Data collection method and system

Abstract

The embodiments of the present invention relate to a data collection method and system, an automatic driving controller and a mobile device, which can automatically, in real time and efficiently screen, record, store and display abnormal operation data from the operation data generated by the automatic driving vehicle, without human intervention, thereby reducing the cost of data collection. The data collection system includes: an automatic driving controller, which is used to monitor abnormal events of each algorithm module; generate monitoring data corresponding to the abnormal event; generate a data recording request containing scene description information and recording requirement information; an industrial computer records the target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generates and stores a local data packet containing the target topic and scene description information; generates basic data information of the data packet according to the scene description information and recording requirement information; and sends the basic data information to a cloud server.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a data acquisition method, a data acquisition system, an autonomous driving controller, an industrial computer and a mobile device. Background Art

[0002] With the upgrading of the autonomous driving industry, a large number of autonomous driving vehicles have been put into testing, mileage accumulation or operational use. The operating data generated by these autonomous driving vehicles in various operating scenarios is very large. Among these operating data, there may be some abnormal operating data that does not meet expectations, such as manual takeover caused by exceeding the current system operation design domain, false detection of obstacles, etc. Such abnormal operating data has very important reference value for autonomous driving algorithm feedback or scenario library establishment. Therefore, it is extremely important to obtain valuable abnormal operating data from the operating data of autonomous driving vehicles put into testing and operation.

[0003] At present, the main way to obtain abnormal operation data of autonomous driving vehicles is for the tester to observe whether the autonomous driving vehicle has abnormal behavior on site, record the operation data corresponding to the abnormal behavior when it is determined that the autonomous driving vehicle has abnormal behavior, and record and store the operation data as abnormal data. The accuracy of this kind of abnormal data recorded manually depends on the experience and professional ability of the tester. Different testers have different experience and professional ability, which will lead to inconsistent standards of abnormal data recorded by different testers. In addition, some abnormal situations cannot be observed from the external appearance of the autonomous driving vehicle, and there will be problems of missed detection of abnormal data. In addition, the number of autonomous driving vehicles put into test operation is huge, and this manual recording method requires a lot of human resources and is costly. Summary of the invention

[0004] The purpose of the present invention is to address the defects of the prior art and provide a data collection method and system that can automatically, in real time and efficiently screen, record, store and display abnormal operating data from the operating data generated by an autonomous driving vehicle without the need for human intervention, thereby reducing data collection costs.

[0005] To achieve the above object, a first aspect of an embodiment of the present invention provides a data acquisition system, the system comprising:

[0006] The automatic driving controller is used to monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; generate monitoring data corresponding to the abnormal events; obtain corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and send the data recording request to the industrial computer;

[0007] The industrial computer is used for, upon receiving a data recording request, recording a target topic according to a topic requirement list and a recording duration in the recording requirement information in the data recording request, and generating and storing a local data packet including the target topic and scene description information; generating basic data information of the data packet according to the scene description information and the recording requirement information; and sending the basic data information to a cloud server;

[0008] The cloud server receives and displays the basic data information.

[0009] According to a second aspect of an embodiment of the present invention, a data collection method is provided, the method comprising:

[0010] Monitor abnormal events of each algorithm module, including abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module;

[0011] Generating monitoring data corresponding to the abnormal event;

[0012] Acquire corresponding scene description information and recording requirement information according to the monitoring data, and generate a data recording request including the scene description information and recording requirement information;

[0013] Record the target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generate and store a local data packet containing the target topic and scene description information; generate basic data information of the data packet according to the scene description information and recording requirement information; and output the basic data information.

[0014] According to a third aspect of an embodiment of the present invention, an automatic driving controller is provided, comprising:

[0015] An abnormal event monitoring module is used to monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal upstream data events of each algorithm module and abnormal events occurring during the operation of each algorithm module;

[0016] A monitoring data generating module, used to generate monitoring data corresponding to the abnormal event;

[0017] The business platform is used to obtain corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and output the data recording request.

[0018] In a fourth aspect of an embodiment of the present invention, another automatic driving controller is provided, wherein in a processing chip provided with an algorithm module, an abnormal event monitoring submodule and a monitoring data generating submodule corresponding to the algorithm module are provided for each algorithm module;

[0019] An abnormal event monitoring submodule is used to monitor abnormal events of its corresponding target algorithm module, wherein the abnormal events include abnormal events of upstream data of the target algorithm module and abnormal events occurring during the operation of the target algorithm module;

[0020] A monitoring data generation submodule, used to generate monitoring data corresponding to the abnormal event monitored by the abnormal event monitoring submodule of the corresponding target algorithm module, and send the monitoring data to the business platform;

[0021] The service platform is used to obtain the corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and output the data recording request.

[0022] According to a fifth aspect of an embodiment of the present invention, an industrial computer is provided, including:

[0023] A communication module, used for receiving a data recording request and sending the data recording request to a data recording module;

[0024] A data recording module is used to record a target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and to generate and store a local data packet containing the target topic and scene description information; to generate basic data information of the data packet according to the scene description information and recording requirement information, and to output the basic data information through the communication module.

[0025] A sixth aspect of an embodiment of the present invention provides a mobile device, which includes the automatic driving controller provided by the third aspect or the fourth aspect, and / or the industrial computer provided by the fifth aspect.

[0026] The technical solution of the present invention, through the automatic driving controller + cloud server or the automatic driving controller + industrial computer + cloud server, can realize automatic, real-time and efficient screening, recording, storage and display of abnormal operation data from the operation data generated by the automatic driving vehicle. The whole process is completed automatically without human participation, which not only reduces the cost of data collection, but also does not rely on the professional ability and experience of the tester. The collected data is more comprehensive and accurate, and there is no problem of missed detection or false detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 One of the structural schematic diagrams of the data acquisition system provided in the first embodiment of the present invention;

[0028] Figure 2 A second structural diagram of the data acquisition system provided in the first embodiment of the present invention;

[0029] Figure 3 A schematic diagram of monitoring data ID provided in the first embodiment of the present invention;

[0030] Figure 3A A specific example of the monitoring data ID provided in the first embodiment of the present invention;

[0031] Figure 4 A schematic diagram of scene description information provided in Embodiment 1 of the present invention;

[0032] Figure 5 A schematic diagram of recording requirement information provided in Embodiment 1 of the present invention;

[0033] Figure 6 This is a schematic diagram of the structure of a data acquisition system in Embodiment 1 of the present invention;

[0034] Figure 7 This is one of the structural schematic diagrams of the automatic driving controller in the first embodiment of the present invention;

[0035] Figure 8 This is a second structural diagram of the automatic driving controller in the first embodiment of the present invention;

[0036] Fig. 9 This is a specific example of the service platform acquiring scene description information and recording requirement information in the first embodiment of the present invention;

[0037] Fig.10 This is a schematic diagram of the structure of an industrial computer in Embodiment 1 of the present invention;

[0038] Fig.11 This is a flow chart of the data collection method in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0041] Embodiment 1

[0042] See also Figure 1, is a structural diagram of a data acquisition system provided in Embodiment 1 of the present invention, the data acquisition system comprises an automatic driving controller 1 and a cloud server 2, the automatic driving controller 1 and the cloud server 2 can be connected by wireless communication, the automatic driving controller 1 can be arranged on a mobile device with an automatic driving function, the mobile device can be, for example, a passenger car, a truck, a bus, a minibus, a floor scrubber, a vacuum cleaner, a sweeper, a logistics delivery vehicle, a shuttle bus, an AGV (Automated Guided Vehicle), etc., the present application does not strictly limit the types of mobile devices, and they are not listed one by one here. Figure 1 The mobile device is a passenger car as an example. Among them:

[0043] The autonomous driving controller 1 is used to monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; generate monitoring data corresponding to the abnormal events; obtain corresponding scene description information and recording requirement information according to the monitoring data; record the target topic according to the topic requirement list and recording duration in the recording requirement information, and generate and store a local data packet containing the target topic and scene description information; generate basic data information of the data packet according to the scene description information and recording requirement information, and send the basic data information of the data packet to the cloud server 2;

[0044] The cloud server 2 receives and displays the basic data information.

[0045] In an optional embodiment, in order to minimize the negative impact between the data acquisition system and the autonomous driving system except for the normal transmission trigger request function, the data recording function that is not related to the normal operation of the autonomous driving system is separated and independently adapted to the industrial computer. Figure 2 FIG. 1 is a schematic diagram of the structure of another data acquisition system, wherein the data acquisition system comprises:

[0046] The automatic driving controller 1A is used to monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; generate monitoring data corresponding to the abnormal events; obtain corresponding scene description information and recording requirement information according to the monitoring data, and generate a data recording request including the scene description information and recording requirement information, and send the data recording request to the industrial computer 3;

[0047] The industrial computer 3 is used for, upon receiving a data recording request, recording a target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generating and storing a local data packet including the target topic and scene description information; generating basic data information of the data packet according to the scene description information and recording requirement information; and sending the basic data information to the cloud server 2;

[0048] The cloud server 2 receives and displays the basic data information.

[0049] In a preferred embodiment, generating monitoring data corresponding to the abnormal event specifically includes: generating monitoring data including the algorithm module identity information that generates the abnormal event, sub-node identity information, abnormal event description information and abnormal event type according to a preset data format.

[0050] The monitoring data may be message data.

[0051] In order to improve the expansibility and adaptability of the data collection and recording function, in the embodiment of the present invention, the monitoring data can be set as a monitoring data ID with a unique number, and the monitoring data ID can be a hexadecimal number (0x0000-0xFFFF), such as Figure 3 As shown, the first bit of the monitoring data ID corresponds to the identity information of the algorithm module (for example, the identity information can be the name or number of the algorithm module, etc.), the second bit corresponds to the identity information of the sub-node under the algorithm module (for example, the name of the sub-node in the algorithm module that generates the abnormal event), the third bit corresponds to the abnormal event type, and the fourth bit corresponds to the abnormal event description information. For example, 0x1000 means that the laser node of the perception module reports that the top laser radar receives data timeout, such as Figure 3A shown.

[0052] In an optional embodiment, a correspondence between monitoring data and scene description information and recording requirement information may be preset, and the aforementioned obtaining corresponding scene description information and recording requirement information according to the monitoring data specifically includes: obtaining scene description information and recording requirement information corresponding to the monitoring data from the preset correspondence between monitoring data and scene description information and recording requirement information. The correspondence may be a correspondence between monitoring data ID and scene description information and recording requirement information, and the expression form of the correspondence may be a list, a tree structure, etc., which is not strictly limited in this application.

[0053] In an embodiment of the present invention, the recording requirement information includes a topic requirement list, a recording duration and a storage path; a target topic is recorded according to the topic requirement list and the recording duration in the recording requirement information in the data recording request, and a local data packet containing the target topic and scene description information is generated and stored, specifically including: determining the target topic from the topic requirement list according to the recording duration, and recording the target topic; packaging the target topic and scene description information to generate a local data packet, and storing the local data packet according to the storage path.

[0054] In some embodiments, the scene description information may include scene description, scene label, mobile device parameters, map name and other information. Taking the aforementioned monitoring data as 0x1000 as an example, the scene description information in the monitoring data is as follows: Figure 4 As shown:

[0055] Scenario description: The top lidar receives data timeout;

[0056] Scenario labels: sensing node, sensor failure, and timeout failure;

[0057] Mobile device parameters: IDPXJ000001;

[0058] Map name: map001.

[0059] In some embodiments, the recording requirement information may be as follows: Figure 5 As shown, it includes a topic requirement list, a storage path, and a recording duration (for example, 60 seconds before and 10 seconds after receiving a data recording request).

[0060] In an embodiment of the present invention, the algorithm module is arranged in the automatic driving controller 1, and the algorithm module may include but is not limited to one or more of the following: a positioning module, a perception module, a decision module, a control module, a prediction module, etc.

[0061] In an embodiment of the present invention, the data of abnormal events collected can be divided into explicit safety data and implicit optimization data. The explicit safety data can refer to data that can directly reflect the performance of autonomous driving, such as unreasonable braking and manual takeover by the driver; the implicit optimization data can refer to the time when the overall driving performance is good, but the downstream algorithm module finds an abnormality when calibrating the upstream data transmitted by the upstream algorithm module, such as data timeout, unstable detection results, etc.

[0062] In the embodiment of the present invention, the data sources of abnormal events are divided into two categories. One category is automatic mining, which uses mutual verification between different algorithm modules of the autonomous driving system, different moments of the same algorithm module, and parallel threads to discover abnormal events. For example, the downstream algorithm module verifies whether the output result of the upstream algorithm module has timed out (the difference between the timestamp of the last frame of data received and the system time exceeds the threshold). For example, whether the laser detection result in the perception module is different from the visual detection result, if not, the abnormality is confirmed. For example, for the same frame, the category of the obstacle obtained by the laser detection result and the visual detection is different, then the abnormality is confirmed. For example, if the difference between the prediction result of the prediction module and the actual result is large, then the abnormality is confirmed, for example, the position of an obstacle in the prediction result of the prediction module at time t and the actual position of the obstacle obtained at time t+1 are large. The other category is manual teaching. For example, when the autonomous driving controller is operating normally, the difference between the decision result output by the decision module and the corresponding operation of the driver's manual driving is judged to determine whether it is abnormal. For example, the decision result is to follow the front car, and the actual operation of the driver is to change lanes and overtake, then it is considered abnormal.

[0063] Preferably, the industrial computer 3 can use a 10 Gigabit Ethernet interface to communicate with the board of the automatic driving controller 1A to achieve the isolation of the hardware and data of the automatic online data collection and the automatic driving controller 1A. Figure 6 As shown, the algorithm modules in the automatic driving controller 1A are distributed on multiple processing chips; each processing chip can transmit data via a Gigabit Ethernet interface; and the industrial computer 3 can transmit data via a 10 Gigabit Ethernet interface.

[0064] In one embodiment, Figure 7 As shown, the automatic driving controller 1A may include an abnormal event monitoring module 11, a monitoring data generating module 12 and a business platform 13 according to the functions, wherein:

[0065] The abnormal event monitoring module 11 is used to monitor the abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module;

[0066] A monitoring data generating module 12, configured to generate monitoring data corresponding to the abnormal event;

[0067] The service platform 13 is used to obtain corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and output the data recording request.

[0068] In another embodiment, Figure 8As shown, the automatic driving controller 1 includes a business platform 13. In a processing chip provided with an algorithm module, an abnormal event monitoring submodule and a monitoring data generating submodule corresponding to the algorithm module are provided for each algorithm module;

[0069] An abnormal event monitoring submodule is used to monitor abnormal events of its corresponding target algorithm module, wherein the abnormal events include abnormal events of upstream data of the target algorithm module and abnormal events occurring during the operation of the target algorithm module;

[0070] A monitoring data generation submodule, used to generate monitoring data corresponding to the abnormal event monitored by the abnormal event monitoring submodule of the corresponding target algorithm module, and send the monitoring data to the business platform;

[0071] The service platform 13 is used to obtain corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and output the data recording request.

[0072] Taking the monitoring data ID of 0x1000 as an example, the business platform 13 obtains the scene description information and recording requirement information according to the monitoring data ID. Fig. 9 shown.

[0073] The structure of the industrial computer 3 in the embodiment of the present invention is as follows: Fig.10 As shown, including:

[0074] The communication module 31 is used to receive a data recording request and send the data recording request to the data recording module 32;

[0075] The data recording module 32 is used to record the target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generate and store a local data packet containing the target topic and scene description information; generate basic data information of the data packet according to the scene description information and recording requirement information, and output the basic data information through the communication module.

[0076] The basic data information may include information such as the name of the local data packet, the size of the local data packet and the storage location of the local data packet, the mobile device ID, and the scene description information.

[0077] The cloud server 2 can display the information in the basic data information in a classified manner and make it available for users to view and download.

[0078] The technical solution of the present invention can automatically screen, record, store and display data when abnormal conditions occur during the operation of autonomous driving mobile devices. On the one hand, it can timely and comprehensively monitor the data corresponding to abnormal events in the algorithm module, avoid the loss or hiding of important data with reference value, and provide basic data for the subsequent use of the collected data to feedback the algorithm, reconstruct the scene simulation and debug the algorithm functions and parameters to improve the various algorithm modules of autonomous driving; on the other hand, this solution can monitor the operating status of a large number of mobile devices online, automatically collect and screen data, without manual participation, saving labor costs, and will not cause inconsistent data collection standards due to different professional capabilities and experiences of different personnel.

[0079] Embodiment 2

[0080] Based on the same inventive concept as the above-mentioned embodiment 1, the second embodiment of the present invention further provides a data collection method, the method flow is as follows: Fig.11 As shown, including:

[0081] Step 100: Monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module.

[0082] Step 110: Generate monitoring data corresponding to the abnormal event.

[0083] Step 120: Obtain corresponding scene description information and recording requirement information according to the monitoring data, and generate a data recording request including the scene description information and recording requirement information.

[0084] Step 130: Record the target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generate and store a local data packet containing the target topic and scene description information.

[0085] Step 140: Generate basic data information of the data packet according to the scene description information and the recording requirement information, and output the basic data information.

[0086] Preferably, in the aforementioned step 110, generating monitoring data corresponding to the abnormal event specifically includes: generating monitoring data including the algorithm module identity information generating the abnormal event, sub-node identity information, abnormal event description information and abnormal event type according to a preset data format.

[0087] Preferably, in the aforementioned step 120, obtaining corresponding scene description information and recording requirement information according to the monitoring data specifically includes: obtaining the scene description information and recording requirement information corresponding to the monitoring data from the correspondence between preset monitoring data and the scene description information and recording requirement information.

[0088] Preferably, the recording requirement information includes a topic requirement list, recording duration and a storage path; in the step 130, the target topic is recorded according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and a local data packet containing the target topic and scene description information is generated and stored, specifically including: determining the target topic from the topic requirement list according to the recording duration, and recording the target topic; packaging the target topic and scene description information to generate a local data packet, and storing the local data packet according to the storage path.

[0089] Embodiment 3

[0090] Embodiment 3 of the present invention provides a mobile device, on which is disposed any one of the autonomous driving controllers provided in Embodiment 1.

[0091] The mobile device may be any device capable of realizing the automatic driving function, such as a vehicle (passenger car, minibus, bus, sweeper, sanitation vehicle, floor scrubber, vacuum cleaner, mop, patrol car, van, semi-trailer, etc.), robot, sweeper, AGV, etc. All of them are omitted here.

[0092] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the determination module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0093] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0094] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The above computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) methods. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0095] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0096] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented by hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0097] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data acquisition system, characterized in that: The system comprises: The automatic driving controller is used to monitor abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; generate monitoring data corresponding to the abnormal events; obtain corresponding scene description information and recording requirement information according to the monitoring data, generate a data recording request including the scene description information and recording requirement information, and send the data recording request to the industrial computer; The industrial computer is used for, upon receiving a data recording request, recording a target topic according to a topic requirement list and a recording duration in the recording requirement information in the data recording request, and generating and storing a local data packet including the target topic and scene description information; generating basic data information of the data packet according to the scene description information and the recording requirement information; and sending the basic data information to a cloud server; The cloud server receives and displays the basic data information.

2. The system according to claim 1, characterized in that The automatic driving controller generates monitoring data corresponding to the abnormal event, specifically including: According to a preset data format, monitoring data including the algorithm module identity information that generates the abnormal event, the sub-node identity information, the abnormal event description information and the abnormal event type is generated.

3. The system according to claim 1, characterized in that The automatic driving controller obtains corresponding scene description information and recording requirement information according to the monitoring data, specifically including: The scene description information and the recording requirement information corresponding to the monitoring data are obtained from the corresponding relationship among the preset monitoring data, the scene description information and the recording requirement information.

4. The system according to claim 1, characterized in that The recording requirement information includes a topic requirement list, recording duration and storage path; Recording a target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generating and storing a local data packet containing the target topic and scene description information, specifically including: Determine the target topic from the topic requirement list based on the recording duration, and record the target topic; The target topic and scene description information are packaged to generate a local data packet, and the local data packet is stored according to the storage path.

5. The system according to claim 1, characterized in that The algorithm modules in the autonomous driving controller are distributed on at least one processing chip; Each processing chip transmits data via a Gigabit Ethernet interface; The industrial computer transmits data via a 10 Gigabit Ethernet interface.

6. A data acquisition system, characterized in that: The system comprises: The autonomous driving controller monitors abnormal events of each algorithm module, wherein the abnormal events include abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; generates monitoring data corresponding to the abnormal events; obtains corresponding scene description information and recording requirement information according to the monitoring data; records a target topic according to the topic requirement list and recording duration in the recording requirement information, and generates and stores a local data packet containing the target topic and scene description information; generates basic data information of the data packet according to the scene description information and recording requirement information, and sends the basic data information of the data packet to a cloud server; The cloud server receives and displays the basic data information.

7. A data collection method, characterized in that: The method comprises: Monitor abnormal events of each algorithm module, including abnormal events of upstream data of each algorithm module and abnormal events occurring during the operation of each algorithm module; Generating monitoring data corresponding to the abnormal event; Acquire corresponding scene description information and recording requirement information according to the monitoring data, and generate a data recording request including the scene description information and recording requirement information; Record the target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generate and store a local data packet containing the target topic and scene description information; generate basic data information of the data packet according to the scene description information and recording requirement information; and output the basic data information.

8. The method according to claim 7, characterized in that The recording requirement information includes a topic requirement list, recording duration and storage path; Recording a target topic according to the topic requirement list and recording duration in the recording requirement information in the data recording request, and generating and storing a local data packet containing the target topic and scene description information, specifically including: Determine the target topic from the topic requirement list based on the recording duration, and record the target topic; The target topic and scene description information are packaged to generate a local data packet, and the local data packet is stored according to the storage path.

Images