Data processing system of autonomous vehicle
Through the communication between the cloud and autonomous vehicles, reliability testing tasks are generated and executed, fault scripts are injected and data are collected, and emergency measures are analyzed, the problem of inefficient reliability detection of autonomous vehicles is solved, and efficient and accurate automated testing is achieved.
Patent Information
- Application Number
- CN202410160265.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-04
- Publication Date
- 2025-08-08
AI Technical Summary
The prior art is difficult to efficiently and accurately detect the reliability of autonomous vehicles under various faults, and the efficiency of manual remote testing is inefficient, making it impossible to fully cover potential risks.
Through communication between the cloud and autonomous vehicles, reliability testing tasks are generated and executed, fault script information is injected, and operation data is collected, and the cloud analyzes the effectiveness of emergency measures to achieve automated testing.
It realizes comprehensive testing of autonomous vehicles under various faults, improves test coverage and efficiency, supports simultaneous testing of multiple vehicles, and improves the accuracy and efficiency of detection.
Smart Images
Figure CN120448164A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to autonomous driving vehicle technology, and more particularly, to a data processing system for an autonomous driving vehicle. Background Art
[0002] With the rapid development of artificial intelligence technology, many automobile manufacturers have begun to develop and manufacture cars with autonomous driving functions.
[0003] One of the biggest obstacles to the commercialization of autonomous vehicles is the lack of adequately addressed reliability and safety issues. Despite extensive virtual simulation and road testing, the simulation software itself suffers from reliability issues, and it is difficult to exhaust all corner cases. Summary of the Invention
[0004] One objective of the present disclosure is to provide a new technical solution for a data processing system for an autonomous driving vehicle.
[0005] According to a first aspect of the present disclosure, a data processing system for an autonomous driving vehicle is provided, comprising: a cloud and at least one autonomous driving vehicle; wherein,
[0006] The cloud is used to create at least one reliability test task; wherein the reliability test task includes an identification information set, wherein the identification information set includes identification information of the autonomous driving vehicle and identification information of the corresponding injected fault;
[0007] The cloud is used to send the reliability test task to the corresponding autonomous driving vehicle according to the identification information of the autonomous driving vehicle;
[0008] The autonomous driving vehicle is configured to send a request for acquiring script information of the injected fault to the cloud according to the identification information of the injected fault;
[0009] The cloud is used to send the fault injection script information to the corresponding autonomous driving vehicle;
[0010] The autonomous driving vehicle is configured to execute the fault injection script information while driving autonomously, and send the collected operating data to the cloud;
[0011] The cloud is used to determine, based on the operating data, the effectiveness of the corresponding emergency measures after the autonomous driving vehicle executes the fault injection script information, so as to determine the reliability test result of the autonomous driving vehicle.
[0012] Optionally, the cloud is also used to generate a script information database for injecting faults; wherein the script information database for injecting faults includes identification information of the injected faults and corresponding script information for injecting faults.
[0013] Optionally, the fault injection script information includes a fault injection script, a fault duration, and a fault elimination script.
[0014] Optionally, in a case where the identification information of the injected fault includes multiple different injected faults, the reliability test task further includes execution sequence information of the injected faults.
[0015] Optionally, the injected fault is at least one of a hardware fault of the autonomous driving system of the autonomous driving vehicle and a software fault of the autonomous driving system of the autonomous driving vehicle.
[0016] Optionally, the operating data includes performance indicator data and log data collected after the autonomous driving vehicle executes the fault injection script information.
[0017] Optionally, the cloud is also used to determine that the reliability test result of the autonomous driving vehicle is in line with expectations when it is determined that the corresponding emergency measures have taken effect after the autonomous driving vehicle executes the fault injection script information.
[0018] Optionally, when the injected fault is an abnormal power-off of the lidar, the operating data includes vehicle speed information and automatic parking information collected after the autonomous driving vehicle executes the script information of the abnormal power-off of the lidar; wherein,
[0019] The cloud is used to determine whether the autonomous driving vehicle automatically decelerates and completes the parking operation after the laser radar abnormally loses power based on the collected vehicle speed information and automatic parking information.
[0020] Optionally, when the injected fault is an abnormal navigation power-off, the operating data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the abnormal navigation power-off; wherein,
[0021] The cloud is used to determine whether the autonomous driving vehicle automatically brakes and completes the parking operation after power is cut off due to navigation abnormality based on the collected automatic braking information and automatic parking information.
[0022] Optionally, when the injected fault is a GPU abnormality, the operation data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the GPU abnormality; wherein,
[0023] The cloud is used to determine whether the autonomous driving vehicle automatically brakes and completes the parking operation after a GPU abnormality occurs based on the collected automatic braking information and automatic parking information.
[0024] The data processing system for autonomous driving vehicles provided by the present disclosure realizes automated testing of the reliability of autonomous driving vehicles, can cover the testing of autonomous driving vehicles under various faults, and can also realize simultaneous testing of multiple autonomous driving vehicles, thereby improving coverage and testing efficiency.
[0025] Features and advantages of the embodiments of the present specification will become apparent from the following detailed description of exemplary embodiments of the present specification with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and, together with the description, serve to explain the principles of the embodiments of the specification.
[0027] Figure 1 It is a hardware configuration diagram of an electronic device provided by an embodiment of the present disclosure and can be used to implement the embodiment of the present disclosure.
[0028] Figure 2 1 is a processing flow chart of a data processing method executed by a data processing system of an autonomous driving vehicle according to an embodiment of the present disclosure.
[0029] Figure 3 is a schematic diagram of a reliability test task according to an embodiment of the present disclosure.
[0030] Figure 4 It is a processing flow chart of a data processing method executed by a data processing system of an autonomous driving vehicle according to an embodiment of the present disclosure.
[0031] Figure 5 1 is a processing flow chart of a data processing method for an autonomous driving vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0032] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.
[0033] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.
[0034] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0035] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.
[0036] At present, the reliability verification of autonomous driving vehicles needs to be performed by manually logging into the vehicle remotely. Due to the limitations and complexity of observation methods, the verification effect is very limited and deep-seated hidden dangers cannot be unearthed. In addition, manual testing is tedious and time-consuming, and inefficient. How to efficiently and accurately detect the reliability of autonomous driving systems is a problem that urgently needs to be solved. The data processing method and data processing system provided by the present invention realize the automated testing of the reliability of autonomous driving vehicles, which can cover the testing of autonomous driving vehicles under various faults, and can also realize the simultaneous testing of multiple autonomous driving vehicles, thereby improving coverage and testing efficiency.
[0037] <Hardware Configuration>
[0038] Figure 1 1 is a schematic diagram of the structure of an electronic device that can be used to implement the embodiment of the present disclosure. The electronic device can be used to implement the data processing method of the embodiment of the present disclosure.
[0039] The electronic device 1000 can be a server, a smart phone, a portable computer, a desktop computer, a tablet computer, etc., which is not limited here.
[0040] The electronic device 1000 may include, but is not limited to, a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. The processor 1100 may be a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MCU), or the like, and is configured to execute computer programs / instructions, which may be written using an instruction set such as an x86, Arm, RISC, MIPS, or SSE architecture. The memory 1200 may include, for example, ROM (read-only memory), RAM (random access memory), or a non-volatile memory such as a hard disk. The interface device 1300 may include, for example, a USB interface, a serial interface, or a parallel interface. The communication device 1400 may be capable of wired communication using optical fiber or cable, or wireless communication, specifically, WiFi, Bluetooth, 2G / 3G / 4G / 5G, or the like. The display device 1500 may be, for example, an LCD display or a touchscreen display. The input device 1600 may include, for example, a touchscreen, a keyboard, or somatosensory input. The speaker 1700 is used to output audio signals, and the microphone 1800 is used to collect audio signals.
[0041] As used in the embodiment of the present disclosure, the memory 1200 of the electronic device 1000 is used to store computer programs / instructions, which are used to control the processor 1100 to operate to implement the data processing method according to the embodiment of the present disclosure. Technicians can design the computer program / instructions according to the scheme disclosed in the present disclosure. How the computer program / instructions control the processor to operate is well known in the art and will not be described in detail here. The electronic device 1000 can be installed with an intelligent operating system (such as Windows, Linux, Android, IOS, etc.) and application software.
[0042] It should be understood by those skilled in the art that although Figure 1 , multiple devices of the electronic device 1000 are shown, but the electronic device 1000 of the present disclosure may only involve some of the devices, for example, only the processor 1100 and the memory 1200.
[0043] Hereinafter, various embodiments and examples of the fundamental disclosure are described with reference to the accompanying drawings.
[0044] <System Example>
[0045] In one embodiment of the present disclosure, a data processing system for an autonomous vehicle is provided. The system includes a cloud and at least one autonomous vehicle. The cloud and the autonomous vehicle can communicate, for example, using MQTTS (Message Queuing Telemetry Transport) plus SSL (Secure Sockets Layer).
[0046] The data processing steps of the data processing system of the autonomous driving vehicle according to this embodiment are shown in Figure 2 .
[0047] The cloud is used to create at least one reliability testing task; wherein the reliability testing task includes an identification information set, wherein the identification information set includes identification information of the autonomous driving vehicle and identification information of the corresponding injected fault.
[0048] Reliability test tasks are formulated based on actual needs and / or vehicle models.
[0049] The identification information of the autonomous driving vehicle is used to represent the identity information of the autonomous driving vehicle.
[0050] In one embodiment, the cloud is further used to generate a fault injection script information database, wherein the fault injection script information database includes identification information of the fault injection and corresponding fault injection script information.
[0051] Based on the interactions between the autonomous driving system and other systems, the system's interactions with the surrounding environment, and the interactions between its internal subsystems, the system identifies faults that could cause the system to malfunction. The cloud then generates a database of fault injection scripts based on these faults.
[0052] The injected fault may be at least one of a hardware fault of the autonomous driving system of the autonomous driving vehicle and a software fault of the autonomous driving system of the autonomous driving vehicle.
[0053] Hardware failures in autonomous driving systems include processors, memory, chassis, navigation, radar, cameras, and power supplies. Software failures in autonomous driving systems include abnormalities in the operating system, vehicle gateway, and various vehicle control programs.
[0054] Processor failures include excessive usage and high temperatures. Memory failures include excessive usage and abnormal memory modules. Chassis failures include power-off failure, emergency stop wiring harness failure, tire pressure sensor failure, steering gear failure, door controller failure, and anti-slip function failure. Navigation failures include antenna failure. Radar failures include abnormal LiDAR jitter, abnormal LiDAR calibration, and abnormal ultrasonic radar. Camera failures include stains or water droplets on the camera and abnormal camera function. Power supply failures include abnormal power supply.
[0055] Operating system failures include operating system crashes, operating system freezes, system file deletion, host configuration tampering, abnormal privileged user access, and system resource occupation. Vehicle gateway failures include network jitter and communication message loss.
[0056] The hardware faults and software faults listed above are only part of the injected faults, and the injected faults may also include other types of faults.
[0057] The fault injection script information database may be in the form of a mapping table, recording the correspondence between the identification information of the fault injection and the fault injection script information.
[0058] The fault injection script information includes the fault injection script, fault duration, and fault elimination script.
[0059] A fault injection script is a computer program that causes the autonomous vehicle to experience a corresponding fault. A fault elimination script is a computer program that causes the autonomous vehicle to eliminate the corresponding fault. The fault duration is the time from the moment the autonomous vehicle executes the fault injection script.
[0060] The reliability test task may include identification information of one injected fault, or may include identification information of multiple injected faults. In the case where there are multiple identification information of injected faults, the reliability test task also includes execution order information of the injected faults.
[0061] When multiple pieces of identification information for injected faults are provided, the duration of the fault in the fault injection script includes a first duration and a second duration. The first duration is the duration from the moment the autonomous vehicle executes the fault injection script. The second duration is the duration from the moment the autonomous vehicle executes the fault elimination script.
[0062] For example, a reliability test task includes identification information of four injected faults, namely, injected fault a, injected fault b, injected fault c, and injected fault d. The execution order information of these four injected faults is injected fault a, injected fault c, injected fault b, and injected fault d.
[0063] Figure 3 This is a schematic diagram of a reliability test task according to one embodiment of the present disclosure. This reliability test task includes identification information for four injected faults, script information for each injected fault, and information about the order in which the injected faults are executed. The script information for each injected fault includes a script for injecting the fault, a script for eliminating the fault, a first duration, and a second duration.
[0064] join Figure 3 The identification information of the four injected faults corresponds to the following four faults: LiDAR abnormality, abnormal power loss of the SIM (Subscriber Identity Module) card module, navigation abnormality, and vehicle gateway communication abnormality. The execution order of the four injected faults is LiDAR abnormality, abnormal power loss of the SIM (Subscriber Identity Module) card module, navigation abnormality, and vehicle gateway communication abnormality.
[0065] See also Figure 3 The first duration corresponding to a LiDAR anomaly is 2 minutes, and the second duration corresponding to a LiDAR anomaly is 1 minute. The first duration corresponding to an abnormal SIM card module power outage is 2 minutes, and the second duration corresponding to an abnormal SIM card module power outage is 1 minute. The first duration corresponding to a navigation anomaly is 2 minutes, and the second duration corresponding to a navigation anomaly is 1 minute. The first duration corresponding to an in-vehicle gateway communication anomaly is 2 minutes, and the second duration corresponding to an in-vehicle gateway communication anomaly is 1 minute.
[0066] The cloud is used to send reliability test tasks to the corresponding autonomous driving vehicles based on the identification information of the autonomous driving vehicles.
[0067] The reliability test can involve one or more autonomous vehicles. The electronic device communicates with the autonomous vehicles and sends the reliability test tasks to them. This allows for simultaneous testing of multiple autonomous vehicles, improving testing efficiency.
[0068] It should be noted that when multiple autonomous driving vehicles are tested simultaneously, the reliability test tasks corresponding to the multiple autonomous driving vehicles can be the same or different.
[0069] The autonomous driving vehicle is used to send a request to the cloud for obtaining the script information of the injected fault according to the identification information of the injected fault.
[0070] The request for obtaining the script information of the injected fault includes identification information of the injected fault.
[0071] The cloud is used to send the fault injection script information to the corresponding autonomous driving vehicle.
[0072] After receiving a request from the autonomous vehicle for the fault injection script, the cloud uses the fault injection identification information to search for the corresponding fault injection script in the fault injection script database. The cloud then sends the fault injection script to the corresponding autonomous vehicle.
[0073] The autonomous vehicle is used to execute the fault-injected script information while driving automatically and send the collected operation data to the cloud.
[0074] Operational data includes performance indicator data and log data collected after the autonomous driving vehicle executes the script information for injecting faults.
[0075] The cloud is used to determine the effectiveness of the corresponding emergency measures after the autonomous driving vehicle executes the fault-injected script information based on the operating data, so as to determine the reliability test results of the autonomous driving vehicle.
[0076] Specifically, the cloud is configured to determine that the reliability test result of the autonomous vehicle meets expectations if it is determined that the corresponding emergency measures have taken effect after the autonomous vehicle executes the fault-injected script information. The cloud is also configured to determine that the reliability test result of the autonomous vehicle does not meet expectations if it is determined that the corresponding emergency measures have not taken effect after the autonomous vehicle executes the fault-injected script information.
[0077] When multiple faults are injected, the cloud determines, based on operational data, whether the emergency measures corresponding to each injected fault are effective after the autonomous vehicle executes the injected fault script. If all emergency measures corresponding to each injected fault are effective, the reliability test result of the autonomous vehicle is determined to be as expected. If at least one emergency measure corresponding to an injected fault is ineffective, the reliability test result of the autonomous vehicle is determined to be as unsatisfactory. The reliability test result of the autonomous vehicle also includes identification information for the injected faults corresponding to the ineffective emergency measures.
[0078] For example, if the injected fault is an abnormal LiDAR power failure, the autonomous vehicle will collect operating data after executing the LiDAR power failure script and send this data to the cloud. This operating data includes vehicle speed information and automatic parking information collected after the autonomous vehicle executes the LiDAR power failure script. Based on this operating data, the cloud determines whether the emergency measures of deceleration and automatic parking are required after the abnormal LiDAR power failure. After determining that the emergency measures of deceleration and automatic parking are required after the abnormal LiDAR power failure, the cloud determines that the reliability test results meet expectations.
[0079] For example, the injected fault is an abnormal power-off of the navigation system, so that the autonomous driving vehicle cannot obtain its own angular velocity and acceleration during the autonomous driving process. After executing the script information of the abnormal power-off of the navigation system, the autonomous driving vehicle collects operating data and sends the operating data to the cloud. The operating data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the abnormal power-off of the navigation system. Based on the operating data, the cloud determines whether the emergency measures of automatic braking and automatic parking are generated after the abnormal power-off of the navigation system. After determining that the emergency measures of automatic braking and automatic parking are generated after the abnormal power-off of the navigation system, the cloud determines that the reliability test results are in line with expectations.
[0080] For example, if the injected fault is a GPU abnormality (GPU consumption is too high), the autonomous driving vehicle collects operating data after executing the script information of the GPU abnormality and sends the operating data to the cloud. The operating data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the GPU abnormality. Based on the operating data, the cloud determines whether emergency measures such as automatic braking and automatic parking are generated after the GPU abnormality. After determining that emergency measures such as automatic braking and automatic parking are generated after the GPU abnormality, the cloud determines that the reliability test results are in line with expectations.
[0081] Figure 4 The following is a processing flow chart of a data processing method of a data processing system for an autonomous driving vehicle according to an embodiment of the present disclosure. Figure 4 As shown, the data processing method of this embodiment may include the following steps S401 to S412.
[0082] In step S401 , the cloud generates a fault injection script information database, wherein the fault injection script information database includes identification information of the fault injection and corresponding fault injection script information.
[0083] In step S402, a reliability test task is created in the cloud; wherein the reliability test task includes an identification information set, wherein the identification information set includes the identification information of the autonomous driving vehicle and the identification information of the corresponding injected fault.
[0084] In step S403, the cloud sends the reliability test task to the corresponding autonomous driving vehicle based on the identification information of the autonomous driving vehicle.
[0085] In step S404, the autonomous driving vehicle receives a reliability test task sent by the electronic device.
[0086] In step S405, the autonomous driving vehicle sends a request to the cloud for obtaining the script information of the injected fault based on the identification information of the injected fault.
[0087] In step S406, the cloud receives a request from the autonomous driving vehicle for obtaining the script information for injecting the fault.
[0088] In step S407 , the cloud obtains corresponding fault injection script information from the fault injection script information database, and sends the fault injection script information to the autonomous driving vehicle.
[0089] Step S408: The autonomous driving vehicle receives and executes the fault injection script information sent by the electronic device.
[0090] Step S409: The autonomous driving vehicle collects operating data after executing the script information of the injected fault.
[0091] In step S410 , the autonomous driving vehicle sends the operating data after executing the script information injected with the fault to the cloud.
[0092] In step S411, the cloud receives the operating data collected after the autonomous driving vehicle executes the script information for injecting faults.
[0093] In step S412, the cloud determines the reliability test result of the autonomous driving vehicle based on the operating data.
[0094] The data processing system for autonomous driving vehicles provided by the present disclosure realizes automated testing of the reliability of autonomous driving vehicles, can cover the testing of autonomous driving vehicles under various faults, and can also realize simultaneous testing of multiple autonomous driving vehicles, thereby improving coverage and testing efficiency.
[0095] <Computer-readable storage medium embodiment>
[0096] The embodiments of the present disclosure further provide a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the data processing method disclosed in any of the aforementioned embodiments is implemented.
[0097] <Method Example>
[0098] In one embodiment of the present disclosure, a data processing method is provided, which is applied to the cloud and autonomous vehicles.
[0099] See also Figure 5 The data processing method of this embodiment may include the following steps S510 to S560.
[0100] In step S510, at least one reliability test task is created in the cloud; wherein the reliability test task includes an identification information set, wherein the identification information set includes identification information of the autonomous driving vehicle and identification information of the corresponding injected fault.
[0101] In step S520, the cloud sends the reliability test task to the corresponding autonomous driving vehicle based on the identification information of the autonomous driving vehicle.
[0102] In step S530, the autonomous driving vehicle sends a request to the cloud for obtaining the script information of the injected fault according to the identification information of the injected fault.
[0103] In step S540, the cloud sends the script information of the injected fault to the corresponding autonomous driving vehicle.
[0104] In step S550, the autonomous driving vehicle executes the fault-injected script information while driving automatically, and sends the collected operating data to the cloud.
[0105] In step S560, the cloud determines, based on the operating data, whether the corresponding emergency measures are effective after the autonomous driving vehicle executes the script information for injecting the fault, so as to determine the reliability test result of the autonomous driving vehicle.
[0106] In one embodiment, the method further includes: generating a fault injection script information database on the cloud, wherein the fault injection script information database includes identification information of the fault injection and corresponding fault injection script information.
[0107] Based on the interactions between the autonomous driving system and other systems, the system's interactions with the surrounding environment, and the interactions between its internal subsystems, the system identifies faults that could cause the system to malfunction. The cloud then generates a database of fault injection scripts based on these faults.
[0108] The injected fault may be at least one of a hardware fault of the autonomous driving system of the autonomous driving vehicle and a software fault of the autonomous driving system of the autonomous driving vehicle.
[0109] Hardware failures in autonomous driving systems include processors, memory, chassis, navigation, radar, cameras, and power supplies. Software failures in autonomous driving systems include abnormalities in the operating system, vehicle gateway, and various vehicle control programs.
[0110] Processor failures include excessive usage and high temperatures. Memory failures include excessive usage and abnormal memory modules. Chassis failures include power-off failure, emergency stop wiring harness failure, tire pressure sensor failure, steering gear failure, door controller failure, and anti-slip function failure. Navigation failures include antenna failure. Radar failures include abnormal LiDAR jitter, abnormal LiDAR calibration, and abnormal ultrasonic radar. Camera failures include stains or water droplets on the camera and abnormal camera function. Power supply failures include abnormal power supply.
[0111] Operating system failures include operating system crashes, operating system freezes, system file deletion, host configuration tampering, abnormal privileged user access, and system resource occupation. Vehicle gateway failures include network jitter and communication message loss.
[0112] The hardware faults and software faults listed above are only part of the injected faults, and the injected faults may also include other types of faults.
[0113] The fault injection script information database may be in the form of a mapping table, recording the correspondence between the identification information of the fault injection and the fault injection script information.
[0114] The fault injection script information includes the fault injection script, fault duration, and fault elimination script.
[0115] A fault injection script is a computer program that causes the autonomous vehicle to experience a corresponding fault. A fault elimination script is a computer program that causes the autonomous vehicle to eliminate the corresponding fault. The fault duration is the time from the moment the autonomous vehicle executes the fault injection script.
[0116] The reliability test task may include identification information of one injected fault, or may include identification information of multiple injected faults. In the case where there are multiple identification information of injected faults, the reliability test task also includes execution order information of the injected faults.
[0117] When multiple pieces of identification information for injected faults are provided, the duration of the fault in the fault injection script includes a first duration and a second duration. The first duration is the duration from the moment the autonomous vehicle executes the fault injection script. The second duration is the duration from the moment the autonomous vehicle executes the fault elimination script.
[0118] In one embodiment, the reliability test task can involve one or more autonomous vehicles. The electronic device, through a communication connection established with the autonomous vehicle, sends the reliability test task to the corresponding autonomous vehicle. This allows for simultaneous testing of multiple autonomous vehicles, improving testing efficiency.
[0119] When multiple autonomous driving vehicles are tested simultaneously, the reliability test tasks corresponding to the multiple autonomous driving vehicles can be the same or different.
[0120] In one embodiment, the method further includes: when the cloud determines that the corresponding emergency measures have taken effect after the autonomous driving vehicle executes the script information for injecting the fault, determining that the reliability test result of the autonomous driving vehicle is in line with expectations.
[0121] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For the electric vehicle embodiment, its related parts can be referred to the partial description of the method embodiment.
[0122] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0123] The embodiments of this specification may be systems, methods, and / or computer program products. The computer program product may include a computer-readable storage medium carrying computer instructions for causing a processor to implement various aspects of the embodiments of this specification.
[0124] A computer-readable storage medium can be a tangible device that can hold and store computer instructions for use by a computer instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which computer instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.
[0125] The computer instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network layer, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network layer can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network layer adapter card or network layer interface in each computing / processing device receives computer instructions from the network layer and forwards the computer instructions for storage in a computer-readable storage medium in each computing / processing device.
[0126] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of this specification. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of a computer instruction, and the module, program segment or part of a computer instruction contains one or more executable computer instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.
[0127] The embodiments of the present specification have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. A data processing system for an autonomous driving vehicle, characterized in that: The system includes: a cloud and at least one autonomous driving vehicle; wherein, The cloud is used to create at least one reliability test task; wherein the reliability test task includes an identification information set, wherein the identification information set includes identification information of the autonomous driving vehicle and identification information of the corresponding injected fault; The cloud is used to send the reliability test task to the corresponding autonomous driving vehicle according to the identification information of the autonomous driving vehicle; The autonomous driving vehicle is configured to send a request for acquiring script information of the injected fault to the cloud according to the identification information of the injected fault; The cloud is used to send the fault injection script information to the corresponding autonomous driving vehicle; The autonomous driving vehicle is configured to execute the fault injection script information while driving autonomously, and send the collected operating data to the cloud; The cloud is used to determine, based on the operating data, the effectiveness of the corresponding emergency measures after the autonomous driving vehicle executes the fault injection script information, so as to determine the reliability test result of the autonomous driving vehicle.
2. The system according to claim 1, wherein: The cloud is also used to generate a fault injection script information database; wherein the fault injection script information database includes identification information of the fault injection and corresponding fault injection script information.
3. The system according to claim 1, wherein: The fault injection script information includes the fault injection script, the duration of the fault, and the fault elimination script.
4. The system according to claim 1, wherein: In a case where the identification information of the injected fault includes a plurality of different injected faults, the reliability test task further includes execution sequence information of the injected faults.
5. The system according to claim 1, wherein: The injected fault is at least one of a hardware fault of the autonomous driving system of the autonomous driving vehicle and a software fault of the autonomous driving system of the autonomous driving vehicle.
6. The system according to claim 1, wherein: The operation data includes performance indicator data and log data collected after the autonomous driving vehicle executes the fault injection script information.
7. The system according to claim 1, wherein: The cloud is also used to determine that the reliability test result of the autonomous driving vehicle is in line with expectations when it is determined that the corresponding emergency measures have taken effect after the autonomous driving vehicle executes the script information of the injected fault.
8. The system according to any one of claims 1 to 7, characterized in that: In the case where the injected fault is an abnormal power-off of the lidar, the operating data includes vehicle speed information and automatic parking information collected after the autonomous driving vehicle executes the script information of the abnormal power-off of the lidar; wherein, The cloud is used to determine whether the autonomous driving vehicle automatically decelerates and completes the parking operation after the laser radar abnormally loses power based on the collected vehicle speed information and automatic parking information.
9. The system according to any one of claims 1 to 7, characterized in that: In the case where the injected fault is an abnormal navigation power-off, the operating data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the abnormal navigation power-off; wherein, The cloud is used to determine whether the autonomous driving vehicle automatically brakes and completes the parking operation after power is cut off due to navigation abnormality based on the collected automatic braking information and automatic parking information.
10. The system according to any one of claims 1 to 7, characterized in that: In the case where the injected fault is a GPU abnormality, the operation data includes automatic braking information and automatic parking information collected after the autonomous driving vehicle executes the script information of the GPU abnormality; wherein, The cloud is used to determine whether the autonomous driving vehicle automatically brakes and completes the parking operation after a GPU abnormality occurs based on the collected automatic braking information and automatic parking information.