Automatic driving data collection system and collection method thereof

Abstract

The present specification provides an automatic driving data collection system and a collection method thereof. The automatic driving data collection system comprises a data collection source device, a data collection host and a domain controller with a perception module. The data collection host is electrically connected between the data collection source device and the domain controller, used to receive the original image data and re-output the original image data to the domain controller, so as to realize the collection of the original raw format data and meet the high requirements of automatic driving on the perception accuracy and reliability.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to an autonomous driving data acquisition system and its acquisition method. Background Technology

[0002] In autonomous driving technology, perception is the most crucial component, essential for accurately identifying and understanding the surrounding environment, and has a significant demand for video data. Data acquisition equipment, as a key data loop medium in autonomous driving development, can be adapted to intelligent driving vehicles to collect full amounts of data and develop software algorithms for this data, thus meeting the perception component's need for video data.

[0003] Currently, devices that acquire video data directly collect processed video data. Because this processed video data lacks verification data and suffers significant loss of detail, feeding this data back into the domain controller for joint training and verification of perception algorithms with the underlying software module generates numerous errors, rendering the entire process unworkable and resulting in poor perception training outcomes. This is because the processed video data lacks verification data, meaning that the integrity and accuracy of the data cannot be effectively verified and guaranteed. In complex autonomous driving systems, any errors or missing data can lead to serious consequences, such as incorrect perception judgments and decisions. Furthermore, perception algorithms require rich and accurate information to learn and optimize; video data lacking detail cannot provide sufficient effective features for the algorithm, resulting in inaccurate and unrobust perception models.

[0004] Due to these issues, the current link cannot function properly and cannot meet the high requirements of autonomous driving for perception accuracy and reliability. Summary of the Invention

[0005] To overcome the problems existing in related technologies, this specification provides an autonomous driving data acquisition system and its acquisition method.

[0006] According to a first aspect of the embodiments of this specification, an autonomous driving data acquisition system is provided, the system comprising: a data acquisition source device, a data acquisition host, and a domain controller having a perception module;

[0007] The data acquisition source device is used to acquire raw image data of the vehicle;

[0008] The data acquisition host is electrically connected between the data acquisition source device and the domain controller. It is used to receive the raw image data and re-output the raw image data to the domain controller so that the domain controller can perform perception analysis based on the raw image data for vehicle driving.

[0009] According to the autonomous driving data acquisition system provided in this application, the data acquisition host uses a serial link of a bidirectional data channel to transmit data with the data acquisition source device and the domain controller respectively; so that the data acquisition host receives the raw image data sent by the data acquisition source device and the verification data sent by the domain controller.

[0010] According to the autonomous driving data acquisition system provided in this application, the data acquisition host performs data splitting processing on the original image data to obtain a first data packet that is re-output to the domain controller and a second data packet that is stored on disk in the data acquisition host. The second data packet is used to feed back into the domain controller for perception training.

[0011] According to the autonomous driving data acquisition system provided in this application, the data acquisition host is further used to strip the original image data after splitting through a preset data structure to obtain raw image data for perception training and embedded row data for vehicle software development and verification.

[0012] According to a second aspect of the embodiments of this specification, an autonomous driving data acquisition method is provided, the method comprising:

[0013] The raw image data of the vehicle is acquired through the data acquisition source device;

[0014] The data acquisition host receives the raw image data and re-outputs the raw image data to the domain controller.

[0015] The domain controller performs perception analysis based on the raw image data for vehicle operation.

[0016] According to the autonomous driving data acquisition method provided in this application, before the data acquisition host re-outputs the original image data to the domain controller, the method further includes:

[0017] The data acquisition host performs data splitting processing on the original image data to obtain a first data packet and a second data packet.

[0018] The first data packet is re-output to the domain controller;

[0019] The second data packet is written to disk and stored in the data acquisition host for use in the domain controller for perception training.

[0020] The data in the first data packet and the second data packet are identical.

[0021] According to the autonomous driving data acquisition method provided in this application, before the step of performing data splitting processing on the original image data through the data acquisition host to obtain a first data packet and a second data packet, the method further includes:

[0022] When the data acquisition source device performs serialization processing on the acquired raw image data, the data acquisition host performs deserialization processing on the raw image data.

[0023] The data acquisition host performs data splitting processing on the original image data to obtain a first data packet and a second data packet, including:

[0024] The data acquisition host performs data splitting processing on the deserialized original image data to obtain a first data packet and a second data packet.

[0025] According to the autonomous driving data acquisition method provided in this application, the step of re-outputting the first data packet to the domain controller includes:

[0026] The data acquisition host performs serialization processing on the first data packet and then re-outputs the processed first data packet to the domain controller.

[0027] According to the autonomous driving data acquisition method provided in this application, before acquiring the raw image data of the vehicle through the data acquisition source device, the method further includes:

[0028] The data link of the autonomous driving data acquisition system is verified.

[0029] According to the autonomous driving data acquisition method provided in this application, the verification of the data link of the autonomous driving data acquisition system includes:

[0030] After connecting to the data acquisition source device, the data acquisition host verifies the data stream status of a series of data transmitted by the data acquisition source device to obtain a first verification result;

[0031] The data acquisition host verifies the verification data sent by the domain controller to obtain a second verification result;

[0032] If both the first verification result and the second verification result pass, the step of acquiring the vehicle's original image data through the data acquisition source device is executed.

[0033] This application also provides an autonomous driving data acquisition device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the autonomous driving data acquisition method described above.

[0034] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the autonomous driving data acquisition method as described above.

[0035] The autonomous driving data acquisition system and its acquisition method in the embodiments of this specification are based on an autonomous driving data acquisition system including a data acquisition source device, a data acquisition host, and a domain controller with a perception module to realize autonomous driving data acquisition. In the autonomous driving data acquisition system, the data acquisition host is electrically connected between the data acquisition source device and the domain controller to receive the raw image data and re-output the raw image data to the domain controller, thereby realizing the acquisition of raw format data and meeting the high requirements of autonomous driving for perception accuracy and reliability.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0038] Figure 1 This is a schematic diagram of an autonomous driving data acquisition system illustrated in this specification according to an exemplary embodiment;

[0039] Figure 2 This is a schematic diagram of another autonomous driving data acquisition system illustrated in this specification according to an exemplary embodiment;

[0040] Figure 3 This is a schematic diagram illustrating data offloading processing according to an exemplary embodiment of this specification;

[0041] Figure 4 This is a flowchart illustrating an autonomous driving data acquisition method according to an exemplary embodiment of this specification;

[0042] Figure 5 This is a schematic diagram of an autonomous driving data acquisition device according to an exemplary embodiment of this specification;

[0043] Figure 6 This is a schematic block diagram of an autonomous driving data acquisition device illustrated in this specification according to an exemplary embodiment. Detailed Implementation

[0044] The technical solutions in the embodiments (or "implementations") of this application will be clearly and completely described herein with reference to the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements.

[0045] If the embodiments of this application contain terms relating to directional indications or positional relationships (such as up, down, left, right, front, back, inside, outside, top, bottom, center, vertical, horizontal, longitudinal, transverse, length, width, counterclockwise, clockwise, axial, radial, circumferential, etc.), such terms are only used to explain the relative positional relationships and movements between components in a specific posture (as shown in the attached figures); if the specific posture changes, the directional indications or positional relationships will also change accordingly. Furthermore, the terms "first" and "second" used in the embodiments of this application are only for descriptive convenience and should not be construed as indicating or implying relative importance.

[0046] This application provides an autonomous driving data acquisition system and method thereof. The following detailed description, in conjunction with the accompanying drawings, illustrates this application. Unless otherwise specified, the features described in the embodiments and implementations can be combined with each other.

[0047] Data acquisition devices are widely used in autonomous driving development, such as the Udacity data collector, Waymo data acquisition system, and comma.ai data collector. As a crucial data loop medium in autonomous driving development, these devices are compatible with intelligent driving vehicles for full-scale data collection and the development of software algorithms based on that data.

[0048] Perception, as the most crucial component of autonomous driving technology, has a significant demand for video data. Currently, the domain controller and camera are highly coupled, with the domain controller embedding processing algorithms. After acquiring video data from the camera, the data is processed directly. Therefore, the current data acquisition solution involves directly acquiring processed video data from the domain controller. However, when this data is fed back into the domain controller for joint training and validation of perception algorithms with the underlying software module, numerous errors occur. This is because the processed video data lacks validation data and suffers from significant loss of detail, rendering the entire process unworkable and resulting in poor perception training outcomes.

[0049] like Figure 1As shown, in the current data acquisition process, the data acquisition host directly collects data output from the domain controller. By configuring the `data_collect` module of the AUTOSAR AP in the domain controller (responsible for filtering and organizing the output data), data is sent out via the ZMQ framework (a high-efficiency message passing framework capable of rapidly transferring data between different components). On the data acquisition host side, the data is received based on the existing ZMQ framework, deserialized, and then stored on disk. This solution can only collect data output from the domain controller. For image / video data, it can only collect YUV image / video data processed by the domain controller's ISP (image signal processing). This compressed and processed data loses some image details and cannot be used for data re-feedback to simulate the real vehicle environment or for combining with underlying software to verify perception algorithms.

[0050] For example, if a subtle feature of an important traffic sign in a real-world vehicle environment is lost during compression, the perception algorithm may fail to correctly identify the traffic sign during the data refeeding simulation, leading to incorrect decisions and potential safety risks.

[0051] The aforementioned issues and the demands of autonomous driving have spurred the development of raw video data acquisition equipment.

[0052] To address the aforementioned technical issues, this specification provides a method for acquiring autonomous driving data.

[0053] By connecting a data acquisition host in series between the data acquisition source device and the domain controller, the raw image data transmitted by the data acquisition source device in GMSL is received and transmitted to the domain controller for analysis and processing. Since the raw image data contains verification data and the video data details are complete, when the data is fed back into the domain controller for perception algorithm training, the perception algorithm has high accuracy and robustness, thus meeting the high requirements of autonomous driving for perception accuracy and reliability.

[0054] like Figure 2 As shown, the autonomous driving data acquisition system described in this article includes: a data acquisition source device, a data acquisition host, and a domain controller with a perception module.

[0055] The data acquisition source device typically refers to the source capable of generating raw data, such as cameras, various sensors, etc., used to collect raw image data of the vehicle. The following explanation uses a camera as an example.

[0056] The data acquisition host focuses on receiving, processing, storing, and distributing data from different data acquisition source devices, and is used to receive raw image data from the data acquisition source devices.

[0057] The domain controller, as an important component of the vehicle's electronic system, is responsible for receiving and processing data from various vehicle subsystems.

[0058] In the aforementioned autonomous driving data acquisition system, the data acquisition host is electrically connected at a crucial location between the data acquisition source device and the domain controller, playing a role in series connection and important data processing. For the camera, the data acquisition host simulates the function of the domain controller to receive the raw image data from the camera. This means that when the camera transmits data, it sends data to the data acquisition host just as if it were sending data to a real domain controller.

[0059] For the domain controller, the data acquisition host simulates a camera to send data, performing data verification at the domain controller end to ensure the entire data transmission channel is open, thus guaranteeing the smooth and stable operation of the data transmission channel from the camera to the domain controller. Therefore, after receiving the data, the data acquisition host re-outputs the raw image data to the domain controller, enabling the domain controller to perform further analysis and decision-making based on its internal algorithms and processing modules, including perception analysis for vehicle navigation.

[0060] In this embodiment, the data acquisition host collects raw image / video data without any image processing, retaining as much image information as possible, providing greater space for image processing and application, and expanding resources for the development and verification of image processing algorithms.

[0061] In some embodiments, upon receiving data, the data acquisition host immediately initiates a data splitting mechanism. During the data splitting process, a portion of the original video data is acquired and stored on the device's hard drive. This stored data provides raw material for subsequent analysis, retrospection, and research. Simultaneously, another portion of the data is reorganized and output, continuing to be transmitted towards the intelligent driving domain as input data for the domain controller, supporting its subsequent processing and decision-making. As an example, the data acquisition host includes a data processing module that performs data splitting processing on the original image data, obtaining a first data packet re-output to the domain controller and a second data packet stored on the disk within the data acquisition host. The second data packet is used to feed back into the domain controller for perception training.

[0062] For example, once the camera captures real-time video data from the road, the data acquisition host acts as an intelligent "transfer station." On the one hand, it stores some data for future problem tracing and in-depth research; on the other hand, it promptly transmits key data to the intelligent driving domain controller. Simultaneously, it simulates the interaction between the camera and the domain controller to ensure the domain controller can correctly receive and verify the data. This ensures the smooth operation of the entire data transmission channel from the camera to the domain controller, providing strong support for the stable operation and continuous optimization of the autonomous driving system.

[0063] Furthermore, data verification on the domain controller side includes CRC verification.

[0064] In this embodiment, the data acquisition host can bypass the original image / video data, with one path used for data acquisition and retention, and the other path re-outputting to the domain controller as input to the intelligent driving domain. This bypass method helps ensure that data is not lost during the acquisition process, while also ensuring the operation of the intelligent driving domain controller.

[0065] In some embodiments, the data acquisition host further includes a communication module, which uses a bidirectional data channel serial link (such as a GMSL2 link) to transmit data with the data acquisition source device and the domain controller respectively, so that the data acquisition host can receive the raw image data sent by the data acquisition source device and the verification data sent by the domain controller. As an example, the data output from the camera is transmitted in the D-PHY via the CSI-2 protocol and output to the data acquisition host via GMSL2. The data acquisition host then transmits data to the domain controller via GMSL2.

[0066] In this embodiment, the same GMSL2 link also serves as a bidirectional control channel for sending and receiving data, receiving verification data returned by the domain controller. Verification ensures that the data received by the domain controller from the camera is reliable, accurate, and usable, thereby guaranteeing the stability and effectiveness of the entire data transmission channel from the camera to the domain controller.

[0067] In some embodiments, the data acquisition host further includes a data stripping module connected to the data processing module. This data stripping module is used to strip the split raw image data using a preset data structure, obtaining raw image data for training the perception algorithm and embedded row data containing real-time dynamic register information for software development and verification. As an example, after acquiring the raw image data, a data processing script combined with a data structure is used to strip the raw image data and embedded row data. The data processing script reads the acquired raw image data. This data typically has a specific data structure, containing raw image data and potentially embedded row data. Through analysis of the data structure, the script can identify the features and locations of the raw image data and embedded row data. Then, according to preset rules and algorithms, the script automatically performs the separation operation. After separation, the obtained raw image data and embedded row data can be further processed and applied.

[0068] For example, if the embedded row data contains metadata about the image, such as the shooting time and geographical location, it can be extracted for data management and analysis; while the separated raw image data can be used for further image processing operations such as image enhancement, compression, and recognition.

[0069] In other embodiments, the data acquisition host further includes a data stripping module connected to the data processing module. This data stripping module strips the raw image data before splitting using a preset data structure to obtain raw image data for perception training and embedded row data for vehicle underlying software development and verification. Subsequently, the raw image data for perception training is split, and the split data is transmitted to the domain controller for analysis and decision-making based on the highly relevant raw image data.

[0070] As an example, the following is an instance of building an autonomous driving data acquisition system based on the above structure:

[0071] First, taking the V4L2 architecture camera adapted in this manual as an example, the raw image data generated at the sensor end is transmitted at the D-PHY physical layer via the CSI-2 protocol. The camera-side serializer performs a serialization operation on this raw image data, converting it into a format suitable for transmission over the GMSL2 serial link, and outputs it on the GMSL2 serial link transceiver. At the data acquisition host end, mimicking a domain controller, the deserializer performs data deserialization and PHY-COPY, mirroring and bypassing the raw image / video data. The same video data is transmitted to two D-PHYs; one path completes data persistence on disk within the device, while the other path is re-output to the device-side serializer for serialization before being sent to the domain controller as input.

[0072] In this autonomous driving data acquisition system, the GMSL2 serial link has its specific transmission protocol and signal requirements. The data format generated by the camera may not conform to the direct transmission standard of this link. The serializer can convert and encode the raw data to adapt it to the electrical characteristics and communication protocol of the GMSL2 link, thereby ensuring that the data can be transmitted accurately and stably on the link.

[0073] It should be noted that this same GMSL2 link is not only used to transmit raw image data, but also serves as a bidirectional control channel for sending and receiving. It receives verification data returned from the domain controller to ensure the accuracy and integrity of data transmission.

[0074] Next, continuing with the example of a V4L2 architecture camera, camera adaptation is still required on the domain controller to ensure compatibility and proper functioning. The NVIDIA Orin chip and DriveOS provide a crucial camera framework. Within this framework, the nvsipl framework on Linux and nvmedia work together, with nvmedia responsible for acquiring camera data. nvsipl not only collaborates with nvmedia but also interacts by calling the kernel layer, enabling communication and data transmission between different layers.

[0075] For the camera to function properly and output images, the correct NITO (Image Quality Object File) needs to be flashed into the domain controller. This file contains the camera module's ISP settings and related characterization parameters, including automatic exposure and white balance configurations. Automatic exposure parameters determine how the camera captures and adjusts light under different lighting conditions to ensure images are neither overexposed nor underexposed. White balance parameters correct color deviations in the image, ensuring that white objects appear true white under different light sources, thus guaranteeing the accuracy and naturalness of the overall image colors. For example, improper automatic exposure settings may result in overexposed white areas and loss of detail in images taken in bright light; inaccurate white balance may cause images taken under indoor lighting to appear yellowish or bluish. Correctly configuring these parameters enables the camera to output high-quality images that meet practical needs, providing a solid foundation for subsequent image processing and applications.

[0076] Finally, after completing the equipment debugging, connect the camera and start the camera_serive module in the SoC (System-on-a-Chip) (this module monitors and manages camera-related services) to verify the data stream status. By verifying the data stream status, key information about data transmission can be obtained, such as data continuity, integrity, and rate, thus determining the camera's working status, such as whether it is working properly. If the data stream status is stable and meets expectations, it usually indicates that the camera is working well; otherwise, there may be a problem.

[0077] On the domain controller, an instance of CNvSIPLCamera is created and configured using the nvsipl module to complete camera initialization, preparing for subsequent data acquisition and processing. Then, NvMedia is called to capture the output YUV image, frame rate, and other data, and the quality and stability of the output image are simply verified in memory, such as checking image clarity, absence of distortion, color accuracy, and frame rate stability. This indirectly infers whether the entire data acquisition process from the camera, through transmission and processing, to the final output, is correct and reliable, thus verifying the correctness of the entire process.

[0078] When the autonomous driving data acquisition link in the autonomous driving data acquisition system is functioning normally, the system can be used to acquire and process raw image / video data, thereby expanding the resources for image processing algorithm development and verification.

[0079] Based on the embodiments of the autonomous driving data acquisition system provided above, this specification proposes an autonomous driving data acquisition method.

[0080] Figure 4 This is a flowchart illustrating an autonomous driving data acquisition method provided in an embodiment of this specification, including the following steps:

[0081] S100. Collect raw image / video data of the vehicle through the data acquisition source device.

[0082] The raw image / video data of the vehicle is acquired by the data acquisition device, and this raw image / video data will be transmitted to the data acquisition host for processing via GMS.

[0083] In some embodiments, prior to step S100, which involves acquiring raw image data of the vehicle via the data acquisition source device, the method further includes:

[0084] S110, verify the data link of the autonomous driving data acquisition system.

[0085] Only by ensuring that the entire data transmission channel is open and verifying the correctness of the entire link can the collection of raw format data for autonomous driving be achieved.

[0086] As an example, S110, which verifies the data link of the autonomous driving data acquisition system, includes:

[0087] After connecting to the data acquisition source device, the data acquisition host verifies the data stream status of a series of data transmitted by the data acquisition source device to obtain the first verification result. Taking the V4L2 architecture camera as an example, after completing the device debugging, the camera is connected. By starting the camera_serive module in the SoC and verifying the data stream status, the working status of the camera can be determined, and the first verification result can be obtained.

[0088] The data acquisition host verifies the verification data sent by the domain controller to obtain a second verification result; for example, on the domain controller, an instance of CNvSIPLCamera is created and configured through the nvsipl module to complete camera initialization, and NvMedia is called to capture the output YUV image, frame rate and other data, and the quality and stability of the output image are simply verified in memory to obtain a second verification result.

[0089] If both the first verification result and the second verification result pass, the step of acquiring the vehicle's original image data through the data acquisition source device is executed.

[0090] S200, the original image data is received by the data acquisition host and then re-outputted to the domain controller.

[0091] When the raw image data arrives at the data acquisition host, it will mimic the function of the domain controller and re-output the raw image data to the domain controller for further processing and decision-making.

[0092] In some embodiments, before the data acquisition host re-outputs the raw image data to the domain controller in S200, the method further includes:

[0093] When the data acquisition source device performs serialization processing on the acquired raw image data, the data acquisition host performs deserialization processing on the raw image data.

[0094] This means that when the raw image data arrives at the data acquisition host, it mimics the function of a domain controller. A deserializer deserializes the serialized raw image data, restoring it to its original format. The raw image data is then re-output to the domain controller for further processing and decision-making.

[0095] The data conversion logic and method of the deserializer on the data acquisition host side and the serializer on the camera side are consistent.

[0096] In this embodiment, in the data transmission link, the serializer at the transmitting end serializes the data for efficient transmission over the transmission medium. At the receiving end, the deserializer restores the serialized data to its original parallel format for subsequent processing and use. The configuration of the deserializer and serializer ensures that the data remains accurate upon arrival at the receiving end, guaranteeing accurate and stable data transmission over the link.

[0097] In the data acquisition host, after deserializing the raw image data, PHY-COPY (physical layer copy) is performed to mirror and bypass the original image / video data. This means that the same video data is copied twice. Figure 3 As shown, the same video data is transmitted to two D-PHYs. One of them completes the data writing and storage on disk within the device, while the other outputs it back to the device-side serializer, adds a serial number, and sends it to the domain controller as input.

[0098] In some embodiments, before the data acquisition host re-outputs the raw image data to the domain controller, the method further includes:

[0099] S210, the data acquisition host performs data splitting processing on the original image data to obtain a first data packet and a second data packet. The data in the first data packet and the second data packet are identical.

[0100] In other examples, the data acquisition host performs data splitting processing on the deserialized original image data to obtain a first data packet and a second data packet.

[0101] S220, the first data packet is re-output to the domain controller for analysis and decision-making.

[0102] In the process of re-outputting the first data packet to the domain controller, in order to ensure the stability and accuracy of data transmission, the first data packet is serialized by the serializer on the data acquisition host, and the processed first data packet is re-output to the domain controller.

[0103] S230, the second data packet is written to disk and stored in the data acquisition host for use in the domain controller for perception training.

[0104] This diversion method helps ensure that the original image data is not lost during the acquisition process, while also ensuring the operation of the intelligent driving domain controller.

[0105] S300, the domain controller performs perception analysis based on the original image data for vehicle driving.

[0106] Once the domain controller receives the raw image data, it can extract valuable information from the raw image data, understand the current scene situation, and make accurate decisions and controls to meet the needs of specific applications, such as safe driving of autonomous driving and anomaly detection of intelligent monitoring.

[0107] This application provides an autonomous driving data acquisition system and method. The autonomous driving data acquisition system is based on a data acquisition source device, a data acquisition host, and a domain controller with a perception module. In the autonomous driving data acquisition system, the data acquisition host is electrically connected between the data acquisition source device and the domain controller. It is used to receive the raw image data and re-output the raw image data to the domain controller, thereby realizing the acquisition of raw format data and meeting the high requirements of autonomous driving for perception accuracy and reliability.

[0108] Based on the same concept as the methods described above, this application also proposes an autonomous driving data acquisition device, such as... Figure 5 As shown.

[0109] The device includes:

[0110] The data acquisition module 602 is used to acquire raw image data of the vehicle through the data acquisition source device;

[0111] Data processing module 604 is used to receive the raw image data through the data acquisition host and re-output the raw image data to the domain controller;

[0112] The data analysis module 606 is used to perform perception analysis based on the original image data through the domain controller for vehicle driving.

[0113] The specific implementation process of the functions and roles of each module / submodule / unit in the above device can be found in the implementation process of the corresponding steps in the above method, which can achieve the same technical effect, and will not be repeated here.

[0114] Figure 6 An example is a schematic diagram of the physical structure of an autonomous driving data acquisition device, such as... Figure 6 As shown, the autonomous driving data acquisition device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions stored in the memory 830 to execute the autonomous driving data acquisition method.

[0115] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the autonomous driving data acquisition method provided by the above methods.

[0117] In another aspect, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the autonomous driving data acquisition methods provided by the above methods.

[0118] It should be noted that the technical solutions or features described in the above embodiments can be combined or supplemented with each other without conflict. The scope of protection of this application is not limited to the precise structures described in the above embodiments and shown in the accompanying drawings; all modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An autonomous driving data acquisition system, characterized in that, The system includes: a data acquisition source device, a data acquisition host, and a domain controller with a sensing module; The data acquisition source device is used to acquire raw image data of the vehicle; The data acquisition host is electrically connected between the data acquisition source device and the domain controller. It receives the raw image data and re-outputs the raw image data to the domain controller, enabling the domain controller to perform perception analysis based on the raw image data for vehicle driving purposes. The data acquisition source device is configured to: after being connected, verify the data stream status of a series of data transmitted by the data acquisition source device through the data acquisition host to obtain a first verification result; verify the verification data sent by the domain controller through the data acquisition host to obtain a second verification result; and, if both the first and second verification results pass, acquire the raw image data of the vehicle.

2. The autonomous driving data acquisition system as described in claim 1, characterized in that, The data acquisition host uses a bidirectional data channel serial link to transmit data with the data acquisition source device and the domain controller respectively, so that the data acquisition host can receive the raw image data sent by the data acquisition source device and the verification data sent by the domain controller.

3. The autonomous driving data acquisition system as described in claim 1, characterized in that, The data acquisition host is used to perform data splitting processing on the original image data to obtain a first data packet that is re-output to the domain controller and a second data packet that is stored on disk in the data acquisition host. The second data packet is used to feed back to the domain controller for perception training.

4. The autonomous driving data acquisition system as described in claim 2, characterized in that, The data acquisition host is also used to strip the original image data after splitting through a preset data structure to obtain raw image data for perception training and embedded row data for vehicle underlying software development and verification.

5. A method for collecting autonomous driving data, characterized in that, The autonomous driving data acquisition method is applied to the autonomous driving data acquisition system according to any one of claims 1-4, and the method includes: The raw image data of the vehicle is acquired through the data acquisition source device; The data acquisition host receives the raw image data and re-outputs the raw image data to the domain controller. The domain controller performs perception analysis based on the raw image data for vehicle driving purposes. Before acquiring the vehicle's raw image data through the data acquisition source device, the method further includes: verifying the data link of the autonomous driving data acquisition system; The verification of the data link of the autonomous driving data acquisition system includes: After accessing the data acquisition source device, the data acquisition host verifies the data stream status of a series of data transmitted by the data acquisition source device to obtain a first verification result; the data acquisition host verifies the verification data sent by the domain controller to obtain a second verification result; if both the first verification result and the second verification result pass, the step of acquiring the vehicle's original image data through the data acquisition source device is executed.

6. The autonomous driving data acquisition method as described in claim 5, characterized in that, Before the original image data is re-output to the domain controller via the data acquisition host, the method further includes: The data acquisition host performs data splitting processing on the original image data to obtain a first data packet and a second data packet. The first data packet is re-output to the domain controller; The second data packet is written to disk and stored in the data acquisition host for use in the domain controller for perception training. The data in the first data packet and the second data packet are identical.

7. The autonomous driving data acquisition method as described in claim 6, characterized in that, Before the data acquisition host performs data splitting processing on the original image data to obtain the first data packet and the second data packet, the method further includes: When the data acquisition source device performs serialization processing on the acquired raw image data, the data acquisition host performs deserialization processing on the raw image data. The data acquisition host performs data splitting processing on the original image data to obtain a first data packet and a second data packet, including: The data acquisition host performs data splitting processing on the deserialized original image data to obtain a first data packet and a second data packet.

8. The autonomous driving data acquisition method as described in claim 7, characterized in that, The step of re-outputting the first data packet to the domain controller includes: The data acquisition host performs serialization processing on the first data packet and then re-outputs the processed first data packet to the domain controller.

Images