030/082—Vehicle operation after collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station

Definitions

  • This application relates to the field of automobiles, and in particular to methods, devices and equipment for managing black box data of smart driving cars.
  • ADAS assisted driving systems
  • automated driving automated driving
  • MDC mobile data center of the vehicle. center
  • intelligent driving technology has brought revolutionary opportunities and challenges to the automotive field. More and more manufacturers are committed to improving the driver's experience in car driving through intelligent driving.
  • This application provides a method, device, equipment and system for managing black boxes in smart driving cars, which can improve the effectiveness of black box data in smart driving cars and improve the overall safety of the entire smart driving car.
  • a method for managing black box data in a smart driving car includes: the black box device first obtains the black box data according to the black box trigger event sent by the received detection controller, and then, according to the event type and data of the black box trigger event The type evaluates the storage level of the black box data, and then stores the black box data according to the storage level and preset rules.
  • the black box trigger event triggers the black box device to obtain the black box data
  • the black box device evaluates the storage level of the black box data, and then stores the black box data according to the storage level and preset rules, and implements different storage methods and storage durations for different types of data. It is convenient to accurately identify faults through black box data during follow-up responsibility definition, which increases the accuracy of black box data.
  • the black box device and the detection controller communicate through the in-car bus.
  • the black box device receives the black box data sent by the detection controller in real time.
  • the black box device receives the black box trigger event notification sent by the detection controller, the black box The data type of the device identification black box data.
  • the black box trigger event notification is generated by the detection controller according to the black box trigger event.
  • the black box trigger event includes one or more of the following events: driving mode transition events and driving risk boundary events.
  • the data types include responsibility delimitation data and auxiliary determination. World data and risk data.
  • the types of black box trigger events are added in combination with the characteristics of the autonomous driving scene, and the accident responsibility can be more accurately defined in subsequent collision accidents.
  • the risk data during driving can also be identified based on the content recorded in the black box data. Further, the above risk data can be analyzed by a third-party management system to prompt the driver of the risks and problems in the operation of intelligent driving cars, which is effective Improve the driving safety of smart-driving cars.
  • the driving mode conversion event includes at least one of the following situations: the driver switches the driving mode of the smart driving car to the smart driving mode, and the driver actively switches the driving mode of the smart driving car to non- Smart driving mode, the driver passively switches the driving mode of the smart driving car to the non-smart driving mode.
  • the driver switches the driving mode of the smart driving car to the smart driving mode
  • the driver actively switches the driving mode of the smart driving car to non- Smart driving mode
  • the driver passively switches the driving mode of the smart driving car to the non-smart driving mode.
  • the driving risk boundary event includes at least one of the following situations:
  • the distance between the smart-driving car and other cars reaches the preset threshold, and the forward or side collision risk event caused by the smart-driving car's emergency braking or emergency lane change; or,
  • the black box data before and after the trigger event is recorded to assist in determining the responsibility division of the accident.
  • the box device determines the storage level of the black box data according to the black box trigger event type and data type, including:
  • the responsibility delimitation data is divided into the first-level storage data; among them, the responsibility delimitation data is used to identify the data that can clearly define the responsibility in the collision;
  • the auxiliary delimitation data is divided into second-level storage data; wherein the auxiliary delimitation data is used to identify data that assists in clarifying the responsibility in the collision;
  • the risk data is divided into the third level of storage data.
  • black box data are divided into different storage levels, and further stored in different storage media according to the storage levels, and the storage time of different black box data is controlled, which not only guarantees the storage time of useful data, and facilitates subsequent responsibility positioning
  • data backup can be realized through cloud storage and local storage, avoiding the problem of unable to locate the cause caused by data loss.
  • it can effectively save storage space and increase storage space utilization.
  • the responsibility delimitation data is stored in the local storage and cloud storage of the black box device, and the above responsibility delimitation data is permanently stored in the black box
  • the local storage and cloud storage of the device the local storage is the storage in the black box device
  • the cloud storage is the storage provided to the black box by the cloud service center
  • the black box device and the cloud storage communicate through the network
  • the responsibility definition data is stored in the local storage of the black box device, and the above auxiliary demarcation data is sent to the cloud service data center, and then stored in the cloud storage, and the above auxiliary delimitation Data does not need to be permanently stored in the local storage and cloud storage of the black box device;
  • the risk data is divided into the third-level storage data
  • the risk data is stored in the local storage of the black box device
  • the above risk data is sent to the cloud service data center, and then stored Cloud storage, the above risk data does not need to be permanently stored in the local storage and cloud storage of the black box device.
  • the black box device when the black box device stores black box data, it sets the length of time for storing data in the local storage and cloud storage, and when the first threshold is met, deletes all or all the data stored in the local storage and/or cloud storage. part of data.
  • black box data are divided into different storage levels, and further stored in different storage media according to the storage levels, and the storage time of different black box data is controlled, which not only guarantees the storage time of useful data, and facilitates subsequent responsibility positioning
  • data backup can be realized through cloud storage and local storage, avoiding the problem of unable to locate the cause caused by data loss.
  • it can effectively save storage space and increase storage space utilization.
  • the black box trigger event includes one or more of the following events:
  • the driver turns on the smart driving mode through the human-computer interaction controller
  • the smart driving car When the smart driving car is in smart driving mode, the smart driving car collides with other cars or objects;
  • the smart driving car When the smart driving car is in the smart driving mode, the smart driving car has hardware failures, including processor reset and sensor failure.
  • 1-4 can also be referred to as a smart driving car driving mode transition event
  • 5-8 can also be referred to as a driving risk boundary event.
  • the event, time, and key delimitation data, system status, positioning, regulatory structured data, and close range within a preset period of time before and after the trigger will be triggered.
  • One or more of the structured data of traffic participants and the sensor data on the collision direction is permanently stored in local storage and cloud storage.
  • the body data includes one of vehicle speed, engine speed, chassis electronic control unit status, and seat belt status. Item or multiple items.
  • the sensor data of the smart-driving car and the data of the main auxiliary demarcation accident within a preset time period before and after the trigger event are stored in the local storage and the cloud storage, and When the duration meets the second threshold, the data stored in the local storage is deleted.
  • all sensor data in the smart-driving car within a preset period of time before and after the trigger is stored, as well as the structured data of perception, fusion, positioning, and regulation.
  • One or more of the driver status, the driving subject, and the vehicle body data are stored in the local storage and the cloud storage, and the data stored in the local storage is deleted after the storage cloud storage completes storage.
  • the black box data management method combined with the newly added scenes in smart driving, adds the types of black box trigger events, can record the black box data when the smart driving mode is switched, and give the risk of smart driving mode switching.
  • dispute assessment provides a basis for accuracy; in addition, the triggering event for the detection of the driving risk boundary enriches the scenes of intelligent driving in operation, and provides a favorable basis for determining responsibility for accidents and disputes.
  • this application also provides a method for black box data grading and remote storage.
  • the black box device can store data in part of the memory according to the event type, and use the storage time limit to control the data storage time in the cloud storage, which ensures that the black box data can be stored.
  • the present application provides a management device for black box data of a smart driving car.
  • the management device includes a black box data management method for a smart driving car in the first aspect or any one of the possible implementations of the first aspect.
  • this application provides a smart-driving car.
  • the smart-driving car includes a detection controller and a black box device; the detection controller is used to detect black box trigger events; and send the black box trigger event detection result to the black box device according to the black box trigger event Notice;
  • the black box device is used to obtain black box data according to the black box trigger event notification and identify the data type; evaluate the storage level of the black box data according to the trigger event type and data type; store the black box data according to the black box data storage level and preset rules .
  • the black box is also used to execute the operation steps of the method implemented by the black box device in the first aspect or any one of the possible implementation manners of the first aspect.
  • the detection controller is further configured to execute the operation steps of the method implemented by the detection controller in the first aspect or any one of the possible implementation manners of the first aspect.
  • the present application provides a black box device.
  • the black box device includes a processor, a memory, a communication interface, and a bus.
  • the processor, the memory, and the communication interface are connected through the bus and complete mutual communication.
  • the memory is used to store computer-executable instructions.
  • the processor executes the computer-executable instructions in the memory to use the hardware resources in the black box device to execute the first aspect or any one of the first aspects It is possible to implement the operation steps performed by the black box device in the method described in the manner.
  • the present application provides a detection controller.
  • the detection controller includes a processor, a memory, a communication interface, and a bus.
  • the processor, the memory, and the communication interface are connected by a bus and complete mutual communication.
  • the memory is used to store computer execution instructions.
  • the processor executes the computer execution instructions in the memory to execute the first aspect or the first aspect using hardware resources in the detection controller In any of the possible implementation manners, the operation steps performed by the detection controller are detected in the method.
  • this application provides a black box data management system, including a cloud service data center and a smart driving car.
  • the system includes a cloud data center and a smart driving car.
  • the cloud data center is connected to the smart driving car through a network.
  • the cloud data center It is used to provide cloud storage for smart driving cars so that all or part of the black box data can be stored in the cloud data center according to the storage level of the black box data to realize the backup of black box data.
  • the smart driving car includes black box equipment and detection controllers, respectively It is used to implement the operation steps of the method executed by the black box device and the detection controller in the first aspect or any one of the possible implementation manners of the first aspect.
  • the present application provides a computer-readable storage medium having instructions stored in the computer-readable storage medium, which when run on a computer, cause the computer to execute the methods described in the foregoing aspects.
  • this application provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the methods described in the above aspects.
  • FIG. 1 is a schematic diagram of the logical architecture of a black box data management system for a smart driving car provided by this application;
  • FIG. 2 is a schematic diagram of the logical architecture of another black box data management system for intelligent driving vehicles provided by this application;
  • FIG. 3 is a schematic flowchart of a method for managing black box data of a smart driving car provided by this application;
  • FIG. 4 is a schematic structural diagram of a black box data management device for a smart driving car provided by this application;
  • FIG. 5 is a schematic structural diagram of a black box data detection device of a smart driving car provided by this application
  • FIG. 6 is a schematic structural diagram of a black box device for a smart driving car provided by this application.
  • FIG. 1 is a schematic diagram of the logical architecture of a black box data management system for smart driving vehicles provided by this application.
  • the system includes a cloud data center 101, a network 102 and a smart driving car 103, and a cloud data center 101 and smart driving The car 103 communicates through the network 102.
  • the cloud service data center 101 refers to a data center that can provide cloud services for storing black box data, including private cloud, public cloud, and hybrid cloud type data centers.
  • the network 102 is used to implement the medium for transmitting the black box data in the smart driving car to the cloud service data center.
  • the network 102 includes wired and wireless transmission methods.
  • the wired transmission methods include data transmission in the form of Ethernet and optical fiber. Transmission methods include mobile hotspot (Wi-Fi), Bluetooth, infrared and other transmission methods.
  • the intelligent driving vehicle 103 includes a communication box (TBOX) 1031, a central gateway 1032, a body control module (BCM) 1033, a human-machine interaction controller 1034, an intelligent driving controller 1035, a vehicle controller 1036, and The black box device 1037, each of the above-mentioned devices or devices may communicate through a controller area network (CAN) or in-vehicle Ethernet, which is not limited in this application.
  • the communication box is used to realize the communication between the smart driving car 103 and the cloud service data center 101.
  • the body controller 1033 is used to control the basic hardware devices of the smart driving car such as the door 10331, the window 10332, and the seat 10333.
  • the human-computer interaction controller 1034 includes in-vehicle infotainment (IVI) and/or hardware monitor interface (HMI) and other in-vehicle entertainment control systems, responsible for the interaction between the person and the vehicle, and is usually used to manage the instrument 10341 , Central control display 10342, steering wheel pressure sensor 10343 and other equipment.
  • Intelligent driving controller 1035 includes advanced driver assistance system (ADAS) and assisted driving system (ADS), which are specifically used to control radar 10351, camera 10352, combined positioning module 10353 and chassis electronic control unit ( electronic control module, ECU) 10361, where the combined positioning module 10353 includes equipment and sensors such as global navigation satellite system (GNSS), inertial measurement unit (IMU), etc.
  • GNSS global navigation satellite system
  • IMU inertial measurement unit
  • the global navigation and positioning system can output Global positioning information with a certain accuracy (for example, 5-10hz), while intelligent driving systems require higher-frequency positioning information.
  • the frequency of inertial measurement units is generally higher (for example, 1000hz).
  • the combined positioning module 10353 integrates inertial measurement units and global The information of the navigation satellite system outputs high-frequency precise positioning information (generally more than 200HZ).
  • the chassis electronic control unit 10361 includes the electronic stability program (ESP) system, Bosch's brake assist (IBOOSTER), electronic parking brake (electrical park brake, EPB), and electronic power steering (electronic power steering, EPS)
  • the electronic control unit of the other subsystems can use one electronic control unit to control each subsystem, or one electronic control unit to control the operation of all subsystems.
  • the vehicle control unit is usually connected to the chassis electronic control unit, the airbag 10362, and the power electronic control unit, and the airbag 10362 is connected to the inertial measurement unit/accelerator 10463 through the inertial measurement unit/accelerator 10463.
  • Detection can determine whether the smart-driving car is in an emergency braking state. If the smart-driving car is in this state, the airbag 10462 can pop out to protect the driver’s safety; the power electronic control unit is used to control the work of the power domain.
  • the vehicle power supply system becomes the power domain, including subsystems that provide current conversion (for example, high-voltage direct current and low-voltage direct current conversion (DCDC) subsystems) and on-board chargers (OBC).
  • DCDC high-voltage direct current and low-voltage direct current conversion
  • OBC on-board chargers
  • both the airbag 10362 and the combined positioning module 10353 are connected with an inertial measurement unit.
  • two different inertial measurement units may be used to connect to the airbag 10362 and the combined positioning module 10353 respectively. Because the combined positioning module 10353 requires low-latency and high-precision inertial measurement unit information; while the airbag 10362 will use the local inertial measurement unit to identify the collision event, and then determine whether the airbag needs to be ejected, requiring a very short delay and relying on external The inertial measurement unit will have a data transmission delay, causing the airbag to fail to bounce in time. On the other hand, the accuracy and functional safety requirements of the two inertial measurement units are also inconsistent, which can be set according to actual vehicle control requirements.
  • the smart driving car 103 also includes a black box device 1037.
  • the black box device is used to record the body data of the smart driving car in an emergency.
  • the body data includes but not limited to one or more of the following data: engine speed, vehicle Speed, braking force, steering angle, throttle plate status, seat belt status, and time stamps of the above data.
  • the smart driving car can also communicate with the outside world through other devices.
  • the management system shown in FIG. 1 may not include the central gateway 1032, and each controller is directly connected to the communication box, so that only the car can be driven to communicate with the data center.
  • FIG. 2 is a logical architecture diagram of another black box data management system in a smart driving car provided by an embodiment of the present application. Compared with FIG. 1, the difference in FIG. 2 is to further explain the structure of the black box device and the detection control of triggering black box events
  • the system includes a black box data detection controller 201 and a black box device 202.
  • the detection controller 201 includes an intelligent driving controller 2011, an inertial measurement unit 2012, a human-computer interaction controller 2013 and a chassis
  • the electronic control unit 2014, the function of the above-mentioned control unit or controller is the same as that in FIG. 1, and will not be repeated here.
  • the black box device 202 includes a processor 2021, a memory 2022, a local storage 2023, and a cloud storage 2024.
  • the processor 2021 includes a hierarchical storage module 20211, which is used to identify the storage level of the data according to preset rules after obtaining the black box data, and store the data in the local storage 2023 and/or the cloud storage 2024 according to different levels.
  • the local memory refers to the built-in memory in the black box device, that is, the processor 2021 can communicate with the local memory 2023 through the internal bus.
  • the cloud storage 2024 is the storage device provided by the cloud service data center in Figure 1 for the smart driving car. The size and device type of its storage space can be set according to actual needs. This application does not limit this.
  • the black box device can be connected via the network.
  • the cloud service data center communicates and uploads the black box data to the cloud storage.
  • the black box 1037 can be transmitted to the communication box 1031 through the central gateway 1032, and then the communication box 1031 uploads the black box data to the cloud service data through the network 102
  • the cloud storage 2024 provided for the smart driving car 103 in the center 101.
  • FIG. 1 and FIG. 2 is only an example of the system architecture provided by the black box data management method provided by the present application, and does not constitute a limitation to the embodiment of the present application.
  • This application provides a management method for black box data in a smart driving car. Based on the management method of black box data in a traditional manual driving car, combined with the characteristics of the smart driving scene, a multi-dimensional black box data trigger event is introduced, and further based on the trigger event The type divides the black box data into different storage levels and stores them in the local storage or cloud service data center. The black box data is stored in different levels according to the type of trigger event, and the black box data management method is improved to improve the entire intelligent driving. The validity and security of black box data in the car.
  • the method for managing black box data in a smart driving car includes:
  • the black box device identifies the data type of the black box data according to the trigger event type.
  • the detection controller includes one or more of the detection controllers 201 shown in FIG. 2.
  • the black box trigger events that can be detected by the detection controller include driving mode switching events and driving risk boundary events.
  • the driving mode switching events can be subdivided into at least one of the following situations:
  • the driver switches the driving mode of the smart driving car to the smart driving mode.
  • the driver When the smart driving car is manually driven and the smart driving system detects that it meets the smart driving opening conditions, the driver is notified through a human-computer interaction controller (for example, HMI), and the driver triggers the smart driving car to switch to smart driving mode through a button. , The human-computer interaction controller notifies the black box device of the black box trigger event.
  • a human-computer interaction controller for example, HMI
  • the black box data includes one or more of the following data: intelligent driving system status information, driver information, HMI system driver status information, body data (including engine speed, vehicle speed, braking force, steering angle, throttle Pedal status, seat belt status) and the time stamp of each data.
  • the driver actively switches the driving mode of the smart-driving car to the non-smart driving mode.
  • the driver can actively switch the smart driving car to non-driving mode by stepping on the brakes, turning the steering wheel, and switching between the man-machine interactive controller modes. At this time, the driver can use the man-machine interactive controller
  • the black box data trigger event is detected, and the black box device is notified of the black box trigger event.
  • the black box data includes one or more of the following: intelligent driving system status information, driver information, HMI system driver status information, body data (including engine speed, vehicle speed, braking force, steering angle, throttle Pedal status, seat belt status, door status, seat status, airbag status) and the time stamp of each data.
  • the driver passively switches the driving mode of the smart driving car to the non-smart driving mode.
  • the smart driving controller When the smart driving car is in smart driving mode, if the smart driving controller detects an internal error or malfunction in the system (for example, processor reset, sensor failure), the smart driving controller will send a notification to the human-computer interaction controller to facilitate the passage The text or voice prompts the driver to switch the driving mode to the non-smart driving mode. At the same time, the smart driving controller will also notify the black box device of the black box trigger event.
  • an internal error or malfunction in the system for example, processor reset, sensor failure
  • the black box data includes one or more of the following: intelligent driving system status information, driver information, HMI system driver status information, body data (including engine speed, vehicle speed, braking force, steering angle, throttle Pedal status, seat belt status, door status, seat status, airbag status), intelligent driving system fault types, and intelligent driving system sensor data, intelligent driving system perception, fusion, positioning, regulatory structured data and various data Timestamp.
  • black box data in the above various situations includes but is not limited to the above data, and the content of the black box data record can be set according to requirements or standards in specific implementation.
  • the second category, driving risk boundary events can include the following situations:
  • Case 1 When the smart driving car is running in the smart driving mode, if there is a collision between vehicles, or the distance between the vehicles is too close, the smart driving controller triggers emergency braking and other collision risk events, at this time, the smart driving controller will interact with the man-machine The controller sends a notification to prompt the driver to switch the driving mode to the non-smart driving mode through text or voice. At the same time, the smart driving controller will also notify the black box device of the black box trigger event.
  • black box data including one or more of the following: intelligent driving system status information, driver information, HMI system driver status information, body data (including engine speed, vehicle speed, braking force, steering angle, accelerator pedal status , Seat belt status) and the time stamp of each data, as well as the sensor data of the intelligent driving system, and the structured data of the perception, fusion, positioning and regulation of the intelligent driving system.
  • Case 2 When the smart driving car collides, there will be a negative acceleration that exceeds the boundary value. At this time, the inertial measurement unit/accelerator will use the accelerator to determine whether the acceleration of the smart driving car exceeds a preset threshold, and if it exceeds the preset threshold, it will notify the black box device that there is a black box trigger event.
  • black box data including one or more of the following: intelligent driving system status information, driver information, HMI system driver status information, body data (including engine speed, vehicle speed, braking force, steering angle, accelerator pedal status , Seat belt status) and the time stamp of each data, as well as intelligent driving system sensor data, intelligent driving system perception, fusion, positioning, and regulatory structured data.
  • the body data can be collected by the vehicle controller and the body controller, and sent to the black box device.
  • black box data in the above various situations includes but is not limited to the above data, and the content of the black box data record can be set according to requirements or standards in specific implementation.
  • the intelligent driving controller 1035 shown in FIG. 1 includes a perception module, a fusion module, a positioning module, a planning decision module, and a regulation control module.
  • a perception module a module that uses the intelligent driving controller 1035 to control the intelligent driving controller 1035 to control the intelligent driving controller 1035.
  • a fusion module a module that uses the intelligent driving controller 1035 to control the intelligent driving controller 1035.
  • a positioning module a module that uses information to control the intelligent driving controller 1035 to control module.
  • a planning decision module includes a regulation control module.
  • a regulation control module includes a regulation control module.
  • Each of the above-mentioned modules may be implemented by independent hardware, or the function of each module may be implemented by software in hardware, which is not limited in this application.
  • sensor data and the structured data of system operation status, perception, fusion, positioning, and regulation generated during operation include but not limited to the following:
  • Sensor data includes data from sensors such as image acquisition equipment (for example, vehicle-mounted camera (camera), lidar (LIDAR), millimeter wave radar, ultrasonic radar, global positioning system positioning data, inertial measurement unit, etc.).
  • image acquisition equipment for example, vehicle-mounted camera (camera), lidar (LIDAR), millimeter wave radar, ultrasonic radar, global positioning system positioning data, inertial measurement unit, etc.
  • System operating status includes engine speed, vehicle speed, brake, throttle and seat belt status.
  • the above-mentioned perception structured data is generated by the perception module.
  • the perception module is mainly responsible for preprocessing the point cloud data collected by the lidar (LIDAR) and the intelligent analysis of the YUV/RGB image frame data collected by the camera to complete the detection and detection of static/dynamic target objects. Tracking, lane line recognition, traffic light recognition, obstacle recognition and other functions, while outputting structured information to the fusion & positioning unit of this computing unit, output to the fusion & positioning unit of another computing system.
  • LIDAR lidar
  • YUV is a color coding method. Often used in various video processing components. When YUV encodes photos or videos, it takes into account human perception and allows the bandwidth of chroma to be reduced.
  • YUV is the type of true-color color space (color space)
  • "Y” represents brightness (luminance or Luma), which is the grayscale value
  • "U” and “V” represent chromaticity (Chrominance or Chroma), the role is to describe the color and saturation of the image, used to specify the color of the pixel.
  • RGB is a color standard defined by the industry. It is obtained by changing the three color channels of red (red, G), green (green, G), and blue (blue, B) and superimposing them with each other. For all kinds of colors, RGB represents the colors of the three channels of red, green, and blue. This standard includes almost all the colors that human vision can perceive, and it is one of the most widely used color systems at present.
  • the fusion structure data is the fusion module after receiving the obstacle list, depth information, lane line information, and drivable area information sent by the perception module, and then output the obstacle state estimation and trajectory prediction in the range of interest through smooth processing. Output the final drivable area and obstacle information to the planning decision unit.
  • the positioning structure data is combined with the global positioning system (GPS)/inertial measurement unit (IMU)/wheel speed meter to fuse positioning information and high-precision maps after the positioning (spatial cognition) module receives the road feature information provided by the perception module. Output the spatial positioning information of the intelligent driving car to the planning and decision-making module.
  • GPS global positioning system
  • IMU intial measurement unit
  • the regulatory structure data is determined by the regulatory module based on the drivable area information, positioning information, obstacle information provided by the fusion module and positioning module, as well as its own real-time motion information, to make behavioral decisions, including horizontal and vertical motion control Planning: Generate control commands (including brakes, accelerators, steering wheels, gears, turn signals, etc.) according to the motion control plan and given speed.
  • Generate control commands including brakes, accelerators, steering wheels, gears, turn signals, etc.
  • a preset algorithm may be used to compress the data after data collection, where the preset algorithm includes but is not limited to camera H.265.
  • compressed data is generally used for storage, including camera H.265 compression, and other sensors are compressed using ZIP/LZS algorithms.
  • the black box device obtains the black box data by collecting data from each detection controller and sending it to the black box device in real time.
  • the black box device saves the black box data sent by each controller according to preset rules.
  • the black box data may use the memory of the black box device or other storage media to store the black box data.
  • the preset rule may be that when the storage time meets a first threshold (for example, 23 hours), part of the data is deleted according to the storage time. For example, after the black box device receives the black box data sent by each detection controller in real time, the data is stored in the memory of the black box device. When the storage time of the earliest data stored in the memory of the black box device is equal to 24 hours, the earliest time is started. 12 hours of data deletion to free up storage space on the storage device.
  • the way that the black box device obtains the black box data can also be that each detection controller collects the black box data in real time.
  • each detection controller collects the black box data in real time.
  • the black box device receives the black box trigger event notification, it sends a collection notification message to each detection controller. Collect corresponding data according to the collection notice.
  • the black box device when the black box device receives the black box trigger event notification sent by the detection controller, the black box device also identifies the data type of the black box data according to preset rules, and can identify the data type of each black box data according to the trigger event type, for example,
  • the data that determines the cause of the vehicle collision is divided into responsibility delimitation data
  • the data that can assist the cause of the vehicle collision is divided into auxiliary delimitation data
  • the data that has not collided but is risky to the operation of intelligent driving vehicles is divided into risk data.
  • the smart driving system sensor data, the smart driving system's perception, fusion, positioning, and regulatory structured data are identified as responsibility delimitation data
  • the body data is identified as auxiliary delimitation data.
  • the black box device determines the storage level to which the data belongs according to the trigger event type and the data type.
  • the black box device stores the data according to the storage level to which the data belongs and preset rules.
  • the black box device sends the black box data to the cloud service data center.
  • the responsibility delimitation data is divided into the first level of storage data, and the responsibility delimitation data is stored in the local storage and cloud storage of the black box device, and the above responsibility delimitation data is permanently stored in the black box. Local storage and cloud storage of the device.
  • the auxiliary delimitation data is divided into second-level storage data, the responsibility definition data is stored in the local storage of the black box device, and the above auxiliary delimitation data is sent to the cloud service data center for storage To cloud storage, and the above auxiliary delimited data does not need to be permanently stored in the local storage and cloud storage of the black box device.
  • the cloud data service center completes the storage of the aforementioned auxiliary delimited data, the auxiliary delimited data stored in the local memory of the black box device is deleted.
  • the risk data is divided into the third level of storage data, the risk data is stored in the local memory of the black box device, and the above risks The data is sent to the cloud service data center and then stored in the cloud storage.
  • the above risk data does not need to be permanently stored in the local storage and cloud storage of the black box device.
  • the cloud data service center completes the storage of the black box data, the risk data stored in the local memory of the black box device is deleted.
  • a preset time limit can be used to control the length of time the black box data is stored in the cloud storage, and then the limited storage space of the cloud storage can be used to store other key data. Avoid storage failures caused by insufficient storage space.
  • the black box device can use the hierarchical storage module shown in Figure 2 to classify and store the black box data.
  • the hierarchical storage module can be a software module or a coprocessor, and the coprocessor can be installed in the black box. Between the processor and the communication interface of the device, so that the coprocessor can accurately and timely obtain the black box data and event type, and determine the storage level to which the data belongs.
  • this application divides different types of black box data into different storage levels, and further stores them in different storage media according to the storage levels, and controls the storage time of different black box data, which not only guarantees the storage time of useful data, so that In the follow-up responsibility positioning and accident cause analysis, data backup can be realized through cloud storage and local storage to avoid the problem of unable to locate the cause caused by data loss. Moreover, by periodically deleting some black box data, it can effectively save storage space and increase storage space Usage rate.
  • the black box data management method provided by the embodiment of the present application will be further introduced in combination with specific examples.
  • This application adds black box trigger events from a safety perspective by combining the differences in the use scenarios of smart driving cars and traditional cars, and distinguishes the data defining the responsibility for the accident based on whether it is related to the collision, and determines the storage location and storage of the black box data duration.
  • the black box trigger event includes one or more of the following events:
  • the driver turns on the smart driving mode through the human-computer interaction controller
  • the smart driving car When the smart driving car is in smart driving mode, the smart driving car collides with other cars or objects;
  • the smart driving car When the smart driving car is in the smart driving mode, the smart driving car has hardware failures, including processor reset and sensor failure.
  • 1-4 can also be referred to as a smart driving car driving mode transition event
  • 5-8 can also be referred to as a driving risk boundary event.
  • One or more of the sensor data is permanently stored in local storage and cloud storage, where the body data includes one or more of vehicle speed, engine speed, chassis electronic control unit status, and seat belt status.
  • the sensor data of the smart-driving car and/or the data of the main auxiliary demarcation accident within a preset period of time before and after the trigger event are stored in the local storage and the cloud storage, and the second threshold is met for the duration Delete the data stored in the local storage at the time.
  • the black box data storage process in FIG. 2 can be implemented by the smart driving controller 1035 in FIG. 1.
  • a black box management module may be set in the smart driving controller 1035, and the management module controls and obtains Black box data, and store the above black box data to the black box device.
  • the black box device is only used as a storage device for storing black box data, allowing the intelligent driving controller 1035 to write the black box data to it.
  • the black box data management system shown in FIG. 1 and FIG. 2 is taken as an example for description.
  • the black box data management method combined with the newly added scenes in smart driving, adds the type of black box trigger events, and can record the black box data when the smart driving mode is switched, and it can be used when the smart driving mode is switched.
  • the assessment of emerging risks and disputes provides a basis for accuracy; in addition, the triggering event for the detection of the driving risk boundary enriches the scenes of intelligent driving in operation, and provides a favorable basis for the determination of accident responsibility and disputes.
  • this application also provides a method for black box data grading and remote storage.
  • the black box device can store data in part of the memory according to the event type, and use the storage time limit to control the data storage time in the cloud storage, which ensures that the black box data can be stored.
  • the black box data management method according to the embodiment of the present application is described in detail, and the following will describe the black box data management device provided by the embodiment of the present application in conjunction with FIG. 4 to FIG. Black box equipment and detection controller.
  • the management device 400 includes an acquisition unit 404, an evaluation unit 402, and a storage unit 403. Among them,
  • the acquiring unit is configured to acquire black box data according to a black box trigger event, and the black box device is configured to manage the black box data in the smart driving car;
  • the evaluation unit is configured to evaluate the storage level of the black box data according to the event type and data type of the black box trigger event;
  • the storage unit is configured to store the black box data according to the storage level and preset rules.
  • the management device 400 of the embodiment of the present application may be implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), and the above PLD may be complex program logic.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • Device complex programmable logical device, CPLD
  • field-programmable gate array field-programmable gate array
  • FPGA field-programmable gate array
  • GAL general array logic
  • the acquiring unit further includes a receiving unit 4011 and an identification unit 4012, wherein:
  • the receiving unit 4011 is configured to receive the black box data sent by the detection controller in real time, wherein the black box device and the detection controller communicate through an in-vehicle bus;
  • the identification unit 4012 is configured to identify the data type of the black box data when receiving the black box trigger event notification sent by the detection controller, wherein the black box trigger event notification is generated by the detection controller according to the black box trigger event,
  • the black box trigger event includes one or more of the following events: a driving mode conversion event and a driving risk boundary event, and the data type includes responsibility delimitation data, auxiliary delimitation data, and risk data.
  • the evaluation unit is further configured to divide the responsibility delimitation data into first-level storage data when the trigger event type is a collision; wherein, the responsibility delimitation data is used to identify those responsible for the collision. Data; or, when the trigger event type is a collision, the auxiliary delimitation data is divided into second-level storage data; wherein the auxiliary delimitation data is used to identify the data that assists in clarifying the responsibility of the collision; or, in the trigger event type When it is non-collision, but when there is no collision, the risk data is classified as the third-level storage data.
  • the storage unit is further configured to store the responsibility demarcation data in the local storage and cloud storage of the black box device when the black box data is divided into the first-level storage data, and the aforementioned responsibility determination
  • the boundary data is permanently stored in the local storage and cloud storage of the black box device
  • the local storage is the storage in the black box device
  • the cloud storage is the storage provided to the black box by the cloud service center
  • the cloud storage communicates through the network
  • the responsibility definition data is stored in the local storage of the black box device, and the above auxiliary delimited data is sent to the cloud service data center, and then stored in the cloud storage, and
  • the above auxiliary demarcation data does not need to be permanently stored in the local storage and cloud storage of the black box device;
  • the black box data When the black box data is divided into the third-level storage data, divide the risk data into the third-level storage data, store the risk data in the local storage of the black box device, and send the above-mentioned risk data to the cloud service data center , And then stored in cloud storage, the above risk data does not need to be permanently stored in the local storage and cloud storage of the black box device.
  • the storage unit is further configured to set the length of time for storing data in the local storage and the cloud storage when storing the black box data; when the first threshold is met, delete the local storage and/ Or all or part of the data stored in the cloud storage.
  • the driving mode conversion event includes at least one of the following situations: the driver switches the driving mode of the smart driving car to the smart driving mode, the driver actively switches the driving mode of the smart driving car to the non-smart driving mode, The driver passively switches the driving mode of the smart driving car to the non-smart driving mode.
  • the driving risk boundary event includes at least one of the following situations:
  • the distance between the smart-driving car and other cars reaches a preset threshold, the forward or side collision caused by the smart-driving car's emergency braking or emergency lane change Risk event; or,
  • the management apparatus 400 may correspond to the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the management apparatus 400 are to implement the corresponding methods in FIG. 3. For the sake of brevity, the process will not be repeated here.
  • FIG. 5 is a schematic structural diagram of a detection device provided by an embodiment of the application. As shown in the figure, the detection device 500 includes a detection unit 501 and a sending unit 502, wherein,
  • the detection unit 501 is configured to detect a black box trigger event according to a preset rule, and generate the black box event trigger notification;
  • the sending unit 502 is configured to send the black box event trigger notification to the black box device.
  • the management device 400 of the embodiment of the present application may be implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), and the above PLD may be complex program logic.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • Device complex programmable logical device, CPLD
  • field-programmable gate array field-programmable gate array
  • FPGA field-programmable gate array
  • GAL general array logic
  • the detection device 500 may correspond to the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the detection device 500 are used to implement the corresponding methods in FIG. 3. For the sake of brevity, the process will not be repeated here.
  • the black box device 100 includes a processor 101, a storage medium 102, a communication interface 103, and a memory unit 104.
  • the processor 701, the storage medium 102, the communication interface 103, and the memory unit 104 communicate through the bus 105, and may also communicate through other means such as wireless transmission.
  • the memory 102 is used to store instructions, and the processor 101 is used to execute instructions stored in the memory 102.
  • the memory 102 stores program codes, and the processor 101 can call the program codes stored in the memory 102 to perform the following operations:
  • the processor 101 may be a CPU, and the processor 101 may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • DSP digital signal processors
  • ASIC application specific integrated circuits
  • FPGA field programmable gate arrays
  • the general-purpose processor may be a microprocessor or any conventional processor.
  • the memory 102 may include a read-only memory and a random access memory, and provides instructions and data to the processor 101.
  • the memory 102 may also include a non-volatile random access memory.
  • the memory 102 may also store device type information.
  • the memory 102 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • the volatile memory may be random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • Double data rate synchronous dynamic random access memory double data date SDRAM, DDR SDRAM
  • enhanced SDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous connection dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • the bus 105 may also include a power bus, a control bus, and a status signal bus. However, for clear description, various buses are marked as the bus 105 in the figure.
  • the black box device 100 may correspond to the management apparatus 400 in the embodiment of the present application, and may correspond to the corresponding main body performing the method shown in FIG. 3 in the embodiment of the present application, and the black box device 100
  • the above and other operations and/or functions of each module in FIG. 3 are used to implement the corresponding process of each method in FIG. 3, and for brevity, they are not repeated here.
  • the present application also provides a detection controller.
  • the detection controller may be any one of the detection controllers shown in FIG. 1 or FIG. 2.
  • FIG. 6 Including processor, storage medium, communication interface and memory unit.
  • the processor, the storage medium, the communication interface, and the memory unit communicate through a bus, and may also communicate through other means such as wireless transmission.
  • the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory.
  • the memory stores program codes, and the processor 101 can call the program codes stored in the memory 102 to execute the operation steps performed by the detection controller in the method shown in FIG. 3, which will not be repeated here for brevity.
  • the present application also provides a smart driving car.
  • the smart driving car includes a black box device and a detection controller as shown in FIG. 1, which are respectively used to implement each of the methods shown in FIG. The operation steps are not repeated here for brevity.
  • this application also provides a black box data management system.
  • the system includes a cloud data center and a smart driving car as shown in Figure 1.
  • the cloud data center is connected to the smart driving car through a network.
  • the data center is used to provide cloud storage for smart driving cars, so that all or part of the black box data can be stored in the cloud data center according to the storage level of the black box data to realize the backup of the black box data.
  • the smart driving car includes black box equipment and detection controllers. , Are respectively used to implement the operation steps performed by the black box device and the detection controller in the black box data management method shown in FIG. 3, and will not be repeated here for brevity.
  • the foregoing embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination.
  • the above-mentioned embodiments may be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions may be transmitted from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more sets of available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium.
  • the semiconductor medium may be a solid state drive (SSD).

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种智能驾驶汽车中黑匣子数据的管理方法，黑匣子设备先根据黑匣子触发事件获取黑匣子数据，然后，根据黑匣子触发事件的事件类型和数据类型评估黑匣子数据的存储级别；再根据存储级别和预置规则存储黑匣子数据，以此满足智能驾驶汽车中黑匣子数据的记录和存储方法，提升智能驾驶汽车中黑匣子数据的有效性和整个智能驾驶汽车的安全性。

Description

智能驾驶汽车中黑匣子数据的管理方法、装置和设备 技术领域
本申请涉及汽车领域，尤其涉及智能驾驶汽车黑匣子数据的管理方法、装置和设备。
背景技术
近年来，智能驾驶汽车已成为汽车领域发展的新趋势，越来越多的汽车采用了辅助驾驶系统(ADAS)和自动驾驶(automated driving)系统，这类系统利用车载的移动数据中心(mobile data center，MDC)和车载传感器，在行驶过程中智能化探测障碍物、感知周围环境并自动决策车辆的路径并控制车辆的行驶状态。智能驾驶技术给汽车领域带来了革命性地机遇和挑战，越来越多的厂商致力于通过智能驾驶提升驾驶员在汽车行驶中的体验。
智能驾驶汽车的安全性也引起了业界的广泛关注，传统人工驾驶汽车通常利用黑匣子设备记录车辆在发生事故前后的引擎速度、车速、刹车、油门和安全带的状态，而黑匣子则是一类安装在汽车上且抗损毁性能高设备。当汽车发生剧烈碰撞时，黑匣子可以通过车身内与黑匣子设备连接的加速传感器提供的数据判断车辆的加速度在短时间内是否超过预设阈值，进而收集并存储车身数据。但是，与传统的人工驾驶车辆相比，智能驾驶汽车在应用场景、驾驶员驾驶习惯和方式，智能驾驶汽车内各个系统的工作方式，以及车身与周围设施和其他汽车的连接关系等方面都发生了巨大的变化，智能驾驶汽车在安全方面也对黑匣子数据的管理方法提出了更高的要求，因此，如何提供一种适用于智能驾驶汽车中更有效的黑匣子管理方法成为亟待解决的技术问题。
发明内容
本申请提供了一种智能驾驶汽车中黑匣子的管理方法、装置、设备和系统，可以提升智能驾驶汽车中黑匣子数据的有效性，提升整个智能驾驶汽车的整体安全性。
第一方面，提供一种智能驾驶汽车中黑匣子数据的管理方法，该方法包括：黑匣子设备先根据接收的检测控制器发送的黑匣子触发事件获取黑匣子数据，然后，根据黑匣子触发事件的事件类型和数据类型评估黑匣子数据的存储级别，再根据存储级别和预置规则存储黑匣子数据。通过上述方法，由黑匣子触发事件触发黑匣子设备获取黑匣子数据，由黑匣子设备评估黑匣子数据的存储级别，然后按照存储级别和预置规则存储黑匣子数据，将不同类型数据实施不同的存储方式和存储时长，便于后续责任界定时能够通过黑匣子数据准确识别故障，增加了黑匣子数据的准确性。
在一种可能的实现方式中，黑匣子设备和检测控制器通过车内总线进行通信，黑匣子设备实时接收检测控制器发送的黑匣子数据，当黑匣子设备接收检测控制器发送的黑匣子触发事件通知时，黑匣子设备标识黑匣子数据的数据类型。其中，黑匣子触 发事件通知是检测控制器根据黑匣子触发事件生成，黑匣子触发事件包括以下事件中一种或多种：驾驶模式转换事件和驾驶行驶风险边界事件，数据类型包括责任定界数据、辅助定界数据和风险数据。本申请中结合自动驾驶场景的特点增加了黑匣子触发事件的种类，在后续碰撞事故中可以更准确对事故责任进行界定。在非碰撞事故中也可以依据黑匣子数据记录的内容识别驾驶过程中风险数据，进一步地，上述风险数据可以通过第三方管理系统的分析，提示驾驶员智能驾驶汽车运行中存在的风险和问题，有效提高智能驾驶汽车行驶安全。
在另一种可能的实现方式中，驾驶模式转换事件包括以下情况中至少一种：驾驶员将智能驾驶汽车的驾驶模式切换至智能驾驶模式、驾驶员主动将智能驾驶车的驾驶模式切换至非智能驾驶模式、驾驶员被动将智能驾驶车的驾驶模式切换至非智能驾驶模式。本申请中通过增加对智能驾驶汽车驾驶模式切换的监控，监控自动驾驶和手动驾驶模式切换的原因和时间，当出现碰撞事故时，可以辅助分析事故的原因，进一步确定事故责任主体。
在另一种可能的实现方式中，驾驶行驶风险边界事件包括以下情况中至少一种：
当智能驾驶汽车运行在智能驾驶模式时，如果智能驾驶汽车出现与其他汽车间碰撞；
当智能驾驶汽车运行在智能驾驶模式时，智能驾驶汽车与其他汽车之间的间距达到预设阈值，智能驾驶汽车紧急刹车或紧急变道所导致的前向或侧向碰撞风险事件；或者，
当所述智能驾驶汽车出现碰撞时，会出现超过边界值的负加速度。
本申请中通过增加驾驶形式风险边界事件，记录触发事件发生前后的黑匣子数据，辅助确定事故的责任划分。
在另一种可能的实现方式中，匣子设备根据黑匣子触发事件类型和数据类型确定黑匣子数据的存储级别，包括：
当触发事件类型为碰撞时，则将责任定界数据划分为第一级存储数据；其中，责任界定数据用于标识对能够明确碰撞中责任的数据；
当触发事件类型为碰撞时，则将辅助定界数据划分为第二级存储数据；其中，所述辅助界定数据用于标识辅助明确碰撞中责任的数据；
当触发事件类型为非碰撞时，将风险数据划分为第三级存储数据。
本申请中，对不同种类型的黑匣子数据划分不同存储级别，进一步依据该存储级别分别存储至不同存储介质，并控制不同黑匣子数据的存储时间，既保证有用数据的存储时长，以便于后续责任定位和事故原因分析，又能够通过云存储器和本地存储器实现数据的备份，避免数据丢失造成无法定位原因的问题，而且，通过定期删除部分黑匣子数据，能够有效节省存储空间，提升存储空间的使用率。
在另一种可能的实现方式中，当黑匣子数据被划分为第一级存储数据时，分别将责任定界数据存储至黑匣子设备的本地存储器和云存储器，且上述责任定界数据永久存储至黑匣子设备的本地存储器和云存储器，本地存储器为黑匣子设备中存储器，云存储器为云服务中心提供给黑匣子的存储器，黑匣子设备和云存储器通过网络进行通信；
当黑匣子数据被划分为第二级存储数据时，将责任界定数据存储至黑匣子设备的本地存储器，并将上述辅助定界数据发送至云服务数据中心，进而存储至云存储器，且上述辅助定界数据无需永久存储至黑匣子设备的本地存储器和云存储器；
当黑匣子数据被划分为第三级存储数据时，将风险数据划分为第三级存储数据，将风险数据存储至黑匣子设备的本地存储器，并将上述风险数据发送至云服务数据中心，进而存储至云存储器，上述风险数据无需永久存储至黑匣子设备的本地存储器和云存储器。
在另一种可能的实现方式中，黑匣子设备在存储黑匣子数据时，设置本地存储器和云存储器中存储数据的时长，当满足第一阈值时，删除本地存储器和/或云存储器中存储的全部或部分数据。
本申请中，对不同种类型的黑匣子数据划分不同存储级别，进一步依据该存储级别分别存储至不同存储介质，并控制不同黑匣子数据的存储时间，既保证有用数据的存储时长，以便于后续责任定位和事故原因分析，又能够通过云存储器和本地存储器实现数据的备份，避免数据丢失造成无法定位原因的问题，而且，通过定期删除部分黑匣子数据，能够有效节省存储空间，提升存储空间的使用率。
在另一种可能的实现方式中，黑匣子触发事件包括以下事件中一种或多种：
1、智能驾驶汽车处于非智能驾驶模式时，驾驶员通过人机交互控制器开启智能驾驶模式；
2、智能驾驶汽车处于智能驾驶模式时，驾驶员踩刹车板；
3、智能驾驶汽车处于智能驾驶模式时，驾驶员转动方向盘；
4、智能驾驶汽车处于智能驾驶模式时，驾驶员通过人机交互控制器将智能驾驶汽车切换为手动驾驶模式；
5、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车出现与其他汽车或物体的碰撞；
6、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车紧急刹车；
7、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车瞬时加速度超过预设值；
8、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车出现硬件故障，硬件故障包括处理器复位、传感器故障。
其中，1-4又可以称为智能驾驶汽车驾驶模式转换事件，5-8又可以被称为驾驶行驶风险边界事件。
在另一种可能的实现方式中，当智能驾驶汽车发生碰撞时，将触发事件、时间、以及触发前后预设时段内的关键定界数据、系统状态、定位、规控结构化数据、近距离交通参与者结构化数据、碰撞方向上传感器数据中的一项或者多项永久存储至本地存储器和云存储器，其中，车身数据包括车速、引擎速度、底盘电子控制单元状态和安全带状态中的一项或者多项。
在另一种可能的实现方式中，当智能驾驶汽车发生碰撞时，将触发事件前后预设时段内的智能驾驶汽车的传感器数据、主要辅助定界事故的数据存储至本地存储器和云端存储器，并在时长满足第二阈值时删除本地存储器中存储的数据。
在另一种可能的实现方式中，当智能驾驶汽车未发生碰撞时，存储触发前后预设 时段内的所述智能驾驶汽车中所有传感器数据，以及感知、融合、定位、规控结构化数据、驾驶员状态、驾驶主体、以及车身数据中的一项或者多项存储至本地存储器和云存储器，并在存储云存储器完成存储后删除所述本地存储器中存储的数据。
通过上述描述，本申请提供的黑匣子数据的管理方法，结合智能驾驶中新增的场景增加了黑匣子触发事件的类型，能够记录智能驾驶模式切换时的黑匣子数据，给智能驾驶模式切换时出现的风险和纠纷评估提供了准确性的依据；另外，对于行驶风险边界检测的触发事件丰富了智能驾驶车量运行中场景，在事故定责、纠纷等方面提供了有利的依据。另一方面，本申请还提供一种黑匣子数据分级和异地存储的方式，黑匣子设备可以依据事件类型将数据存储在部分存储器，并利用保存时限控制云存储器中数据存储时长，即保证了黑匣子数据能够通过更有效的方式备份存储，又通过时限控制了关键和非关键的黑匣子数据在云存储器中存储的时长，有效利用云存储器对黑匣子数据进行备份，保证云存储器的利用率。
第二方面，本申请提供一种智能驾驶汽车的黑匣子数据的管理装置，所述管理装置包括用于执行第一方面或第一方面任一种可能实现方式中的智能驾驶汽车的黑匣子数据管理方法的各个模块。
第三方面，本申请提供一种智能驾驶汽车，智能驾驶汽车包括检测控制器和黑匣子设备；所述检测控制器，用于检测黑匣子触发事件；根据黑匣子触发事件向黑匣子设备发送黑匣子触发事件检测结果通知；
所述黑匣子设备，用于根据黑匣子触发事件通知获取黑匣子数据，并标识数据类型；根据触发事件类型和数据类型评估黑匣子数据的存储级别；按照黑匣子数据的存储级别和预置规则存储所述黑匣子数据。
在一种可能的实现方式中，所述黑匣子还用于执行第一方面或第一方面的任一种可能的实现方式中黑匣子设备所实现的方法的操作步骤。
在另一种可能的实现方式中，所述检测控制器还用于执行第一方面或第一方面的任一种可能的实现方式中检测控制器所实现的方法的操作步骤。
第四方面，本申请提供一种黑匣子设备，所述黑匣子设备包括处理器、存储器、通信接口、总线，所述处理器、存储器和通信接口之间通过总线连接并完成相互间的通信，所述存储器中用于存储计算机执行指令，所述黑匣子设备运行时，所述处理器执行所述存储器中的计算机执行指令以利用所述黑匣子设备中的硬件资源执行第一方面或第一方面任一种可能实现方式中所述方法中黑匣子设备所执行的操作步骤。
第五方面，本申请提供一种检测控制器，所述检测控制器包括处理器、存储器、通信接口、总线，所述处理器、存储器和通信接口之间通过总线连接并完成相互间的通信，所述存储器中用于存储计算机执行指令，所述黑匣子设备运行时，所述处理器执行所述存储器中的计算机执行指令以利用所述检测控制器中的硬件资源执行第一方面或第一方面任一种可能实现方式中所述方法中检测控制器所执行的操作步骤。
第六方面，本申请提供一种黑匣子数据的管理系统，包括云服务数据中心和智能驾驶汽车，该系统包括云数据中心、智能驾驶汽车，云数据中心通过网络与智能驾驶汽车相连，云数据中心用于为智能驾驶汽车提供云存储器，以便于根据黑匣子数据的存储级别将全部或部分黑匣子数据存储至云数据中心中，实现对黑匣子数据的备份， 智能驾驶汽车包括黑匣子设备和检测控制器，分别用于实现上述第一方面或第一方面任一种可能的实现方式中黑匣子设备和检测控制器所执行的方法的操作步骤。
第七方面，本申请提供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
第八方面，本申请提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
本申请在上述各方面提供的实现方式的基础上，还可以进行进一步组合以提供更多实现方式。
附图说明
图1为本申请提供的一种智能驾驶车的黑匣子数据的管理系统的逻辑架构示意图；
图2为本申请提供的另一种智能驾驶车的黑匣子数据的管理系统的逻辑架构示意图；
图3为本申请提供的一种智能驾驶车的黑匣子数据的管理方法的流程示意图；
图4为本申请提供的一种智能驾驶车的黑匣子数据的管理装置的结构示意图；
图5为本申请提供的一种智能驾驶车的黑匣子数据的检测装置的结构示意图
图6为本申请提供的一种智能驾驶车的黑匣子设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。
图1为本申请提供的一种智能驾驶车黑匣子数据的管理系统的逻辑架构示意图,如图所示,该系统包括云数据中心101、网络102和智能驾驶车103，云数据中心101和智能驾驶车103通过网络102进行通信。其中，云服务数据中心101是指能够提供用于存储黑匣子数据的云服务的数据中心，包括私有云、公有云和混合云类型的数据中心，对于云服务数据中心中设备的类型、虚拟化管理方式本申请不作限定。网络102用于实现将智能驾驶车中黑匣子数据传输至云服务数据中心的媒介，网络102包括以有线和无线的传输方式，其中，有线的传输方式包括利用以太、光纤等形式进行数据传输，无线传输方式包括移动热点(Wi-Fi)、蓝牙、红外等传输方式。
智能驾驶车103包括通信盒子(telecommunications box,TBOX)1031、中央网关1032、车身控制器(body control module,BCM)1033、人机交互控制器1034、智能驾驶控制器1035、整车控制器1036和黑匣子设备1037，上述各个器件或设备可以通过控制器局域网络(controller area network,CAN)或车内以太网进行通信，本申请对此并不做限定。其中，通信盒子用于实现智能驾驶车103和云服务数据中心101的通信。车身控制器1033用于控制器车门10331、车窗10332和座椅10333等智能驾驶车的基础硬件设备。人机交互控制器1034包括车载娱乐(in-vehicle infotainment,IVI)和/或硬件监视器接口(hardware monitor interface,HMI)等车载娱乐控制系统，负责人和车辆的交互，通常用于管理仪表10341，中控显示10342，方向盘压力传感器10343等设备。智能驾驶控制器1035则包括高级驾驶辅助系统(advanced driver assistant system,ADAS)和辅助系统(assisted driving system,ADS)，具体用于控制雷达10351、相机10352、组合定位模块10353和底盘电子控 制单元(electronic control module,ECU)10361，其中，组合定位模块10353包括全球导航卫星系统(global navigation satellite system,GNSS)、惯性测量单元(inertial measurement unit,IMU)等设备和传感器)，全球导航定位系统能够输出一定精度(例如，5-10hz)的全局定位信息，而智能驾驶系统要求频率更高的定位信息，惯性测量单元频率一般较高(例如，1000hz)，组合定位模块10353通过融合惯性测量单元和全球导航卫星系统的信息，输出高频的精准定位信息(一般要求200HZ以上)。底盘电子控制单元10361包括电子车身稳定(electronic stability program,ESP)系统、博世的制动助力(IBOOSTER)、电子驻车制动(electrical park brake,EPB)、电子助力转向(electronic power steering,EPS)等子系统的电子控制单元，可以分别利用一个电子控制单元控制各个子系统，也可以利用一个电子控制单元控制所有子系统的运行。整车控制器(vehicle control unit,VCU)通常与底盘电子控制单元、安全气囊10362和动力电子控制单元相连，而安全气囊10362又与惯性测量单元/加速器10463相连，通过惯性测量单元/加速器10463的检测，可以判断智能驾驶汽车是否处于紧急制动状态，若智能驾驶汽车处于该状态，安全气囊10462可以弹出以保护驾驶员安全；动力电子控制单元用于控制动力域的工作，其中，可以将整车供电系统成为动力域，包括提供电流转换的子系统(例如，高压直流电和低压直流电转换(DCDC)的子系统)和车载充电机(on board charger,OBC)。
值得说明的是，安全气囊10362和组合定位模块10353均连接有惯性测量单元，具体实施时，可以利用两个不同的惯性测量单元分别与安全气囊10362和组合定位模块10353相连。因为组合定位模块10353需要低时延和高精度的惯性测量单元的信息；而安全气囊10362会使用本地惯性测量单元识别碰撞事件，进而决定安全气囊是否需要弹出，要求时延很短，依赖外部的惯性测量单元会存在数据传输时延导致安全气囊不能及时弹。另一方面，两个惯性测量单元的精度和功能安全要求也不一致，具体可以根据实际车辆控制要求设置。
智能驾驶车103中还包括黑匣子设备1037，黑匣子设备用于在紧急情况下记录智能驾驶车的车身数据，所述车身数据包括但不限于下述数据中的一种或者多种：引擎速度、车辆速度、刹车力度、转向角、油门板状态、安全带状态，以及上述各个数据的时间戳。
可选地，智能驾驶汽车除了通过通信盒子与外界进行通信外，还可以通过其他设备实现与外界的通信。可选地，图1所示的管理系统中也可以不包括中央网关1032，各个控制器直接与通信盒子连接，实现只能驾驶汽车与数据中心的通信。
图2是本申请实施例提供的另一种智能驾驶车中黑匣子数据的管理系统的逻辑架构图，与图1相比，图2的区别在于进一步解释黑匣子设备的结构和触发黑匣子事件的检测控制器的关系，如图所示，该系统包括黑匣子数据的检测控制器201和黑匣子设备202，其中，检测控制器201包括智能驾驶控制器2011、惯性测量单元2012、人机交互控制器2013和底盘电子控制单元2014，上述控制单元或控制器的作用与图1中相同，在此不再赘述。
黑匣子设备202包括处理器2021、内存2022、本地存储器2023和云存储器2024。其中，处理器2021中包括分级存储模块20211，用于在获取黑匣子数据后，按照预设规则识别数据所属存储级别，并按照不同级别分别将数据存储在本地存储器2023和/或云存储器2024。本地存储器是指黑匣子设备中自带的存储器，也就是说处理器2021可以通过内部总线与本地存储器2023进行通信。而云存储器2024则是图1中云服务数据中心为智能驾 驶车提供的存储设备，其存储空间的大小和设备类型可以根据实际需求进行设置，本申请对此不作限定，黑匣子设备可以通过网络与云服务数据中心进行通信，将黑匣子数据上传至云存储器，具体可以参考图1，黑匣子1037可以通过中央网关1032传输至通信盒子1031，然后由通信盒子1031通过网络102将黑匣子数据上传至云服务数据中心中101中为智能驾驶车103提供的云存储器2024。
值得说明的是，图1和图2所示的系统架构仅仅是为了更好的说明本申请所提供的黑匣子数据管理方法所提供的系统架构的示例，并不构成对本申请实施例的限定。
本申请提供一种智能驾驶汽车中黑匣子数据的管理方法，在传统人工驾驶车中黑匣子数据的管理方法基础上，结合智能驾驶场景的特点，引入多维的黑匣子数据触发事件，并进一步依据触发事件的类型将黑匣子数据划分为不同存储级别，并分别存储在本地存储器或云服务数据中心中，实现黑匣子数据依据触发事件的类型不同分级分地存储的机制，进而完善黑匣子数据管理方法，提升整个智能驾驶车中黑匣子数据有效性和安全性。
接下来，结合图3详细介绍本申请所提供的智能驾驶汽车中黑匣子数据的管理方法，如图所示，所述方法包括：
S301、当检测控制器检测到黑匣子触发事件时，检测控制器向黑匣子设备发送触发事件通知。
S302、黑匣子设备根据触发事件类型标识黑匣子数据的数据类型。
检测控制器包括图2所示的检测控制器201中的一种或多种。为了适应智能驾驶场景的要求，检测控制器能够检测的黑匣子触发事件包括驾驶模式转换事件和驾驶风险边界事件两类，其中，驾驶模式转换事件又可以细分为以下情况中至少一种情况：
情况一，驾驶员将智能驾驶汽车的驾驶模式切换至智能驾驶模式。
当智能驾驶车为人工驾驶且智能驾驶系统检测符合智能驾驶开启条件，通过人机交互控制器(例如，HMI)通知驾驶员，由驾驶员通过按钮触发智能驾驶车切换为智能驾驶模式，此时，由人机交互控制器通知黑匣子设备存在黑匣子触发事件。
此时，黑匣子数据包括以下数据中的一项或多项：智能驾驶系统状态信息、驾驶主体信息、HMI系统驾驶员状态信息，车身数据(包括引擎速度、车辆速度、刹车力度、转向角、油门踏板状态、安全带状态)以及各个数据的时间戳。
情况二，驾驶员主动将智能驾驶汽车的驾驶模式切换至非智能驾驶模式。
当智能驾驶车为智能驾驶模式时，驾驶员可以通过踩刹车、转动方向盘、人机交互控制器模式切换的方式主动将智能驾驶车切换为非驾驶模式，此时，可以通过人机交互控制器检测到黑匣子数据触发事件，并通知黑匣子设备存在黑匣子触发事件。
此时，黑匣子数据包括以下各项中一种或多种：智能驾驶系统状态信息、驾驶主体信息、HMI系统驾驶员状态信息，车身数据(包括引擎速度、车辆速度、刹车力度、转向角、油门踏板状态、安全带状态、车门状态、座椅状态、安全气囊状态)以及各个数据的时间戳。
情况三，驾驶员被动将智能驾驶车的驾驶模式切换至非智能驾驶模式。
当智能驾驶车为智能驾驶模式时，若智能驾驶控制器检测到系统内部错误或故障(例如，处理器复位、传感器故障)，智能驾驶控制器会向人机交互控制器发送通知，以便于通过文字或语音的方式提示驾驶员驾驶模式切换至非智能驾驶模式，与此同时，智能驾驶 控制器还会通知黑匣子设备存在黑匣子触发事件。
此时，黑匣子数据包括以下各项中一种或多种：智能驾驶系统状态信息、驾驶主体信息、HMI系统驾驶员状态信息，车身数据(包括引擎速度、车辆速度、刹车力度、转向角、油门踏板状态、安全带状态、车门状态、座椅状态、安全气囊状态)，智能驾驶系统故障类型，以及智能驾驶系统传感器数据，智能驾驶系统的感知、融合、定位、规控结构化数据以及各个数据的时间戳。
值得说明的是，上述各种情况中黑匣子数据包括但不限于上述数据，具体实施时可以根据需求或标准设置黑匣子数据记录的内容。
第二类，驾驶行驶风险边界事件又可以包括以下几种情况：
情况一，当智能驾驶车运行在智能驾驶模式时，如果出现车辆间碰撞，或车辆间距过近智能驾驶控制器触发紧急刹车等碰撞风险事件，此时，智能驾驶控制器会通过向人机交互控制器发送通知，以便于通过文字或语音的方式提示驾驶员驾驶模式切换至非智能驾驶模式，与此同时，智能驾驶控制器还会通知黑匣子设备存在黑匣子触发事件。
包括黑匣子数据包括以下各项中一种或多种：智能驾驶系统状态信息、驾驶主体信息、HMI系统驾驶员状态信息，车身数据(包括引擎速度、车辆速度、刹车力度、转向角、油门踏板状态、安全带状态)和各个数据的时间戳，以及智能驾驶系统的传感器数据，智能驾驶系统的感知、融合、定位、规控结构化数据。
情况二，当智能驾驶车出现碰撞时，会出现超过边界值的负加速度。此时，惯性测量单元/加速器会通过加速器判断智能驾驶车的加速度是否超过预设阈值，如果超过预设阈值，则会通知黑匣子设备存在黑匣子触发事件。
包括黑匣子数据包括以下各项中一种或多种：智能驾驶系统状态信息、驾驶主体信息、HMI系统驾驶员状态信息，车身数据(包括引擎速度、车辆速度、刹车力度、转向角、油门踏板状态、安全带状态)和各个数据的时间戳，以及智能驾驶系统传感器数据，智能驾驶系统的感知、融合、定位、规控结构化数据。
上述各种情况中，车身数据可以由整车控制器和车身控制器收集，并发送给黑匣子设备。
值得说明的是，上述各种情况中黑匣子数据包括但不限于上述数据，具体实施时可以根据需求或标准设置黑匣子数据记录的内容。
作为一个可能的实现方式，图1所示的智能驾驶控制器1035包括感知模块、融合模块、定位模块、规划决策模块、规控模块。上述各个模块可以分别由独立的硬件实现，也可以由硬件中软件实现各个模块的功能，本申请对此不作限定。
进一步地，传感器数据以及运行过程中生成的系统运行状态、感知、融合、定位、规控结构化数据包括但不限于以下内容：
1.传感器数据包括图像采集设备(例如，车载相机(camera)、激光雷达(LIDAR)、毫米波雷达、超声波雷达、全球定位系统定位数据、惯性测量单元等传感器的数据。
2.系统运行状态包括引擎速度、车速、刹车、油门和安全带的状态。
3.上述感知结构化数据由感知模块生成，感知模块主要负责预处理激光雷达(LIDAR)收集的点云数据和相机采集的YUV/RGB图像帧数据的智能分析，完成静态/动态目标物体检测和跟踪，车道线识别，交通灯识别，障碍物识别等功能，在输出结构化的信息给本 计算单元融合&定位单元的同时，输出给另一计算系统的融合&定位单元。其中，YUV是一种颜色编码方法。常使用在各个视频处理组件中。YUV在对照片或视频编码时，考虑到人类的感知能力，允许降低色度的带宽。YUV是编译真彩(true-color)颜色空间(color space)的种类，“Y”表示明亮度(luminance或Luma)，也就是灰阶值，“U”和“V”表示的则是色度(chrominance或Chroma)，作用是描述影像色彩及饱和度，用于指定像素的颜色。RGB则是工业界定义的一种颜色标准，是通过对红(red，G)、绿(green,G)、蓝(blue,B)三个颜色通道的变化以及它们相互之间的叠加来得到各式各样的颜色的，RGB即是代表红、绿、蓝三个通道的颜色，这个标准几乎包括了人类视力所能感知的所有颜色，是目前运用最广的颜色系统之一。
4.融合结构数据则是融合模块在接收感知模块发送的障碍物列表、深度信息、车道线信息、可行驶区域信息后，通过平滑处理，输出感兴趣范围内的障碍物状态估计、轨迹预测，输出最终的可行驶区域、障碍物信息给规划决策单元。
5.定位结构数据由定位(空间认知)模块在接收到感知模块提供道路特征信息后，结合全球定位系统(GPS)/惯性测量单元(IMU)/轮速计融合定位信息和高精地图，输出智能驾驶汽车自身空间定位信息给规划决策模块。
6.规控结构数据则是由规控模块根据融合模块、定位模块提供的可行驶区域信息、定位信息、障碍物信息，以及自身实时运动信息，做出行为决策，包括横向和纵向的运动控制规划；根据运动控制规划和给定速度，产生控制指令(包括刹车、油门、方向盘、档位、转向灯等)。
可选地，为了减少数据传输所占用的网络资源，数据采集后可以先利用预置算法进行压缩后，其中，预置算法包括但不限于camera H.265。示例地，一般采用压缩后的数据进行存储，包括camera H.265压缩，其他传感器采用ZIP/LZS算法压缩等。
黑匣子设备获取黑匣子数据的方式，可以是各个检测控制器收集数据，并实时的发送给黑匣子设备，黑匣子设备按照预置规则保存各个控制器发送的黑匣子数据。其中，黑匣子数据可以利用黑匣子设备的内存或其他存储介质存储上述黑匣子数据，预置规则可以是存储时间满足第一阈值(例如，23小时)时，按照存储时长删除部分数据。例如，黑匣子设备接收各个检测控制器实时发送的黑匣子数据后，将该数据存储至黑匣子设备的内存中，当黑匣子设备的内存中最早存储的数据的存储时长等于24小时时，则将最早时间起12小时的数据删除，以此释放存储设备的存储空间。可选地，黑匣子设备获取黑匣子数据的方式，还可以是各个检测控制器实时收集黑匣子数据，当黑匣子设备在接收到黑匣子触发事件通知后，向各个检测控制器发送收集通知消息，由各个控制器根据该收集通知收集对应数据。
进一步地，黑匣子设备在接收到检测控制器发送的黑匣子触发事件通知时，黑匣子设备还会根据预置规则标识黑匣子数据的数据类型，可以根据触发事件类型标识各个黑匣子数据的数据类型，例如，将跟确定车辆碰撞原因的数据划分为责任定界数据，将能够辅助车辆碰撞原因的数据划分为辅助定界数据，将未发生碰撞但对智能驾驶汽车运行存在风险的数据划分为风险数据。示例地，当智能驾驶汽车发生碰撞时，将智能驾驶系统传感器数据，智能驾驶系统的感知、融合、定位、规控结构化数据标识为责任定界数据、将车身数据标识为辅助定界数据。
S303、黑匣子设备根据触发事件类型和数据类型确定数据所属存储级别。
S304、黑匣子设备按照数据所属存储级别和预置规则存储数据。
S305、当数据所属存储级别满足预设条件时，黑匣子设备向云服务数据中心发送黑匣子数据。
当触发事件类型为碰撞时，则将责任定界数据划分为第一级存储数据，并分别将责任定界数据存储至黑匣子设备的本地存储器和云存储器，且上述责任定界数据永久存储至黑匣子设备的本地存储器和云存储器。
当触发事件类型为碰撞时，则将辅助定界数据划分为第二级存储数据，将责任界定数据存储至黑匣子设备的本地存储器，并将上述辅助定界数据发送至云服务数据中心，进而存储至云存储器，且上述辅助定界数据无需永久存储至黑匣子设备的本地存储器和云存储器。可选地，当云数据服务中心完成上述辅助定界数据的存储时，删除黑匣子设备本地存储器中存储的辅助定界数据。
当触发事件类型为非碰撞(例如，驾驶行驶风险边界事件)时，但未发生碰撞时，将风险数据划分为第三级存储数据，将风险数据存储至黑匣子设备的本地存储器，并将上述风险数据发送至云服务数据中心，进而存储至云存储器，上述风险数据无需永久存储至黑匣子设备的本地存储器和云存储器。可选地，当云数据服务中心完成上述黑匣子数据的存储时，删除黑匣子设备本地存储器中存储的风险数据。
作为一个可能的实施例，对于云存储器中存储的无需永久保存的黑匣子数据，可以通过预设时限来控制云存储器中保存黑匣子数据的时长，进而利用有限的云存储器的存储空间存储其他关键数据，避免因存储空间不足所导致的存储失败问题。
黑匣子设备中可以利用如图2所示的分级存储模块对黑匣子数据进行分级和分地存储，该分级存储模块可以为一个软件模块，也可以制作成协处理器，并将该协处理器安装黑匣子设备的处理器和通信接口之间，以便于该协处理器准确及时地获取黑匣子数据和事件类型，并确定数据所归属的存储级别。
通过上述内容的描述，本申请对不同种类型的黑匣子数据划分不同存储级别，进一步依据该存储级别分别存储至不同存储介质，并控制不同黑匣子数据的存储时间，既保证有用数据的存储时长，以便于后续责任定位和事故原因分析，又能够通过云存储器和本地存储器实现数据的备份，避免数据丢失造成无法定位原因的问题，而且，通过定期删除部分黑匣子数据，能够有效节省存储空间，提升存储空间的使用率。
接下来，结合具体示例进一步介绍本申请实施例提供的黑匣子数据的管理方法。本申请通过结合智能驾驶汽车与传统汽车在使用场景上的差异，从安全角度增加了黑匣子触发事件，并依据是否与碰撞有关去区分对事故责任界定的数据，并决定黑匣子数据的存储位置和存储时长。其中，黑匣子触发事件包括以下事件中一种或多种：
1、智能驾驶汽车处于非智能驾驶模式时，驾驶员通过人机交互控制器开启智能驾驶模式；
2、智能驾驶汽车处于智能驾驶模式时，驾驶员踩刹车板；
3、智能驾驶汽车处于智能驾驶模式时，驾驶员转动方向盘；
4、智能驾驶汽车处于智能驾驶模式时，驾驶员通过人机交互控制器将智能驾驶汽车切换为手动驾驶模式；
5、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车出现与其他汽车或物体的碰撞；
6、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车紧急刹车；
7、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车瞬时加速度超过预设值；
8、智能驾驶汽车处于智能驾驶模式时，智能驾驶汽车出现硬件故障，硬件故障包括处理器复位、传感器故障。
其中，1-4又可以称为智能驾驶汽车驾驶模式转换事件，5-8又可以被称为驾驶行驶风险边界事件。
当智能驾驶汽车发生碰撞时，将触发事件、时间、触发前后预设时段内的关键定界数据、系统状态、定位、规控结构化数据、近距离交通参与者结构化数据、以及碰撞方向上传感器数据中的一项或多项永久存储至本地存储器和云存储器，其中，车身数据包括车速、引擎速度、底盘电子控制单元状态和安全带状态中的一项或多项。
当智能驾驶汽车发生碰撞时，将发生触发事件前后预设时段内的智能驾驶汽车的传感器数据、和/或主要辅助定界事故的数据存储至本地存储器和云端存储器，并在时长满足第二阈值时删除本地存储器中存储的数据。
当智能驾驶汽车未发生碰撞时，将发生触发事件前后预设时段内的：所述智能驾驶汽车中所有传感器数据，以及感知、融合、定位、规控结构化数据、驾驶员状态、驾驶主体、车声数据存储至本地存储器和云存储器，并在存储云存储器完成存储后删除所述本地存储器中存储的数据。
作为一种可能的实施例，图2中黑匣子数据的存储过程可以由图1中智能驾驶控制器1035实现，具体可以在智能驾驶控制器1035中设置黑匣子的管理模块，由该管理模块控制和获取黑匣子数据，并将上述黑匣子数据存储至黑匣子设备。此时，黑匣子设备仅仅作为一种用于存储黑匣子数据的存储设备，允许智能驾驶控制器1035向其写入黑匣子数据。为了便于说明，本申请实施例的以下描述中，以图1和图2所示的黑匣子数据的管理系统为例进行说明。
通过上述实施例的描述，本申请提供的黑匣子数据的管理方法，结合智能驾驶中新增的场景增加了黑匣子触发事件的类型，能够记录智能驾驶模式切换时的黑匣子数据，给智能驾驶模式切换时出现的风险和纠纷评估提供了准确性的依据；另外，对于行驶风险边界检测的触发事件丰富了智能驾驶车量运行中场景，在事故定责、纠纷等方面提供了有利的依据。另一方面，本申请还提供一种黑匣子数据分级和异地存储的方式，黑匣子设备可以依据事件类型将数据存储在部分存储器，并利用保存时限控制云存储器中数据存储时长，即保证了黑匣子数据能够通过更有效的方式备份存储，又通过时限控制了关键和非关键的黑匣子数据在云存储器中存储的时长，有效利用云存储器对黑匣子数据进行备份，保证云存储器的利用率。
值得说明的是，对于上述方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制。
本领域的技术人员根据以上描述的内容，能够想到的其他合理的步骤组合，也属于本申请的保护范围内。其次，本领域技术人员也应该熟悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本申请所必须的。
上文中结合图1至图3，详细描述了根据本申请实施例所提供的黑匣子数据的管理方法，下面将结合图4至图6，描述根据本申请实施例所提供的黑匣子数据的管理装置、黑匣子设备和检测控制器。
图4为本申请实施例提供的一种黑匣子数据的管理装置400，该管理装置400包括获取单元404、评估单元402和存储单元403，其中，
所述获取单元，用于根据黑匣子触发事件获取黑匣子数据，所述黑匣子设备用于管理所述智能驾驶汽车中所述黑匣子数据；
所述评估单元，用于根据所述黑匣子触发事件的事件类型和数据类型评估所述黑匣子数据的存储级别；
所述存储单元，用于根据所述存储级别和预置规则存储所述黑匣子数据。
应理解的是，本申请实施例的管理装置400可以通过专用集成电路(application-specific integrated circuit,ASIC)实现，或可编程逻辑器件(programmable logic device,PLD)实现，上述PLD可以是复杂程序逻辑器件(complex programmable logical device,CPLD)，现场可编程门阵列(field-programmable gate array,FPGA)，通用阵列逻辑(generic array logic,GAL)或其任意组合。也可以通过软件实现图3所示的黑匣子数据的管理方法时，管理装置400及其各个模块也可以为软件模块。
可选地，所述获取单元还包括接收单元4011和标识单元4012，其中，
所述接收单元4011，用于实时接收所述检测控制器发送的黑匣子数据，其中，所述黑匣子设备和所述检测控制器通过车内总线进行通信；
所述标识单元4012，用于在接收检测控制器发送的黑匣子触发事件通知时，标识所述黑匣子数据的数据类型，其中，所述黑匣子触发事件通知是所述检测控制器根据黑匣子触发事件生成，所述黑匣子触发事件包括以下事件中一种或多种：驾驶模式转换事件和驾驶行驶风险边界事件，所述数据类型包括责任定界数据、辅助定界数据和风险数据。
可选地，所述评估单元，还用于在触发事件类型为碰撞时，将责任定界数据划分为第一级存储数据；其中，所述责任界定数据用于标识对能够明确碰撞中责任的数据；或，在触发事件类型为碰撞时，则将辅助定界数据划分为第二级存储数据；其中，所述辅助界定数据用于标识辅助明确碰撞中责任的数据；或，在触发事件类型为非碰撞时，但未发生碰撞时，将风险数据划分为第三级存储数据。
可选地，所述存储单元，还用于当所述黑匣子数据被划分为所述第一级存储数据时，分别将责任定界数据存储至黑匣子设备的本地存储器和云存储器，且上述责任定界数据永久存储至黑匣子设备的本地存储器和云存储器，所述本地存储器为所述黑匣子设备中存储器，所述云存储器为所述云服务中心提供给所述黑匣子的存储器，所述黑匣子设备和所述云存储器通过网络进行通信；
当所述黑匣子数据被划分为所述第二级存储数据时，将责任界定数据存储至黑匣子设备的本地存储器，并将上述辅助定界数据发送至云服务数据中心，进而存储至云存储器，且上述辅助定界数据无需永久存储至黑匣子设备的本地存储器和云存储器；
当所述黑匣子数据被划分为所述第三级存储数据时，将风险数据划分为第三级存储数据，将风险数据存储至黑匣子设备的本地存储器，并将上述风险数据发送至云服务数据中心，进而存储至云存储器，上述风险数据无需永久存储至黑匣子设备的本地存储器和云存 储器。
可选地，所述存储单元，还用于在存储所述黑匣子数据时，设置所述本地存储器和所述云存储器中存储数据的时长；当满足第一阈值时，删除所述本地存储器和/或所述云存储器中存储的全部或部分数据。
可选地，所述驾驶模式转换事件包括以下情况中至少一种：驾驶员将智能驾驶汽车的驾驶模式切换至智能驾驶模式、驾驶员主动将智能驾驶车的驾驶模式切换至非智能驾驶模式、驾驶员被动将智能驾驶车的驾驶模式切换至非智能驾驶模式。
可选地，所述驾驶行驶风险边界事件包括以下情况中至少一种：
当所述智能驾驶汽车运行在智能驾驶模式时，如果所述智能驾驶汽车出现与其他汽车间碰撞；
当所述智能驾驶汽车运行在智能驾驶模式时，所述智能驾驶汽车与其他汽车之间的间距达到预设阈值，所述智能驾驶汽车紧急刹车或紧急变道所导致的前向或侧向碰撞风险事件；或者，
当所述智能驾驶汽车出现碰撞时，会出现超过边界值的负加速度。
根据本申请实施例的管理装置400可对应于执行本申请实施例中描述的方法，并且管理装置400中的各个单元的上述和其它操作和/或功能分别为了实现图3中的各个方法的相应流程，为了简洁，在此不再赘述。
图5为本申请实施例提供的一种检测装置的结构示意图，如图所示，该检测装置500包括检测单元501和发送单元502，其中，
所述检测单元501，用于按照预置规则检测黑匣子触发事件，并生成所述黑匣子事件触发通知；
所述发送单元502，用于向黑匣子设备发送所述黑匣子事件触发通知。
应理解的是，本申请实施例的管理装置400可以通过专用集成电路(application-specific integrated circuit,ASIC)实现，或可编程逻辑器件(programmable logic device,PLD)实现，上述PLD可以是复杂程序逻辑器件(complex programmable logical device,CPLD)，现场可编程门阵列(field-programmable gate array,FPGA)，通用阵列逻辑(generic array logic,GAL)或其任意组合。也可以通过软件实现图3所示的黑匣子数据的管理方法时，管理装置400及其各个模块也可以为软件模块。
根据本申请实施例的检测装置500可对应于执行本申请实施例中描述的方法，并且检测装置500中的各个单元的上述和其它操作和/或功能分别为了实现图3中的各个方法的相应流程，为了简洁，在此不再赘述。
图6为本申请实施例提供的一种黑匣子设备100的示意图，如图所示，所述黑匣子设备100包括处理器101、存储介质102、通信接口103和内存单元104。其中，处理器701、存储介质102、通信接口103、内存单元104通过总线105进行通信，也可以通过无线传输等其他手段实现通信。该存储器102用于存储指令，该处理器101用于执行该存储器102存储的指令。该存储器102存储程序代码，且处理器101可以调用存储器102中存储的程序代码执行以下操作：
根据黑匣子触发事件获取黑匣子数据；
根据所述黑匣子触发事件的事件类型和数据类型评估所述黑匣子数据的存储级别；
根据所述存储级别和预置规则存储所述黑匣子数据
应理解，在本申请实施例中，该处理器101可以是CPU，该处理器101还可以是其他通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。
该存储器102可以包括只读存储器和随机存取存储器，并向处理器101提供指令和数据。存储器102还可以包括非易失性随机存取存储器。例如，存储器102还可以存储设备类型的信息。
该存储器102可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM,DR RAM)。
该总线105除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都标为总线105。
应理解，根据本申请实施例的黑匣子设备100可对应于本申请实施例中的管理装置400，并可以对应于执行根据本申请实施例中图3所示方法中的相应主体，并且黑匣子设备100中的各个模块的上述和其它操作和/或功能分别为了实现图3中的各个方法的相应流程，为了简洁，在此不再赘述。
作为一个可能的实施例，本申请还提供一种检测控制器，该检测控制器可以是图1或图2所示的检测控制器中的任意一种，该检测控制器的结构可以参考图6，包括处理器、存储介质、通信接口和内存单元。其中，处理器、存储介质、通信接口、内存单元通过总线进行通信，也可以通过无线传输等其他手段实现通信。该存储器用于存储指令，该处理器用于执行该存储器存储的指令。该存储器存储程序代码，且处理器101可以调用存储器102中存储的程序代码执行图3所示的方法中检测控制器所执行的操作步骤，为了简洁，在此不再赘述。
作为另一种可能的实施例，本申请还提供一种智能驾驶汽车，该智能驾驶汽车包括如图1所示的黑匣子设备和检测控制器，分别用于实现如图3所示的方法的各个操作步骤，为了简洁在此不再赘述。
作为另一种可能的实施例，本申请还提供一种黑匣子数据的管理系统，该系统包括如图1所示的云数据中心、智能驾驶汽车，云数据中心通过网络与智能驾驶汽车相连，云数据中心用于为智能驾驶汽车提供云存储器，以便于根据黑匣子数据的存储级别将全部或部分黑匣子数据存储至云数据中心中，实现对黑匣子数据的备份，智能驾驶汽车包括黑匣子 设备和检测控制器，分别用于实现图3所示黑匣子数据管理方法中黑匣子设备和检测控制器所执行的操作步骤，为了简洁在此不再赘述。
上述实施例，可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时，上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载或执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质。半导体介质可以是固态硬盘(solid state drive,SSD)。
以上所述，仅为本申请的具体实施方式。熟悉本技术领域的技术人员根据本申请提供的具体实施方式，可想到变化或替换，都应涵盖在本申请的保护范围之内。

Claims (20)

  1. 一种智能驾驶汽车中黑匣子数据的管理方法，其特征在于，所述方法包括：
    黑匣子设备根据黑匣子触发事件获取黑匣子数据，所述黑匣子设备用于管理所述智能驾驶汽车中所述黑匣子数据；
    所述黑匣子设备根据所述黑匣子触发事件的事件类型和数据类型评估所述黑匣子数据的存储级别；
    所述黑匣子设备根据所述存储级别和预置规则存储所述黑匣子数据。
  2. 根据权利要求1所述方法，其特征在于，所述黑匣子设备根据黑匣子触发事件获取所述黑匣子数据，包括：
    所述黑匣子设备实时接收检测控制器发送的黑匣子数据，其中，所述黑匣子设备和所述检测控制器相连；
    当所述黑匣子设备接收所述检测控制器发送的黑匣子触发事件通知时，所述黑匣子设备标识所述黑匣子数据的数据类型，其中，所述黑匣子触发事件通知是所述检测控制器根据黑匣子触发事件生成，所述黑匣子触发事件包括以下事件中一种或多种：驾驶模式转换事件和驾驶行驶风险边界事件，所述数据类型包括责任定界数据、辅助定界数据和风险数据。
  3. 根据权利要求2所述方法，其特征在于，所述驾驶模式转换事件包括以下情况中至少一种：驾驶员将智能驾驶汽车的驾驶模式切换至智能驾驶模式、驾驶员主动将所述智能驾驶汽车的驾驶模式切换至非智能驾驶模式、驾驶员被动将智能驾驶车的驾驶模式切换至非智能驾驶模式。
  4. 根据权利要求2所述方法，其特征在于，所述驾驶行驶风险边界事件包括以下情况中至少一种：
    当所述智能驾驶汽车运行在智能驾驶模式时，如果所述智能驾驶汽车出现与其他汽车或物体的碰撞；
    当所述智能驾驶汽车运行在智能驾驶模式时，所述智能驾驶汽车与其他汽车之间的间距达到预设阈值，所述智能驾驶汽车紧急刹车或紧急变道所导致的前向或侧向碰撞风险事件；或者，
    当所述智能驾驶汽车出现碰撞时，会出现超过边界值的负加速度。
  5. 根据权利要求1所述方法，其特征在于，所述黑匣子设备根据黑匣子触发事件类型和数据类型确定所述黑匣子数据的存储级别，包括：
    当触发事件类型为碰撞时，则将责任定界数据划分为第一级存储数据；其中，所述责任界定数据用于标识对能够明确碰撞中责任的数据；
    当触发事件类型为碰撞时，则将辅助定界数据划分为第二级存储数据；其中，所述辅助界定数据用于标识辅助明确碰撞中责任的数据；
    当触发事件类型为非碰撞时，将风险数据划分为第三级存储数据。
  6. 根据权利要求1-5中任一所述方法，其特征在于，所述黑匣子设备根据所述存储级别和预置规则存储黑匣子数据，包括：
    当所述黑匣子数据被划分为所述第一级存储数据时，分别将责任定界数据存储至黑匣子设备的本地存储器和云存储器，且上述责任定界数据永久存储至黑匣子设备的本地存储器和云存储器，所述本地存储器为所述黑匣子设备中存储器，所述云存储器为所述云服务中心提供给所述黑匣子设备的存储器，所述黑匣子设备和所述云存储器通过网络进行通信；
    当所述黑匣子数据被划分为所述第二级存储数据时，将责任界定数据存储至黑匣子设备的本地存储器，并将上述辅助定界数据发送至云服务数据中心，进而存储至云存储器，且上述辅助定界数据无需永久存储至黑匣子设备的本地存储器和云存储器；
    当所述黑匣子数据被划分为所述第三级存储数据时，将风险数据划分为第三级存储数据，将风险数据存储至黑匣子设备的本地存储器，并将上述风险数据发送至云服务数据中心，进而存储至云存储器，上述风险数据无需永久存储至黑匣子设备的本地存储器和云存储器。
  7. 根据权利要求6所述方法，其特征在于，所述黑匣子设备在存储所述黑匣子数据时，设置所述本地存储器和所述云存储器中存储数据的时长，当满足第一阈值时，删除所述本地存储器和/或所述云存储器中存储的全部或部分数据。
  8. 根据权利要求1所述方法，其特征在于，所述黑匣子触发事件包括：
    所述智能驾驶汽车处于非智能驾驶模式时，驾驶员通过人机交互控制器开启智能驾驶模式；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员踩刹车板；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员转动方向盘；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员通过所述人机交互控制器将智能驾驶汽车切换为手动驾驶模式；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车出现硬件故障，所述硬件故障包括处理器复位、传感器故障；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车出现与其他汽车或物体的碰撞；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车紧急刹车；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车瞬时加速度超过预设值。
  9. 根据权利要求1-5，8中个任一项所述方法，其特征在于，所述黑匣子设备根据所述黑匣子触发事件的事件类型和数据类型评估所述黑匣子数据的存储级别，包括：
    当所述智能驾驶汽车发生碰撞时，将触发事件、时间、触发前后预设时段内的关键定界数据、系统状态、定位、规控结构化数据、近距离交通参与者结构化数据以及 碰撞方向上传感器数据中的一项或者多项永久存储至本地存储器和云存储器，其中，车身数据包括车速、引擎速度、底盘电子控制单元状态和安全带状态中的一项或者多项；或者
    当所述智能驾驶汽车发生碰撞时，将发生触发事件前后预设时段内的所述智能驾驶汽车的传感器数据和/或主要辅助定界事故的数据存储至本地存储器和云端存储器，并在时长满足第二阈值时删除；或者
    当所述智能驾驶汽车未发生碰撞时，将发生触发事件前后预设时段内的：所述智能驾驶汽车中所有传感器数据，以及感知、融合、定位、规控结构化数据、驾驶员状态、驾驶主体以及车身数据中的一项或者多项存储至本地存储器和云存储器，并在存储云存储器完成存储后删除所述本地存储器中存储的数据。
  10. 一种智能驾驶汽车的黑匣子数据管理装置，其特征在于，所述管理装置包括获取单元、评估单元和存储单元；
    所述获取单元，用于根据黑匣子触发事件获取黑匣子数据，所述管理装置用于管理所述智能驾驶汽车中所述黑匣子数据；
    所述评估单元，用于根据所述黑匣子触发事件的事件类型和数据类型评估所述黑匣子数据的存储级别；
    所述存储单元，用于根据所述存储级别和预置规则存储所述黑匣子数据。
  11. 根据权利要求10所述黑匣子数据管理装置，其特征在于，所述获取单元还包括接收单元和标识单元，
    所述接收单元，用于实时接收所述检测控制器发送的黑匣子数据，其中，所述黑匣子设备和所述检测控制器相连；
    所述标识单元，用于在接收检测控制器发送的黑匣子触发事件通知时，标识所述黑匣子数据的数据类型，其中，所述黑匣子触发事件通知是所述检测控制器根据黑匣子触发事件生成，所述黑匣子触发事件包括以下事件中一种或多种：驾驶模式转换事件和驾驶行驶风险边界事件，所述数据类型包括责任定界数据、辅助定界数据和风险数据。
  12. 根据权利要求10所述黑匣子数据管理装置，其特征在于，
    所述评估单元，还用于在触发事件类型为碰撞时，将责任定界数据划分为第一级存储数据；其中，所述责任界定数据用于标识对能够明确碰撞中责任的数据；或，在触发事件类型为碰撞时，将辅助定界数据划分为第二级存储数据；其中，所述辅助界定数据用于标识辅助明确碰撞中责任的数据；或，在触发事件类型为非碰撞时，将风险数据划分为第三级存储数据。
  13. 根据权利要求10-12任一所述黑匣子数据管理装置，其特征在于，
    所述存储单元，还用于当所述黑匣子数据被划分为所述第一级存储数据时，分别将责任定界数据存储至黑匣子设备的本地存储器和云存储器，且上述责任定界数据永 久存储至黑匣子设备的本地存储器和云存储器，所述本地存储器为所述管理装置中存储器，所述云存储器为所述云服务中心提供给所述黑匣子的存储器，所述黑匣子设备和所述云存储器通过网络进行通信；
    当所述黑匣子数据被划分为所述第二级存储数据时，将责任界定数据存储至黑匣子设备的本地存储器，并将上述辅助定界数据发送至云服务数据中心，进而存储至云存储器，且上述辅助定界数据无需永久存储至黑匣子设备的本地存储器和云存储器；
    当所述黑匣子数据被划分为所述第三级存储数据时，将风险数据划分为第三级存储数据，将风险数据存储至黑匣子设备的本地存储器，并将上述风险数据发送至云服务数据中心，进而存储至云存储器，上述风险数据无需永久存储至黑匣子设备的本地存储器和云存储器。
  14. 根据权利要求13所述黑匣子数据管理装置，其特征在于，
    所述存储单元，还用于在存储所述黑匣子数据时，设置所述本地存储器和所述云存储器中存储数据的时长；当满足第一阈值时，删除所述本地存储器和/或所述云存储器中存储的全部或部分数据。
  15. 根据权利要求10所述黑匣子数据管理装置，其特征在于，所述驾驶模式转换事件包括以下情况中至少一种：驾驶员将智能驾驶汽车的驾驶模式切换至智能驾驶模式、驾驶员主动将智能驾驶车的驾驶模式切换至非智能驾驶模式、驾驶员被动将智能驾驶车的驾驶模式切换至非智能驾驶模式。
  16. 根据权利要求10所述黑匣子数据管理装置，其特征在于，所述驾驶行驶风险边界事件包括以下情况中至少一种：
    当所述智能驾驶汽车运行在智能驾驶模式时，如果所述智能驾驶汽车出现与其他汽车间碰撞；
    当所述智能驾驶汽车运行在智能驾驶模式时，所述智能驾驶汽车与其他汽车之间的间距达到预设阈值，所述智能驾驶汽车紧急刹车或紧急变道所导致的前向或侧向碰撞风险事件；或者，
    当所述智能驾驶汽车出现碰撞时，会出现超过边界值的负加速度。
  17. 根据权利要求10所述黑匣子数据管理装置，其特征在于，所述黑匣子触发事件包括：
    所述智能驾驶汽车处于非智能驾驶模式时，驾驶员通过人机交互控制器开启智能驾驶模式；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员踩刹车板；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员转动方向盘；或者
    所述智能驾驶汽车处于智能驾驶模式时，驾驶员通过所述人机交互控制器将智能驾驶汽车切换为手动驾驶模式；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车出现硬件故障，所述 硬件故障包括处理器复位、传感器故障；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车出现与其他汽车或物体的碰撞；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车紧急刹车；或者
    所述智能驾驶汽车处于智能驾驶模式时，所述智能驾驶汽车瞬时加速度超过预设值。
  18. 根据权利要求10至12，17中任一所述黑匣子数据管理装置，其特征在于，
    所述存储单元，还用于当所述智能驾驶汽车发生碰撞时，将触发事件、时间、触发前后预设时段内的关键定界数据、系统状态、定位、规控结构化数据、近距离交通参与者结构化数据、以及碰撞方向上传感器数据中的一项或多项永久存储至本地存储器和云存储器，其中，所述车身数据包括车速、引擎速度、底盘电子控制单元状态和安全带状态中的一项或多项；或者
    当所述智能驾驶汽车发生碰撞时，将触发前后预设时段内的所述智能驾驶汽车的传感器数据、和/或主要辅助定界事故的数据存储至本地存储器和云端存储器，并在时长满足第二阈值时删除本地存储器中存储的数据；
    当所述智能驾驶汽车未发生碰撞时，存储触发前后预设时段内的所述智能驾驶汽车中所有传感器数据，以及感知、融合、定位、规控结构化数据、驾驶员状态、驾驶主体、车声数据存储至本地存储器和云存储器，并在存储云存储器完成存储后删除所述本地存储器中存储的数据。
  19. 一种智能驾驶汽车，其特征在于，所述智能驾驶汽车包括黑匣子设备，所述黑匣子设备中包括处理器、内存、本地存储器和云存储器，其中，所述云存储器为云数据中心提供给所述智能驾驶汽车的存储器，所述内存用于存储计算机执行指令，所述智能驾驶汽车运行时，所述处理器执行所述存储器中的计算机执行指令以利用所述智能驾驶汽车中的硬件资源执行权利要求1至9中任一所述方法的操作步骤。
  20. 一种智能驾驶汽车，其特征在于，所述智能驾驶汽车包括检测控制器和黑匣子设备；
    所述检测控制器，用于检测黑匣子触发事件；根据所述黑匣子触发事件向所述黑匣子设备发送所述黑匣子触发事件检测结果通知；
    所述黑匣子设备，用于根据所述黑匣子触发事件通知获取黑匣子数据，并标识数据类型；根据触发事件类型和数据类型评估所述黑匣子数据的存储级别；按照所述黑匣子数据的存储级别和预置规则存储所述黑匣子数据。
PCT/CN2020/081534 2019-08-07 2020-03-27 智能驾驶汽车中黑匣子数据的管理方法、装置和设备 WO2021022818A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20849244.7A EP4009291A4 (en) 2019-08-07 2020-03-27 INTELLIGENT DRIVING AUTOMOBILE BLACK BOX DATA MANAGEMENT METHOD, APPARATUS AND DEVICE
US17/665,143 US20220157092A1 (en) 2019-08-07 2022-02-04 Black box data management method, apparatus, and device for intelligent driving vehicle

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910726567.X 2019-08-07
CN201910726567.XA CN110570538B (zh) 2019-08-07 2019-08-07 智能驾驶汽车中黑匣子数据的管理方法、装置和设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/665,143 Continuation US20220157092A1 (en) 2019-08-07 2022-02-04 Black box data management method, apparatus, and device for intelligent driving vehicle

Publications (1)

Publication Number Publication Date
WO2021022818A1 true WO2021022818A1 (zh) 2021-02-11

Family

ID=68774840

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081534 WO2021022818A1 (zh) 2019-08-07 2020-03-27 智能驾驶汽车中黑匣子数据的管理方法、装置和设备

Country Status (4)

Country Link
US (1) US20220157092A1 (zh)
EP (1) EP4009291A4 (zh)
CN (1) CN110570538B (zh)
WO (1) WO2021022818A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113411778A (zh) * 2021-06-03 2021-09-17 中国联合网络通信集团有限公司 一种v2x通信方法及系统
CN116244664A (zh) * 2023-03-10 2023-06-09 上海机动车检测认证技术研究中心有限公司 一种智能网联汽车自动驾驶事故的责任判定方法、装置、设备及可读存储介质

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023504386A (ja) * 2019-11-22 2023-02-03 ヒョンダイ モーター カンパニー 自律走行車両のイベントデータ記録のためのシステム
CN111145380A (zh) * 2019-12-31 2020-05-12 上海能塔智能科技有限公司 适配车载设备的上报数据处理方法、装置、电子设备
CN111462351A (zh) * 2020-03-20 2020-07-28 北京智行者科技有限公司 基于自动驾驶平台的车辆行驶数据处理方法、系统以及设备
CN111930306A (zh) * 2020-07-29 2020-11-13 北京京东乾石科技有限公司 一种数据处理方法和装置
US11994399B2 (en) * 2020-10-12 2024-05-28 Robert Bosch Gmbh Management and upload of ride monitoring data of rides of a mobility service provider
CN114691018A (zh) * 2020-12-30 2022-07-01 大陆汽车电子（连云港）有限公司 碰撞事件数据记录方法及碰撞事件数据读取方法
CN115129232A (zh) * 2021-03-26 2022-09-30 华为技术有限公司 一种存储方法及装置
CN113190977A (zh) * 2021-04-13 2021-07-30 北京汽车研究总院有限公司 自动驾驶车辆的事故责任分析方法及装置
WO2022226689A1 (zh) * 2021-04-25 2022-11-03 华为技术有限公司 数据管理方法、装置和终端设备
CN114095301B (zh) * 2021-11-17 2024-03-12 广州小鹏自动驾驶科技有限公司 一种车辆中数据处理的方法和装置
CN115203216B (zh) * 2022-05-23 2023-02-07 中国测绘科学研究院 一种面向自动驾驶地图在线更新场景的地理信息数据分类分级及保护方法及系统
CN115167783A (zh) * 2022-08-03 2022-10-11 贵州同创科技有限公司 一种基于大数据的电力物资数据多元存储方法及系统
CN115499722A (zh) * 2022-08-23 2022-12-20 重庆长安汽车股份有限公司 车辆数据采集的熔断控制方法及装置
CN115861959A (zh) * 2023-02-24 2023-03-28 中国第一汽车股份有限公司 一种车道线识别方法、装置、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100238009A1 (en) * 2009-01-26 2010-09-23 Bryon Cook Driver Risk Assessment System and Method Employing Automated Driver Log
CN105976450A (zh) * 2016-04-27 2016-09-28 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据处理方法和装置、黑匣子系统
CN108876965A (zh) * 2018-07-24 2018-11-23 重庆长安汽车股份有限公司 用于自动驾驶人车事故判责的数据记录方法
CN109215170A (zh) * 2017-07-04 2019-01-15 百度在线网络技术（北京）有限公司 行车数据的存储方法、装置和设备
US10282922B1 (en) * 2015-03-27 2019-05-07 Sunman Engineering, Inc. Techniques for detecting and reporting a vehicle crash
CN109788025A (zh) * 2018-12-12 2019-05-21 北京世纪互联宽带数据中心有限公司 数据分级方法及其装置、电子设备、计算机可读介质
CN109830002A (zh) * 2019-01-23 2019-05-31 征辕科技(宁波)有限公司 行车事件数据记录方法、装置及事件数据记录器

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110004529A (ko) * 2009-07-08 2011-01-14 주식회사 만도 무선 스위치 트리거링 차량용 블랙박스 시스템과 그 제어방법
DE102014208638A1 (de) * 2014-05-08 2015-11-12 Continental Teves Ag & Co. Ohg Fahrerassistenzsystem und Verfahren zur automatisierten Protokollierung von Protokolldaten
EP3073449A1 (en) * 2015-03-23 2016-09-28 Continental Automotive GmbH Apparatus and method for recording data associated with a vehicle
EP3159853B1 (en) * 2015-10-23 2019-03-27 Harman International Industries, Incorporated Systems and methods for advanced driver assistance analytics
CN105243702B (zh) * 2015-11-04 2017-10-20 江苏南亿迪纳数字科技发展有限公司 一种基于云存储的汽车黑匣子数据处理方法
CN105346483B (zh) * 2015-11-04 2018-07-17 常州加美科技有限公司 一种无人驾驶车辆的人机交互系统
CN109215160A (zh) * 2017-06-30 2019-01-15 百度在线网络技术（北京）有限公司 用于黑匣子的数据发送方法和装置
CN109215162B (zh) * 2017-07-04 2021-06-15 百度在线网络技术（北京）有限公司 无人车黑匣子的数据监测方法和装置、无人车黑匣子
KR102029883B1 (ko) * 2018-01-15 2019-10-10 동국대학교 산학협력단 드론을 이용한 블랙박스 서비스 방법 및 이를 수행하기 위한 장치와 시스템
US11022971B2 (en) * 2018-01-16 2021-06-01 Nio Usa, Inc. Event data recordation to identify and resolve anomalies associated with control of driverless vehicles
US10909782B1 (en) * 2018-02-14 2021-02-02 EMC IP Holding Company LLC Data management for vehicle event data recorder
US20190302766A1 (en) * 2018-03-28 2019-10-03 Micron Technology, Inc. Black Box Data Recorder with Artificial Intelligence Processor in Autonomous Driving Vehicle
CN108961462A (zh) * 2018-07-24 2018-12-07 重庆长安汽车股份有限公司 用于自动驾驶人车事故判责的数据记录装置、系统及车辆

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100238009A1 (en) * 2009-01-26 2010-09-23 Bryon Cook Driver Risk Assessment System and Method Employing Automated Driver Log
US10282922B1 (en) * 2015-03-27 2019-05-07 Sunman Engineering, Inc. Techniques for detecting and reporting a vehicle crash
CN105976450A (zh) * 2016-04-27 2016-09-28 百度在线网络技术（北京）有限公司 无人驾驶车辆的数据处理方法和装置、黑匣子系统
CN109215170A (zh) * 2017-07-04 2019-01-15 百度在线网络技术（北京）有限公司 行车数据的存储方法、装置和设备
CN108876965A (zh) * 2018-07-24 2018-11-23 重庆长安汽车股份有限公司 用于自动驾驶人车事故判责的数据记录方法
CN109788025A (zh) * 2018-12-12 2019-05-21 北京世纪互联宽带数据中心有限公司 数据分级方法及其装置、电子设备、计算机可读介质
CN109830002A (zh) * 2019-01-23 2019-05-31 征辕科技(宁波)有限公司 行车事件数据记录方法、装置及事件数据记录器

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4009291A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113411778A (zh) * 2021-06-03 2021-09-17 中国联合网络通信集团有限公司 一种v2x通信方法及系统
CN116244664A (zh) * 2023-03-10 2023-06-09 上海机动车检测认证技术研究中心有限公司 一种智能网联汽车自动驾驶事故的责任判定方法、装置、设备及可读存储介质
CN116244664B (zh) * 2023-03-10 2023-10-20 上海机动车检测认证技术研究中心有限公司 一种智能网联汽车自动驾驶事故的责任判定方法、装置、设备及可读存储介质

Also Published As

Publication number Publication date
CN110570538A (zh) 2019-12-13
US20220157092A1 (en) 2022-05-19
EP4009291A4 (en) 2022-10-05
EP4009291A1 (en) 2022-06-08
CN110570538B (zh) 2022-05-10

Similar Documents

Publication Publication Date Title
WO2021022818A1 (zh) 智能驾驶汽车中黑匣子数据的管理方法、装置和设备
US20180357484A1 (en) Video processing device and video processing method
CN109080626B (zh) 车辆故障处理方法
CN111127931B (zh) 一种智能网联汽车的车路云协同方法、装置及系统
CN113223317B (zh) 一种更新地图的方法、装置和设备
CN113470371B (zh) 识别违规车辆的方法、系统和计算机可读存储介质
CN109544725B (zh) 一种基于事件驱动的自动驾驶事故智能处理方法
CN112306051A (zh) 一种高速公路无人驾驶交警车辆机器人系统
US10977882B1 (en) Driver health profile
CN108958248A (zh) 备份系统
WO2023179494A1 (zh) 危险预警的方法、装置和车辆
DE112020004545T5 (de) Signalverarbeitungsvorrichtung, signalverarbeitungsverfahren, programm und mobile vorrichtung
DE112021002953T5 (de) Informationsverarbeitungsvorrichtung, informationsverarbeitungsverfahren und programm
KR20210063244A (ko) 자율주행차량의 이벤트 데이터 기록을 위한 시스템
CN117015493A (zh) 自动紧急制动系统
CN116901875A (zh) 感知融合系统、车辆及控制方法
CN114734966B (zh) 基于摄像头和云端实时地图的自动紧急制动系统及方法
US20180047283A1 (en) Systems and methods for assigning responsibility during traffic incidents
CN115601852A (zh) 一种处理车辆数据的方法、装置及车辆
CN111243290B (zh) 驾驶行为数据获取和分析方法及系统
CN115240470A (zh) 基于nr-v2x的弱势交通参与者碰撞预警系统与方法
CN114511834A (zh) 一种确定提示信息的方法、装置、电子设备及存储介质
CN111275986A (zh) 一种车辆于加速车道自主汇入主干道的风险决策装置及方法
CN114572219B (zh) 自动超车方法、装置、车辆、存储介质及芯片
CN115798182B (zh) 一种摩托车的智能安全管理方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20849244

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020849244

Country of ref document: EP

Effective date: 20220303