Motor vehicle side obstacle map construction method and device, computer readable storage medium and computer program product

Abstract

This invention provides a method, apparatus, computer-readable storage medium, and computer program product for constructing a side obstacle map of a motor vehicle. The method includes: associating each side ultrasonic radar on both sides of the motor vehicle body and its corresponding adjacent corner ultrasonic radar into a detection group, and determining one ultrasonic radar as the primary transmitting radar and the other as the listening radar in each detection group; controlling each detection group to detect obstacles on the side of the motor vehicle to obtain point cloud information of the obstacles; and fitting the point cloud information to construct a point cloud map of obstacles located on the side of the motor vehicle body. This embodiment detects obstacles by using a detection group composed of side ultrasonic radars and corner ultrasonic radars, and constructs an obstacle map by fusing point cloud information generated by multiple ultrasonic radars around the vehicle body, which can improve the accuracy of side obstacle map construction.

Description

Technical Field

[0001] This invention relates to the field of vehicle obstacle detection technology, and in particular to a method, apparatus and computer-readable storage medium for constructing a map of obstacles on the side of a motor vehicle. Background Technology

[0002] Motor vehicles use ultrasonic radar installed on their bodies to detect obstacles around them, enabling driver assistance functions such as automatic parking and obstacle avoidance. When the ultrasonic radar detects and identifies obstacles, the detected obstacle coordinates need to be converted into a corresponding obstacle map for subsequent parking obstacle avoidance and scene map construction. In driving scenarios where space on both sides is relatively narrow, such as when parking, side obstacle maps are typically built for both sides of the vehicle.

[0003] An existing method for constructing a side obstacle map for motor vehicles involves controlling the detection coordinate data generated by a single-side ultrasonic radar to detect obstacles, and then fusing the detection coordinate data from all the side ultrasonic radars to construct a side obstacle map. However, the inventors found in practice that a single-side ultrasonic radar is prone to errors and blind spots when detecting obstacles. For example, when a vehicle approaches a pillar on the side of a parking space, the ultrasonic radar probe on one side may have a detection deviation due to angle issues. Therefore, the accuracy of traditional side obstacle map construction for motor vehicles is relatively low. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a method for constructing a map of obstacles on the side of a motor vehicle, which can effectively improve the accuracy of obstacle map construction.

[0005] A further technical problem to be solved by the embodiments of the present invention is to provide a vehicle side obstacle map construction device, which can effectively improve the accuracy of obstacle map construction.

[0006] A further technical problem to be solved by the embodiments of the present invention is to provide a computer-readable storage medium for storing a computer program that can effectively improve the accuracy of obstacle map construction.

[0007] A further technical problem to be solved by the embodiments of the present invention is to provide a computer program product that can effectively improve the accuracy of obstacle map construction.

[0008] To address the aforementioned technical problems, this invention first provides the following technical solution: a method for constructing a map of side obstacles of a motor vehicle, comprising the following steps: Each side ultrasonic radar on both sides of the vehicle body and its corresponding adjacent corner ultrasonic radar are associated as a detection group, and in each detection group, one ultrasonic radar is designated as the main transmitting radar and the other ultrasonic radar as the listening radar. Control each detection group to detect obstacles on the side of the vehicle and obtain point cloud information of the obstacles; and The point cloud information is fitted to construct a point cloud map of obstacles located on the side of the vehicle.

[0009] Furthermore, the control of each detection group to detect obstacles on the side of the vehicle and obtain point cloud information of the obstacles specifically includes: The system controls each detection group to detect obstacles on the side of the vehicle, and calculates and saves the detection coordinates of the obstacles within the radar coordinate system of the main radar using the triangulation principle; and The detected coordinates are respectively transformed to the pre-constructed vehicle coordinate system and world coordinate system to obtain the first transformed coordinates and the second transformed coordinates. Each set of coordinate points of an obstacle detected is taken as a point cloud, and the corresponding first transformed coordinates and the second transformed coordinates are taken as the point cloud information of the point cloud.

[0010] Furthermore, the step of fitting the point cloud information to construct a point cloud map of obstacles around the vehicle body specifically includes: summarizing the point clouds generated based on the detection coordinates of each of the main radars on the same side of the vehicle body, and using a preset fitting algorithm model to perform point cloud fitting based on the first transformed coordinates or the second transformed coordinates in the point cloud information of each of the point clouds on the same side of the vehicle body in history to generate a point cloud map of obstacles on the same side of the vehicle body.

[0011] Furthermore, before fitting the point cloud information, the point cloud information is first filtered, and the data filtering includes at least outlier filtering, duplicate value filtering, and false detection value filtering.

[0012] Furthermore, the outlier filtering specifically includes: determining whether the main echo height and the listener echo height contained in the point cloud information both fall within the corresponding preset echo height range; if not, the point cloud corresponding to the relevant point cloud information is removed.

[0013] Furthermore, it is determined whether the actual distance between the current point cloud and each point cloud on the same side of the vehicle in history is less than a preset distance threshold. If not, the point cloud corresponding to the corresponding point cloud information is removed.

[0014] Furthermore, in each detection group, the side ultrasonic radar is used as the main transmitting radar, while the corner ultrasonic radar is used as the listening radar.

[0015] On the other hand, in order to solve the above-mentioned further technical problems, the present invention provides the following technical solution: a vehicle side obstacle map construction device, connected to various ultrasonic radars installed on the vehicle body, 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 vehicle side obstacle map construction method as described in any of the above.

[0016] Furthermore, in order to solve the aforementioned technical problems, the present invention provides the following technical solution: 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 execute the vehicle side obstacle map construction method as described in any of the above.

[0017] On another front, in order to solve the aforementioned further technical problems, the present invention provides the following technical solution: a computer program product, including a computer program, wherein when the computer program is executed by a processor, it implements the method for constructing a vehicle side obstacle map as described in any of the above claims.

[0018] After adopting the above technical solution, the embodiments of the present invention have at least the following beneficial effects: The embodiments of the present invention associate each side ultrasonic radar on both sides of the vehicle body and its corresponding adjacent corner ultrasonic radar into a detection group, and determine one ultrasonic radar as the main transmitting radar and the other ultrasonic radar as the listening radar in each detection group. A side ultrasonic radar and a corner ultrasonic radar can be combined in pairs to detect obstacles, thereby avoiding the detection blind spot caused by the detection angle when a single ultrasonic radar is detected, and improving the accuracy of obstacle detection. Furthermore, by controlling each detection group to detect obstacles on the side of the vehicle, point cloud information can be obtained. Finally, by fitting the point cloud information, a point cloud map of obstacles located on the side of the vehicle is constructed. The point cloud map integrates the detection data of multiple ultrasonic radars on the side of the vehicle body, which can effectively reduce errors and improve the accuracy of obstacle map construction. Attached Figure Description

[0019] Figure 1 This is a flowchart of an optional embodiment of the method for constructing a map of side obstacles of a motor vehicle according to the present invention.

[0020] Figure 2 This is a flowchart of step S2 of an optional embodiment of the method for constructing a map of side obstacles of a motor vehicle according to the present invention.

[0021] Figure 3This is a schematic diagram of the arrangement of ultrasonic radar on a motor vehicle, which is an optional embodiment of the method for constructing a side obstacle map of a motor vehicle according to the present invention.

[0022] Figure 4 This is a schematic diagram of a combination of side ultrasonic radar and corner ultrasonic radar for an optional embodiment of the method for constructing a vehicle side obstacle map according to the present invention.

[0023] Figure 5 This is a schematic diagram of point cloud fitting for an optional embodiment of the method for constructing a map of obstacles on the side of a motor vehicle according to the present invention.

[0024] Figure 6 This is a schematic diagram of an optional embodiment of the vehicle side obstacle map construction device of the present invention.

[0025] Figure 7 This is a functional block diagram of an optional embodiment of the vehicle side obstacle map construction device of the present invention. Detailed Implementation

[0026] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments. It should be understood that the following illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention. Moreover, the embodiments and features in the embodiments of the present application can be combined with each other unless otherwise specified.

[0027] like Figure 1 As shown, an optional embodiment of the present invention provides a method for constructing a map of obstacles on the side of a motor vehicle, comprising the following steps: S1: Associate each side ultrasonic radar on both sides of the vehicle body and its corresponding adjacent corner ultrasonic radar into a detection group, and in each detection group, determine one ultrasonic radar 3 as the main transmitting radar and the other ultrasonic radar as the listening radar. S2: Control each detection group to detect obstacles on the side of the vehicle and obtain point cloud information of the obstacles; and S3: Fit the point cloud information to construct a point cloud map of obstacles located on the side of the vehicle.

[0028] This invention relates to a detection group by associating each side ultrasonic radar on both sides of a vehicle body with its corresponding adjacent corner ultrasonic radar. Within each detection group, one ultrasonic radar 3 is designated as the primary transmitting radar, while the other ultrasonic radar 3 is designated as the listening radar. A side ultrasonic radar and a corner ultrasonic radar can be combined in pairs to detect obstacles, thereby avoiding blind spots caused by the detection angle when a single ultrasonic radar 3 is used, and improving the accuracy of obstacle detection. Furthermore, by controlling each detection group to detect obstacles on the side of the vehicle, point cloud information can be obtained. Finally, by fitting the point cloud information, a point cloud map of obstacles located on the side of the vehicle is constructed. The point cloud map integrates the detection data of multiple ultrasonic radars on the side of the vehicle body, which can effectively reduce errors and improve the accuracy of obstacle map construction.

[0029] In an optional embodiment of the present invention, such as Figure 2 As shown, step S2 specifically includes: S21: Control each detection group to detect obstacles on the side of the vehicle by using the triangulation principle to calculate and save the detection coordinates of the obstacles in the radar coordinate system of the main radar; and S22: The detection coordinates are respectively transformed to the pre-constructed vehicle coordinate system and world coordinate system to obtain the first transformed coordinates and the second transformed coordinates. Each set of coordinate points of an obstacle detected is taken as a point cloud, and the corresponding first transformed coordinates and the second transformed coordinates are taken as the point cloud information of the point cloud.

[0030] In this embodiment, the two ultrasonic radars in each detection group can accurately and quickly calculate the detection coordinates of the corresponding obstacles by adopting the triangulation principle. Through the corresponding coordinate transformation, the first transformed coordinates and the second transformed coordinates are formed. Finally, the corresponding point cloud information can be formed based on the first transformed coordinates and the second transformed coordinates, which has high processing efficiency.

[0031] In an optional embodiment of the present invention, step S3 specifically includes: summarizing the point clouds generated based on the detection coordinates of each of the main radars on the same side of the vehicle body, and using a preset fitting algorithm model to perform point cloud fitting based on the first transformed coordinates or the second transformed coordinates in the point cloud information of each point cloud on the same side of the vehicle body in history to generate a point cloud map of obstacles on the side of the vehicle body. In this embodiment, by summarizing the point cloud information of each point cloud on the same side of the vehicle body, and then performing point cloud fitting on each point cloud on the same side, a point cloud map of one side of the vehicle body can be formed, which has high fitting efficiency.

[0032] In specific implementation, the fitting algorithm model is linear least squares. Linear least squares fits point clouds based on residuals within a preset range. The linear least squares method determines model parameters by minimizing the sum of squared errors between predicted and observed values. Its goal is to find linear model parameters that minimize the sum of squared errors, ultimately achieving linear fitting, i.e., minimizing the following equation: (Formula 1); in, For predicted values, This is the actual value.

[0033] The linear model used is a univariate model: (Formula 2); The error function used is the sum of squared errors: (Formula 3); By differentiating Equation 3 and taking partial derivatives with respect to a and b, and setting them to zero, we obtain the following system of normal equations: (Formula 4); Solving the system of equations yields: (Formula 5); The residual analysis is as follows: Model prediction value (Formula 6); The residual of the observed values ​​is (Formula 7); In practice, the equation is optimized to make the residual e as close to 0 as possible. The preset range of residual e can be set to ±10cm. The closer the residual e is to 0, the stronger the linearity of the fitted line.

[0034] When pre-establishing the vehicle coordinate system and world coordinate system, the vehicle coordinate system (X) V Y V Z V Typically, the origin is the center point of the rear axle of the vehicle, the X-axis is along the driver's direction of travel, the Y-axis is the driver's left-hand side, and the steering wheel angle is positive counterclockwise (i.e., turning the steering wheel to the left is positive). In the world coordinate system, the Z-axis points upwards from the ground, and the unit is meters. The vehicle's heading angle is relative to the positive X-axis, with counterclockwise being positive. Transforming the detected coordinates to both the vehicle coordinate system and the world coordinate system to obtain the first and second transformed coordinates is a common calculation process in computer data processing, and will not be elaborated upon here.

[0035] In an optional embodiment of the present invention, the point cloud information is first filtered before fitting, and the data filtering includes at least outlier filtering, duplicate value filtering, and false positive filtering. In this embodiment, before point cloud fitting, data filtering can remove obviously abnormal, duplicate, and erroneous point clouds, thereby improving computational accuracy and efficiency. It is understood that outliers usually refer to observation points in the dataset that are significantly different from other values, usually due to data noise; duplicate values ​​usually refer to data with the same timestamp, angle, and distance, which can be merged; and false positives refer to obviously incorrect data caused by data quality problems (such as input errors, sensor malfunctions, or program defects).

[0036] In an optional embodiment of the present invention, the outlier filtering specifically includes: determining whether the main echo height and the listener echo height contained in the point cloud information both fall within a corresponding preset echo height range (e.g., 1-3 times the preset echo height value); if not, the point cloud corresponding to the relevant point cloud information is removed. In this embodiment, the main echo height and the listener echo height in the point cloud information can be combined for judgment to remove point cloud information exceeding the corresponding echo height range, making outlier data filtering convenient and efficient. In specific implementation, when the detection coordinates of the obstacle are calculated and stored in the radar coordinate system using the triangulation principle, the main echo height of the obstacle relative to the main transmitting radar and the listener echo height relative to the listener radar are also calculated and stored.

[0037] In specific implementation, when calculating and storing the detection coordinates of the obstacle in the radar coordinate system using the triangulation principle, the main detection range of the obstacle relative to the main transmitting radar and the listening detection range relative to the listening radar are also calculated and stored. The point cloud information also includes the main detection range and the listening detection range. In this embodiment, the point cloud information also includes the main detection range of the obstacle relative to the main transmitting radar and the listening detection range relative to the listening radar, which facilitates long-range tracking of the obstacle by combining this data information in the point cloud information.

[0038] In an optional embodiment of the present invention, the false detection filtering specifically includes: determining whether the actual distance between the current point cloud and each of the historical point clouds on the same side of the vehicle body is less than a preset distance threshold; if not, the point cloud corresponding to the corresponding point cloud information is removed. In this embodiment, when the distance between the detected point cloud and the historical point cloud differs too much, the point cloud is determined as false detection data and filtered out, thereby improving the accuracy of the obstacle point cloud and thus improving the coordinate accuracy when constructing the side obstacle map.

[0039] In an optional embodiment of the present invention, the side ultrasonic radar is used as the main transmitting radar in each detection group, while the corner ultrasonic radar is used as the listening radar. In this embodiment, the corner ultrasonic radar is set as the main transmitting radar responsible for actively emitting ultrasonic signals, while the side ultrasonic radar is used as a dedicated listening radar to passively receive echoes; this enables asymmetric distributed detection, effectively covering the vehicle's lateral blind spots and corner blind areas, significantly improving the accuracy of obstacle distance and orientation determination, and enhancing environmental perception capabilities in low-speed parking and close-range collision avoidance scenarios. In specific implementation, the main transmitting radar and the listening radar can be interchanged in each detection group, that is, the side ultrasonic radar can also be used as the listening radar, while the corner ultrasonic radar is used as the main transmitting radar.

[0040] In addition, such as Figure 3 As shown, in the common ultrasonic radar layout of motor vehicles, the onboard ECU system controls each ultrasonic radar. Motor vehicles typically have one side ultrasonic radar (FLS, FRS, RLS, and RRS) installed at the front and rear positions on both sides of the vehicle. Each side ultrasonic radar can be combined with a nearby corner ultrasonic radar (FL, FR, RL, and RR) to detect obstacles. Figure 4 In the illustrated embodiment, the side ultrasonic radar FLS is associated with the corner ultrasonic radar FL, the side ultrasonic radar FRS with the corner ultrasonic radar FR, the side ultrasonic radar RLS with the corner ultrasonic radar RL, and the side ultrasonic radar RRS with the corner ultrasonic radar RR, forming a total of four detection groups. In each detection group, the corresponding side ultrasonic radar is used as the main transmitting radar and the corner ultrasonic radar is used as the listening radar. Taking the detection group composed of the side ultrasonic radar FLS and the corner ultrasonic radar FL as an example, the side ultrasonic radar FLS emits ultrasonic waves as the main transmitting radar. The echo reflected by the obstacle obj is received by the side ultrasonic radar FLS and the corner ultrasonic radar FL, respectively, thereby generating the main transmitting detection range (calculated by the side ultrasonic radar FLS based on the received echo) and the listening detection range (calculated by the corner ultrasonic radar FL based on the received echo). By combining the main transmitting detection range, the listening detection range, and the pre-calibrated installation indirection d of the side ultrasonic radar FLS and the corner ultrasonic radar FL, the detection coordinates of the obstacle can be calculated using geometric knowledge.

[0041] In addition, such as Figure 5 As shown in the figure, the yellow frame represents the motor vehicle, the green dots inside the yellow frame represent the ultrasonic radars on the vehicle body, the white dots outside the yellow frame represent the point cloud generated by the detection, and the red dots at both ends of each white dot represent the two endpoints of the fitted line generated after the point cloud is fitted.

[0042] On the other hand, such as Figure 6This invention further provides a vehicle side obstacle map construction device 1, which is connected to each ultrasonic radar 3 installed on the vehicle body. It includes a processor 10, a memory 12, and a computer program stored in the memory 12 and configured to be executed by the processor 10. When the processor 10 executes the computer program, it implements the vehicle side obstacle map construction method as described in any of the above.

[0043] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 10 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the vehicle side obstacle map construction device 1. For example, the computer program can be divided into... Figure 7 The functional modules in the motor vehicle side obstacle map construction device 1 include the radar association module 41, the radar control module 42, and the point cloud fitting and mapping module 43, which respectively perform the above steps S1-S3.

[0044] The vehicle side obstacle map building device 1 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The vehicle side obstacle map building device 1 may include, but is not limited to, a processor 10 and a memory 12. Those skilled in the art will understand that the schematic diagram is merely an example of the vehicle side obstacle map building device 1 and does not constitute a limitation on the device. It may include more or fewer components than shown, or combine certain components, or use different components. For example, the vehicle side obstacle map building device 1 may also include input / output devices, network access devices, buses, etc.

[0045] The processor 10 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 10 is the control center of the vehicle side obstacle map building device 1, connecting all parts of the device via various interfaces and lines.

[0046] The memory 12 can be used to store the computer program and / or modules. The processor 10 implements various functions of the vehicle side obstacle map building device 1 by running or executing the computer program and / or modules stored in the memory 12 and calling the data stored in the memory 12. The memory 12 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as image recognition function, image overlay function, etc.), etc.; the data storage area may store data (such as graphic data, etc.) created based on the use of the vehicle side obstacle map building device 1. In addition, the memory 12 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0047] If the functions described in the embodiments of the present invention are implemented in the form of software functional modules or units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the embodiments of the present invention can implement all or part of the processes in the methods described above, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 10, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0048] In another aspect, embodiments of the present invention 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 execute the vehicle side obstacle map construction method as described in any of the above.

[0049] In another aspect, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method for constructing a vehicle side obstacle map as described in any of the above embodiments.

[0050] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0051] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the scope of protection of the present invention.

Claims

1. A method for constructing a map of side obstacles of a motor vehicle, characterized in that, The method includes the following steps: Each side ultrasonic radar on both sides of the vehicle body and its corresponding adjacent corner ultrasonic radar are associated as a detection group, and in each detection group, one ultrasonic radar is designated as the main transmitting radar and the other ultrasonic radar as the listening radar. Control each detection group to detect obstacles on the side of the vehicle and obtain point cloud information of the obstacles; and The point cloud information is fitted to construct a point cloud map of obstacles located on the side of the vehicle.

2. The method for constructing a vehicle side obstacle map as described in claim 1, characterized in that, The control of each detection group to detect obstacles on the side of the vehicle and obtain point cloud information of the obstacles specifically includes: The system controls each detection group to detect obstacles on the side of the vehicle, and calculates and saves the detection coordinates of the obstacles within the radar coordinate system of the main radar using the triangulation principle; and The detected coordinates are respectively transformed to the pre-constructed vehicle coordinate system and world coordinate system to obtain the first transformed coordinates and the second transformed coordinates. Each set of coordinate points of an obstacle detected is taken as a point cloud, and the corresponding first transformed coordinates and the second transformed coordinates are taken as the point cloud information of the point cloud.

3. The method for constructing a vehicle side obstacle map as described in claim 2, characterized in that, The step of fitting the point cloud information to construct a point cloud map of obstacles located on the side of the vehicle specifically includes: summarizing the point clouds generated based on the detection coordinates of each of the main radars on the same side of the vehicle, and using a preset fitting algorithm model to perform point cloud fitting based on the first or second transformed coordinates in the point cloud information of each of the point clouds on the same side of the vehicle in history to generate a point cloud map of obstacles on the side of the vehicle.

4. The method for constructing a vehicle side obstacle map as described in claim 1, characterized in that, Before fitting the point cloud information, the point cloud information is first filtered, and the data filtering includes at least outlier filtering, duplicate value filtering and false detection value filtering.

5. The method for constructing a vehicle side obstacle map as described in claim 4, characterized in that, The outlier filtering specifically includes: determining whether the main echo height and the listener echo height contained in the point cloud information both fall within the corresponding preset echo height range; if not, the point cloud corresponding to the corresponding point cloud information is removed.

6. The method for constructing a vehicle side obstacle map as described in claim 4, characterized in that, The false detection filtering specifically includes: determining whether the actual distance between the current point cloud and each point cloud on the same side of the vehicle in history is less than a preset distance threshold; if not, the point cloud corresponding to the corresponding point cloud information is removed.

7. The method for constructing a vehicle side obstacle map as described in claim 1, characterized in that, In each detection group, the side ultrasonic radar is used as the main transmitting radar, while the corner ultrasonic radar is used as the listening radar.

8. A vehicle side obstacle map construction device, connected to various ultrasonic radars installed on the vehicle body, characterized in that, The apparatus includes 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 for constructing a vehicle side obstacle map as described in any one of claims 1 to 7.

9. 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 for constructing a vehicle side obstacle map as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for constructing a vehicle side obstacle map as described in any one of claims 1-7.

Images