Data acquisition method, device, apparatus and storage medium

Abstract

The application discloses a data acquisition method and device, equipment and a storage medium. The method comprises the following steps: each target vehicle identifies an identification area around the vehicle, acquires real-time obstacle information of the identification area, and sends the real-time obstacle information to a server; the server receives the real-time obstacle information sent by each target vehicle, fuses the real-time obstacle information sent by each target vehicle, and obtains fused obstacle information; the server updates historical obstacle information based on the fused obstacle information, and obtains target obstacle information; the server obtains sub-target obstacle information matched with each target vehicle based on the target obstacle information; and the server sends the sub-target obstacle information matched with each target vehicle to the corresponding target vehicle respectively. According to the embodiment of the application, the obstacle is detected based on multiple vehicles, the accuracy of obstacle detection is improved, and the safety of automatic driving is improved.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to a data acquisition method, apparatus, device and storage medium. Background Technology

[0002] Currently, when autonomous vehicles detect obstacles, they rely solely on their own detection system to detect obstacles around the vehicle and then determine subsequent driving strategies based on the detection results. However, due to the existence of blind spots in single-vehicle detection, obstacles can only be identified in a portion of the identifiable area, while obstacles in the blind spots cannot be detected, thus increasing the risks of autonomous driving. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art. Therefore, one objective of this application is to provide a data acquisition method, apparatus, device, and storage medium.

[0004] To address the aforementioned technical problems, embodiments of this application provide the following technical solutions:

[0005] A data acquisition method, comprising:

[0006] Each target vehicle identifies the recognition area around its own vehicle, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server;

[0007] The server receives the real-time obstacle information sent by each of the target vehicles, and merges the real-time obstacle information sent by each of the target vehicles to obtain merged obstacle information;

[0008] The server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information;

[0009] Based on the target obstacle information, the server obtains sub-target obstacle information that matches each target vehicle;

[0010] The server will send the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle.

[0011] Optionally, each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server, including:

[0012] Each target vehicle identifies the identification area and obtains various identification data;

[0013] Each target vehicle fuses multiple types of identification data to obtain fused data;

[0014] Each target vehicle performs a first coordinate transformation on the fused data to obtain the real-time obstacle information and sends the real-time obstacle information to the server.

[0015] Optionally, the method further includes: each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server;

[0016] Each target vehicle identifies the identification area and obtains various identification data;

[0017] Each target vehicle fuses multiple types of recognition data to obtain real-time obstacle information, and sends the real-time obstacle information to the server.

[0018] The server performs a second coordinate transformation on the real-time obstacle information to obtain the target obstacle information.

[0019] Optionally, the server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information, including:

[0020] The server obtains an updated obstacle list based on the fused obstacle information;

[0021] The server obtains a list of historical obstacles based on the historical obstacle information;

[0022] The server compares the updated obstacle list with the historical obstacle list to obtain the comparison result;

[0023] If the comparison results include common obstacles, the server obtains the updated status information of the common obstacles based on the fused obstacle information.

[0024] The server obtains the historical status information of the shared obstacle information based on the historical obstacle information;

[0025] The server updates the historical status information of the shared obstacles based on the updated status information of the shared obstacles, thereby obtaining the target obstacle information.

[0026] Optionally, after the server compares the updated obstacle list and the historical obstacle list to obtain the comparison result, the method further includes:

[0027] If a non-shared obstacle is found in the comparison results, the location of the non-shared obstacle is determined.

[0028] If the location of the non-shared obstacle is in the historical obstacle list, then the server obtains the historical status information of the non-shared obstacle based on the historical obstacle information;

[0029] The server obtains the predicted state information of the non-shared obstacle based on the historical state information, and updates the historical state information of the non-shared obstacle based on the predicted state information of the non-shared obstacle to obtain the target obstacle information.

[0030] Optionally, after determining the location of the non-shared obstacle if it exists in the comparison result, the method further includes:

[0031] If the location of the non-shared obstacle is in the updated obstacle list, the server obtains the updated status information of the non-shared obstacle based on the fused obstacle information;

[0032] The server adds the non-shared obstacles to the historical obstacle list to obtain the target obstacle list, and adds the updated status information of the non-shared obstacles to the historical obstacle information to obtain the target obstacle information.

[0033] Optionally, the server obtains sub-target obstacle information matching each target vehicle based on the target obstacle information, including:

[0034] Based on the target obstacle information, the server obtains the first real-time position of each target obstacle in the target obstacle list and the second real-time position of each target vehicle;

[0035] The server obtains relative parameters between each target obstacle and each target vehicle based on the first real-time position of each target obstacle and the second real-time position of each target vehicle; wherein the relative parameters include relative distance and relative time.

[0036] The server compares the relative parameter with the parameter threshold. If the relative parameter is less than the parameter threshold, it generates the sub-target obstacle information of the target vehicle that matches the relative parameter based on the target obstacle that matches the relative parameter.

[0037] Embodiments of this application also provide a data acquisition device, including:

[0038] The recognition module is used for each target vehicle to recognize the recognition area around its own vehicle, obtain real-time obstacle information of the recognition area, and send the real-time obstacle information to the server.

[0039] The fusion module is used by the server to receive the real-time obstacle information sent by each of the target vehicles, and to fuse the real-time obstacle information sent by each of the target vehicles to obtain fused obstacle information.

[0040] The update module is used by the server to update the historical obstacle information based on the fused obstacle information to obtain the target obstacle information;

[0041] The acquisition module is used by the server to obtain sub-target obstacle information matching each target vehicle based on the target obstacle information;

[0042] The sending module is used by the server to send the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle.

[0043] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.

[0044] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.

[0045] The embodiments of this application have the following technical effects:

[0046] The above-mentioned technical solution of this application 1) identifies the recognition area around the vehicle based on multiple target vehicles, uploads the identified real-time obstacle information to the cloud, and fuses the real-time obstacle information of multiple target vehicles based on the cloud to obtain fused obstacle information; the server can directly obtain the current state information of the obstacle based on the fused obstacle information, or the server can predict the current state information of the obstacle based on the fused obstacle information and historical obstacle information, saving the computing power of a single vehicle, providing more accurate obstacle information for each target vehicle, and also solving the blind spot problem of a single vehicle.

[0047] 2) After obtaining the sub-target obstacle information that matches each target vehicle, the server sends the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle, instead of sending the target obstacle information to each target vehicle. This is to save the transmission resources required for data transmission, improve the data transmission rate and efficiency, and further improve the safety of autonomous driving and user satisfaction.

[0048] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating a data acquisition method provided in an embodiment of this application;

[0050] Figure 2 This is a schematic diagram of the structure of a data acquisition device provided in an embodiment of this application. Detailed Implementation

[0051] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0052] To facilitate understanding of the embodiments by those skilled in the art, some terms are explained below:

[0053] (1) GPS: Global Positioning System.

[0054] (2)rtk: Real Time Kinematic) Real-time dynamic measurement technology.

[0055] like Figure 1 As shown, an embodiment of this application provides a data acquisition method, including:

[0056] Step S11: Each target vehicle identifies the recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server;

[0057] In one optional embodiment of this application, each target vehicle is equipped with a radar and multiple sensors. Each target vehicle's radar is equipped with a first sub-identification area, and the radar identifies the first sub-identification area. Each sensor is equipped with a second sub-identification area, and each sensor is assigned to identify the matched second sub-identification area.

[0058] Furthermore, based on the first sub-identification region and multiple second sub-identification regions of each target vehicle, the identification region corresponding to each target vehicle is obtained respectively; wherein, during the driving process of each target vehicle, the identification region corresponding to each target vehicle also undergoes corresponding dynamic changes as the target vehicle moves.

[0059] Furthermore, each target vehicle communicates with the server via a network; the server can be implemented in the cloud; the cloud interacts with each communicating target vehicle in real time via the network.

[0060] In an optional embodiment of this application, each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server, including:

[0061] Each target vehicle identifies the identification area and obtains various identification data;

[0062] Each target vehicle fuses multiple types of identification data to obtain fused data;

[0063] Each target vehicle performs a first coordinate transformation on the fused data to obtain the real-time obstacle information and sends the real-time obstacle information to the server.

[0064] In one optional embodiment of this application, each target vehicle identifies the surrounding identification area based on radar to obtain radar identification data; each target vehicle identifies the surrounding identification area based on multiple sensors to obtain sensor identification data; wherein, the types of sensor identification data obtained by different types of sensors are also different.

[0065] In an optional embodiment of this application, after obtaining radar identification data and sensor identification data, the radar identification data and sensor identification data are fused. Specifically, the obstacles included in the radar identification data are analyzed to obtain a first analysis result; simultaneously, the obstacles included in the sensor identification data are analyzed to obtain a second analysis result; the first analysis result and the second analysis result are compared, and obstacles that appear in both the first analysis result and the second analysis result are identified as valid obstacles and stored; obstacles that appear only in the first analysis result or only in the second analysis result are identified as invalid obstacles and are not stored, in order to eliminate false positives and noise.

[0066] In an optional embodiment of this application, after each target vehicle identifies a valid obstacle, since the coordinate system corresponding to the current valid obstacle is the vehicle's coordinate system, the vehicle needs to transform the valid obstacle from the vehicle's coordinate system to the global coordinate system (i.e., the first coordinate transformation) and obtain real-time obstacle information to achieve the fusion of real-time obstacle information of multiple vehicles.

[0067] The global coordinate system can be GPS or RTK, etc.

[0068] In an optional embodiment of this application, each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server, further comprising:

[0069] Each target vehicle identifies the identification area and obtains various identification data;

[0070] Each target vehicle fuses multiple types of recognition data to obtain real-time obstacle information, and sends the real-time obstacle information to the server.

[0071] The server performs a second coordinate transformation on the real-time obstacle information to obtain the target obstacle information.

[0072] In one optional embodiment of this application, after each target vehicle identifies a valid obstacle, it generates real-time obstacle information to be uploaded based on the valid obstacle, and uploads the real-time obstacle information to the cloud via the network.

[0073] However, since the coordinate system corresponding to the current valid obstacles is the coordinate system of the corresponding target vehicle, the cloud needs to transform the valid obstacles from the coordinate system of the corresponding target vehicle to the global coordinate system (i.e., the second coordinate transformation) and obtain real-time obstacle information.

[0074] In an optional embodiment of this application, for any target vehicle and the cloud connected to the target vehicle, the computing power requirements and the computing power that the target vehicle and the cloud can provide can be considered to select whether to perform a first coordinate transformation based on the target vehicle or to perform a second coordinate transformation on the real-time obstacle information after the target vehicle uploads the real-time obstacle information to the cloud, thereby improving the data transmission rate and efficiency.

[0075] Step S12: The server receives the real-time obstacle information sent by each of the target vehicles, and fuses the real-time obstacle information sent by each of the target vehicles to obtain fused obstacle information;

[0076] In one optional embodiment of this application, the cloud receives real-time obstacle information sent by multiple target vehicles connected to the cloud via a network.

[0077] After receiving real-time obstacle information uploaded by multiple target vehicles, the cloud platform merges the real-time obstacle information uploaded by multiple target vehicles.

[0078] Specifically, before fusing multiple real-time obstacle information, the cloud first obtains parameters such as obstacle type, location, size, color, orientation, and speed contained in each real-time obstacle information.

[0079] Based on multiple parameters of each obstacle contained in each real-time obstacle information, a weighted calculation is performed to obtain the loss function corresponding to each obstacle. Then, based on the Hungarian matching algorithm, each obstacle in each real-time obstacle information is matched to determine which obstacles are the same obstacle identified by different target vehicles.

[0080] Before performing the weighted calculation, the weight corresponding to each parameter can be preset. The preset weight can also be adjusted in real time according to actual needs. The embodiments of this application do not impose specific limitations on this.

[0081] It should be noted that the Hungarian algorithm can be obtained based on related algorithms and is not within the scope of protection of this application, so it will not be elaborated further.

[0082] Step S13: The server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information;

[0083] In an optional embodiment of this application, the server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information, including:

[0084] The server obtains an updated obstacle list based on the fused obstacle information;

[0085] The server obtains a list of historical obstacles based on the historical obstacle information;

[0086] The server compares the updated obstacle list with the historical obstacle list to obtain the comparison result;

[0087] If the comparison results include common obstacles, the server obtains the updated status information of the common obstacles based on the fused obstacle information.

[0088] The server obtains the historical status information of the shared obstacle information based on the historical obstacle information;

[0089] The server updates the historical status information of the shared obstacles based on the updated status information of the shared obstacles, thereby obtaining the target obstacle information.

[0090] In one optional embodiment of this application, the content of updating the obstacle list and the historical obstacle list generally depends on the type of obstacle of interest in the application scenario. For example, in the current application scenario, the type of obstacle of interest may include other target vehicles, pedestrians, cyclists, and roadblocks around the target vehicle.

[0091] It should be noted that the types of obstacles included in the updated obstacle list and the historical obstacle list can be added or removed as needed to improve the safety of autonomous driving and enhance user satisfaction.

[0092] In an optional embodiment of this application, for common obstacles that appear simultaneously in the updated obstacle list and the historical obstacle list, the updated status information of each common obstacle is obtained based on the fused obstacle information, and the historical status information of the corresponding common obstacle is updated.

[0093] Specifically, based on the updated status information of each shared obstacle, the historical status information of the corresponding shared obstacle is updated. This can include updating the driving speed, driving trajectory, and driving direction in the updated status information of each shared obstacle, and updating the historical driving speed, historical driving trajectory, and historical driving direction in the historical status information of the corresponding shared obstacle, thereby obtaining the target obstacle information.

[0094] In an optional embodiment of this application, after the server compares the updated obstacle list and the historical obstacle list to obtain the comparison result, the method further includes:

[0095] If a non-shared obstacle is found in the comparison results, the location of the non-shared obstacle is determined.

[0096] If the location of the non-shared obstacle is in the historical obstacle list, then the server obtains the historical status information of the non-shared obstacle based on the historical obstacle information;

[0097] The server obtains the predicted state information of the non-shared obstacle based on the historical state information, and updates the historical state information of the non-shared obstacle based on the predicted state information of the non-shared obstacle to obtain the target obstacle information.

[0098] In an optional embodiment of this application, for non-shared obstacles that only exist in historical obstacle information, the disappearance duration of the non-shared obstacle is first determined, and the disappearance duration is compared with a disappearance duration threshold. If the disappearance duration is less than the disappearance duration threshold, the predicted state information of the corresponding non-shared obstacle in the disappearance duration is predicted based on the historical driving trajectory, historical driving speed, and historical driving direction of the non-shared obstacle in the historical state information. The predicted state information includes the predicted driving trajectory, predicted driving speed, predicted driving direction, and predicted driving position.

[0099] Based on the predicted driving trajectory, predicted driving speed, predicted driving direction, and predicted driving position, the cloud predicts the current status information of the shared obstacle, such as the current driving position, current driving speed, and current driving direction. The cloud then updates the predicted current driving position, current driving speed, and current driving direction to the historical obstacle list and obtains the target obstacle list.

[0100] In one optional embodiment of this application, it is assumed that a target vehicle A passes by a target vehicle B at a first moment, is identified by the target vehicle B, and is then uploaded to the cloud.

[0101] Assuming that only target vehicle B recognizes target vehicle A between the first and second moments, and target vehicle A enters the blind spot at the third moment and is not recognized by any other target vehicle, then the driving state of target vehicle A at the third moment can be obtained by using the historical obstacle information of target vehicle B to obtain the historical state information of target vehicle A, including the historical driving trajectory, historical driving speed, and historical driving direction of target vehicle A. Based on the historical driving trajectory, historical driving speed, and historical driving direction of target vehicle A, the state of target vehicle A at the third moment can be predicted to obtain the predicted state information, including the predicted driving position, predicted driving speed, and predicted driving direction of target vehicle A at the third moment.

[0102] In the embodiments of this application, if at least one target vehicle has identified an obstacle in the historical obstacle information, the current state information of the obstacle can be predicted based on the historical obstacle information of the target vehicle.

[0103] In an optional embodiment of this application, it is assumed that at the fourth moment, target vehicle A enters the recognition range of target vehicle C, and target vehicle C does indeed recognize a vehicle in the recognition area around itself at the fourth moment. The vehicle recognized by target vehicle C at the fourth moment is matched with target vehicle A based on the Hungarian algorithm. If the match is successful, the state information of target vehicle A is updated based on the historical state information of target vehicle A and the current state information of target vehicle A recognized by target vehicle C, thereby updating the historical obstacle list and obtaining the target obstacle list.

[0104] In an optional embodiment of this application, when a non-shared obstacle exists only in the historical obstacle list and the disappearance duration of the non-shared obstacle is greater than the disappearance duration threshold, it is determined that the non-shared obstacle has disappeared or is out of sight. Therefore, the non-shared obstacle is deleted from the historical obstacle list, thereby updating the historical obstacle list and obtaining the target obstacle list.

[0105] In one optional embodiment of this application, the disappearance duration threshold can be set to 3 seconds. In practical application scenarios, the disappearance duration threshold can be adjusted according to actual needs.

[0106] In an optional embodiment of this application, after determining the location of the non-common obstacle if it exists in the comparison result, the method further includes:

[0107] If the location of the non-shared obstacle is in the updated obstacle list, the server obtains the updated status information of the non-shared obstacle based on the fused obstacle information;

[0108] The server adds the non-shared obstacles to the historical obstacle list to obtain the target obstacle list, and adds the updated status information of the non-shared obstacles to the historical obstacle information to obtain the target obstacle information.

[0109] In an optional embodiment of this application, if a non-shared obstacle exists only in the updated obstacle list, it indicates that the non-shared obstacle is a newly appeared obstacle that has not been identified before. Then, based on the fused obstacle information, the updated status information of the non-shared obstacle is obtained, including the updated driving position, updated driving speed, and updated driving direction, etc., and the non-shared obstacle is added to the historical obstacle list, thereby realizing the update of the historical obstacle list and obtaining the target obstacle list.

[0110] In the embodiments of this application, multiple target vehicles identify the recognition area around the vehicle and upload the identified real-time obstacle information to the cloud. The real-time obstacle information of multiple target vehicles is then fused based on the cloud to obtain fused obstacle information. The server can directly obtain the current state information of the obstacles based on the fused obstacle information, or the server can predict the current state information of the obstacles based on the fused obstacle information and historical obstacle information. This saves computing power per vehicle, provides more accurate obstacle information for each target vehicle, and solves the blind spot problem that exists in a single vehicle.

[0111] Step S14: The server obtains sub-target obstacle information matching each target vehicle based on the target obstacle information;

[0112] In an optional embodiment of this application, the server obtains sub-target obstacle information matching each target vehicle based on the target obstacle information, including:

[0113] Based on the target obstacle information, the server obtains the first real-time position of each target obstacle in the target obstacle list and the second real-time position of each target vehicle;

[0114] The server obtains relative parameters between each target obstacle and each target vehicle based on the first real-time position of each target obstacle and the second real-time position of each target vehicle; wherein the relative parameters include relative distance and relative time.

[0115] The server compares the relative parameter with the parameter threshold. If the relative parameter is less than the parameter threshold, it generates the sub-target obstacle information of the target vehicle that matches the relative parameter based on the target obstacle that matches the relative parameter.

[0116] In an optional embodiment of this application, since the target obstacle information obtained by the cloud includes the first real-time position of each obstacle, the cloud can also obtain the second real-time position of each target vehicle currently interacting with the cloud.

[0117] The second real-time position of each target vehicle is matched with the first real-time position of each obstacle in the target obstacle information, and the relative distance between each target vehicle and any obstacle or the relative time of their encounter is obtained.

[0118] The relative parameters include relative distance or relative time; the parameter thresholds include relative distance thresholds or relative time thresholds.

[0119] Furthermore, the relative distance is compared with a relative distance threshold. If the relative distance is less than the relative distance threshold, the obstacle that matches the relative distance is identified as the target obstacle, and sub-target obstacle information is generated based on the target obstacle.

[0120] Similarly, multiple target obstacles matching each target vehicle are found, and based on all the multiple target obstacles matching each target vehicle, sub-target obstacle information matching each target vehicle is generated; or

[0121] The relative time is compared with the relative time threshold. If the relative time is less than the relative time threshold, the obstacle that matches the relative time is identified as the target obstacle, and sub-target obstacle information is generated based on the target obstacle.

[0122] By analogy, multiple target obstacles that match each target vehicle are found, and based on all the multiple target obstacles that match each target vehicle, sub-target obstacle information that matches each target vehicle is generated.

[0123] Step S15: The server sends the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle.

[0124] In an optional embodiment of this application, after obtaining the sub-target obstacle information matching each target vehicle, the server sends the sub-target obstacle information matching each target vehicle to the corresponding target vehicle, instead of sending the target obstacle information to each target vehicle. This is to save the transmission resources required for data transmission, improve the data transmission rate and efficiency, and further improve the safety of autonomous driving and user satisfaction.

[0125] like Figure 2 As shown, embodiments of this application also provide a data acquisition device 20, including:

[0126] The identification module 21 is used for each target vehicle to identify the identification area around its own vehicle, obtain real-time obstacle information of the identification area, and send the real-time obstacle information to the server.

[0127] The fusion module 22 is used for the server to receive the real-time obstacle information sent by each of the target vehicles, and to fuse the real-time obstacle information sent by each of the target vehicles to obtain fused obstacle information;

[0128] Update module 23 is used by the server to update the historical obstacle information based on the fused obstacle information to obtain the target obstacle information;

[0129] The acquisition module 24 is used by the server to obtain sub-target obstacle information matching each target vehicle based on the target obstacle information;

[0130] The sending module 25 is used by the server to send the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle.

[0131] Optionally, each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server, including:

[0132] Each target vehicle identifies the identification area and obtains various identification data;

[0133] Each target vehicle fuses multiple types of identification data to obtain fused data;

[0134] Each target vehicle performs a first coordinate transformation on the fused data to obtain the real-time obstacle information and sends the real-time obstacle information to the server.

[0135] Optionally, the method further includes: each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server;

[0136] Each target vehicle identifies the identification area and obtains various identification data;

[0137] Each target vehicle fuses multiple types of recognition data to obtain real-time obstacle information, and sends the real-time obstacle information to the server.

[0138] The server performs a second coordinate transformation on the real-time obstacle information to obtain the target obstacle information.

[0139] Optionally, the server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information, including:

[0140] The server obtains an updated obstacle list based on the fused obstacle information;

[0141] The server obtains a list of historical obstacles based on the historical obstacle information;

[0142] The server compares the updated obstacle list with the historical obstacle list to obtain the comparison result;

[0143] If the comparison results include common obstacles, the server obtains the updated status information of the common obstacles based on the fused obstacle information.

[0144] The server obtains the historical status information of the shared obstacle information based on the historical obstacle information;

[0145] The server updates the historical status information of the shared obstacles based on the updated status information of the shared obstacles, thereby obtaining the target obstacle information.

[0146] Optionally, after the server compares the updated obstacle list and the historical obstacle list to obtain the comparison result, the method further includes:

[0147] If a non-shared obstacle is found in the comparison results, the location of the non-shared obstacle is determined.

[0148] If the location of the non-shared obstacle is in the historical obstacle list, then the server obtains the historical status information of the non-shared obstacle based on the historical obstacle information;

[0149] The server obtains the predicted state information of the non-shared obstacle based on the historical state information, and updates the historical state information of the non-shared obstacle based on the predicted state information of the non-shared obstacle to obtain the target obstacle information.

[0150] Optionally, after determining the location of the non-shared obstacle if it exists in the comparison result, the method further includes:

[0151] If the location of the non-shared obstacle is in the updated obstacle list, the server obtains the updated status information of the non-shared obstacle based on the fused obstacle information;

[0152] The server adds the non-shared obstacles to the historical obstacle list to obtain the target obstacle list, and adds the updated status information of the non-shared obstacles to the historical obstacle information to obtain the target obstacle information.

[0153] Optionally, the server obtains sub-target obstacle information matching each target vehicle based on the target obstacle information, including:

[0154] Based on the target obstacle information, the server obtains the first real-time position of each target obstacle in the target obstacle list and the second real-time position of each target vehicle;

[0155] The server obtains relative parameters between each target obstacle and each target vehicle based on the first real-time position of each target obstacle and the second real-time position of each target vehicle; wherein the relative parameters include relative distance and relative time.

[0156] The server compares the relative parameter with the parameter threshold. If the relative parameter is less than the parameter threshold, it generates the sub-target obstacle information of the target vehicle that matches the relative parameter based on the target obstacle that matches the relative parameter.

[0157] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.

[0158] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.

[0159] Furthermore, other configurations and functions of the apparatus in the embodiments of this application are known to those skilled in the art, and will not be described in detail here to reduce redundancy.

[0160] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0161] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0162] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0163] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0164] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0165] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0166] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0167] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A data acquisition method, characterized in that, include: Each target vehicle identifies the recognition area around its own vehicle, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server; The server receives the real-time obstacle information sent by each of the target vehicles, and merges the real-time obstacle information sent by each of the target vehicles to obtain merged obstacle information; The server updates the historical obstacle information based on the fused obstacle information to obtain the target obstacle information; Based on the target obstacle information, the server obtains sub-target obstacle information that matches each target vehicle; The server will send the sub-target obstacle information matched with each target vehicle to the corresponding target vehicle respectively; Specifically, the server obtains an updated obstacle list based on the fused obstacle information; the server obtains a historical obstacle list based on the historical obstacle information; and the server compares the updated obstacle list and the historical obstacle list to obtain a comparison result. If the comparison result includes a common obstacle, the server obtains the updated status information of the common obstacle based on the fused obstacle information; the server obtains the historical status information of the common obstacle based on the historical obstacle information; the server updates the historical status information of the common obstacle based on the updated status information of the common obstacle to obtain the target obstacle information. If a non-shared obstacle exists in the comparison result, the location of the non-shared obstacle is determined; if the location of the non-shared obstacle is in the historical obstacle list, the server obtains the historical state information of the non-shared obstacle based on the historical obstacle information; the server obtains the predicted state information of the non-shared obstacle based on the historical state information, and updates the historical state information of the non-shared obstacle based on the predicted state information of the non-shared obstacle to obtain the target obstacle information.

2. The method according to claim 1, characterized in that, Each target vehicle identifies a recognition area around itself, obtains real-time obstacle information within that area, and sends the real-time obstacle information to the server, including: Each target vehicle identifies the identification area and obtains various identification data; Each target vehicle fuses multiple types of identification data to obtain fused data; Each target vehicle performs a first coordinate transformation on the fused data to obtain the real-time obstacle information and sends the real-time obstacle information to the server.

3. The method according to claim 1, characterized in that, Each target vehicle identifies a recognition area around itself, obtains real-time obstacle information of the recognition area, and sends the real-time obstacle information to the server. The method also includes: Each target vehicle identifies the identification area and obtains various identification data; Each target vehicle fuses multiple types of recognition data to obtain real-time obstacle information, and sends the real-time obstacle information to the server. The server performs a second coordinate transformation on the real-time obstacle information to obtain the target obstacle information.

4. The method according to claim 1, characterized in that, After determining the location of the non-shared obstacle if it exists in the comparison result, the method further includes: If the location of the non-shared obstacle is in the updated obstacle list, the server obtains the updated status information of the non-shared obstacle based on the fused obstacle information; The server adds the non-shared obstacles to the historical obstacle list to obtain the target obstacle list, and adds the updated status information of the non-shared obstacles to the historical obstacle information to obtain the target obstacle information.

5. The method according to claim 4, characterized in that, Based on the target obstacle information, the server obtains sub-target obstacle information matching each target vehicle, including: Based on the target obstacle information, the server obtains the first real-time position of each target obstacle in the target obstacle list and the second real-time position of each target vehicle; The server obtains relative parameters between each target obstacle and each target vehicle based on the first real-time position of each target obstacle and the second real-time position of each target vehicle; wherein the relative parameters include relative distance and relative time. The server compares the relative parameter with the parameter threshold. If the relative parameter is less than the parameter threshold, it generates the sub-target obstacle information of the target vehicle that matches the relative parameter based on the target obstacle that matches the relative parameter.

6. A data acquisition device, characterized in that, The apparatus for implementing the method as described in any one of claims 1 to 5, the apparatus comprising: The recognition module is used for each target vehicle to recognize the recognition area around its own vehicle, obtain real-time obstacle information of the recognition area, and send the real-time obstacle information to the server. The fusion module is used by the server to receive the real-time obstacle information sent by each of the target vehicles, and to fuse the real-time obstacle information sent by each of the target vehicles to obtain fused obstacle information. The update module is used by the server to update the historical obstacle information based on the fused obstacle information to obtain the target obstacle information; The acquisition module is used by the server to obtain sub-target obstacle information matching each target vehicle based on the target obstacle information; The sending module is used by the server to send the sub-target obstacle information that matches each target vehicle to the corresponding target vehicle.

7. An electronic device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1 to 5.

Images