Obstacle modeling method and device, equipment and medium

Abstract

The embodiment of the invention provides an obstacle modeling method and device, equipment and a medium. The method comprises the steps that firstly, for each obstacle, according to obstacle envelope point information and lane information collected by data collection equipment of a vehicle, an obstacle envelope point is projected to a vehicle body coordinate system, and first position information of the obstacle envelope point is determined; then, for each data point, calculating the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope point and the lane information; filtering the data points according to the lane distance and the lane information to generate second position information of the obstacle envelope point; then, according to the lane distance, the lane information and the second position information of the obstacle envelope point, performing classification processing on the data points according to different lanes, and generating third position information of the obstacle envelope point; and finally, according to the third position information of the obstacle envelope point, obstacle modeling is carried out on the obstacle, and the obstacle modeling complexity is reduced.

Description

Technical Field

[0001] This application relates to the field of vehicle autonomous driving, and particularly to an obstacle modeling method, apparatus, device and medium. Background Art

[0002] Environmental modeling refers to the perception ability of an unmanned driving system for the surrounding environment, which is one of the key technologies of autonomous driving. Through environmental modeling, it can help the vehicle generate an optimal path based on road obstacles and Internet of Things information, and help the vehicle predict potential risks. Therefore, environmental modeling is not only the basis for the unmanned driving system to perceive, understand and respond to complex environmental roads, but also one of the core technologies to ensure that autonomous driving vehicles can make road decisions efficiently and safely.

[0003] The obstacle modeling method in the prior art first collects road information and obstacle information in real time through sensors, then processes different types of data separately, fuses the processed data to generate an environmental model, and then the vehicle determines its own position and drivable area in the road based on the environmental model to make road decisions to ensure the safety and efficiency of autonomous driving.

[0004] The obstacle modeling method in the prior art is relatively complex in the data processing process, thus reducing the efficiency of the vehicle to make road decisions. Summary of the Invention

[0005] Embodiments of this application provide an obstacle modeling method, apparatus, device and medium, which are used to solve the problem that the obstacle modeling method in the prior art is relatively complex in the data processing process, thus reducing the efficiency of the vehicle to make road decisions.

[0006] In a first aspect, embodiments of this application provide an obstacle modeling method, including:

[0007] For each obstacle, according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device, project the obstacle envelope points into the vehicle body coordinate system to determine the first position information of the obstacle envelope points, where the obstacle envelope point information includes at least one data point information constituting the outer boundary of the obstacle;

[0008] For each data point, calculate the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope point and the lane information;

[0009] Filter the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points;

[0010] Classify the data points according to different lanes based on the lane distance, the lane information, and the second position information of the obstacle envelope points, and generate the third position information of the obstacle envelope points;

[0011] Perform obstacle modeling on the obstacle according to the third position information of the obstacle envelope points.

[0012] In a possible implementation, the lane information includes the lane width and the lane center line point information, and the lane width includes a first preset width and a second preset width;

[0013] The calculating the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope point and the lane information includes:

[0014] Calculate the relative distance between the data point and the position of the lane center line point according to the first position information of the obstacle envelope point and the lane center line point information;

[0015] Determine the relative distance as the lane distance between the data point and the vehicle.

[0016] In a possible implementation, the projecting the obstacle envelope point onto the vehicle body coordinate system according to the obstacle envelope point information and the lane information collected by the vehicle's data acquisition device to determine the first position information of the obstacle envelope point includes:

[0017] Determine the coordinates of the obstacle envelope point according to the obstacle envelope point information;

[0018] Project the coordinates of the obstacle envelope point onto the vehicle body coordinate system to obtain the two-dimensional coordinates of the obstacle envelope point;

[0019] Determine the first position information of the obstacle envelope point according to the two-dimensional coordinates of the obstacle envelope point.

[0020] In a possible implementation, the classifying and processing the data points according to different lanes based on the lane distance, the lane information, and the second position information of the obstacle envelope point to generate the third position information of the obstacle envelope point includes:

[0021] Determine the data points with the lane distance less than the first preset lane width as the data points in the lane where the vehicle is located according to the lane distance and the first preset lane width;

[0022] Determine the data points with the lane distance greater than the first preset lane width and less than the second preset lane width as the data points in the adjacent lane of the lane where the vehicle is located according to the lane distance, the first preset lane width, and the second preset lane width;

[0023] According to the data points of the lane where the vehicle is located, the data points of the adjacent lanes of the lane where the vehicle is located, and the two-dimensional coordinates of the obstacle envelope points, the third position information of the obstacle envelope points is generated according to the positive and negative values of the two-dimensional coordinates.

[0024] In a possible implementation manner, the generating the third position information of the obstacle envelope points according to the data points of the lane where the vehicle is located, the data points of the adjacent lanes of the lane where the vehicle is located, and the two-dimensional coordinates of the obstacle envelope points according to the positive and negative values of the two-dimensional coordinates includes:

[0025] For the data points in the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, the data points with positive ordinates in the two-dimensional coordinates are determined as the front obstacles in the lane where the vehicle is located, and the data points with positive ordinates in the two-dimensional coordinates are determined as the rear obstacles in the lane where the vehicle is located;

[0026] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, the data points with positive ordinates and positive abscissas in the two-dimensional coordinates are determined as the front obstacles in the adjacent right lane of the lane where the vehicle is located;

[0027] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, the data points with positive ordinates and negative abscissas in the two-dimensional coordinates are determined as the front obstacles in the adjacent left lane of the lane where the vehicle is located;

[0028] For the data point obstacles in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacles, the data point obstacles with negative ordinates and positive abscissas in the two-dimensional coordinates are determined as the rear obstacles in the adjacent right lane of the lane where the vehicle is located;

[0029] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, the data points with negative ordinates and negative abscissas in the two-dimensional coordinates are determined as the rear obstacles in the adjacent left lane of the lane where the vehicle is located.

[0030] In a possible implementation manner, the filtering the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points includes:

[0031] According to the lane distance and the second preset lane width, the data points with the lane distance greater than the second preset lane width are deleted to generate the second position information of the obstacle envelope points.

[0032] In a possible implementation, before performing obstacle modeling on the obstacle according to the third position information of the obstacle envelope points, the method further includes:

[0033] Judging whether the number of data points in the obstacle envelope points is greater than a preset number according to the third position information of the obstacle envelope points;

[0034] If the number of data points in the obstacle envelope points is greater than the preset number, then sort all the data points in the obstacle envelope points in ascending order of the lane distance, and determine the position information corresponding to the first preset number of data points as the third position information of the obstacle envelope points.

[0035] In a second aspect, an embodiment of the present application provides an obstacle modeling device, including:

[0036] A determination module, configured to project the obstacle envelope points onto the vehicle body coordinate system for each obstacle according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device, and determine the first position information of the obstacle envelope points, where the obstacle envelope point information includes at least one data point information constituting the outer boundary of the obstacle;

[0037] A calculation module, configured to calculate the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope points and the lane information for each data point;

[0038] A first generation module, configured to perform filtering processing on the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points;

[0039] A second generation module, configured to classify the data points according to different lanes according to the lane distance, the lane information, and the second position information of the obstacle envelope points to generate the third position information of the obstacle envelope points;

[0040] A processing module, performing obstacle modeling on the obstacle according to the third position information of the obstacle envelope points.

[0041] In a possible implementation, the lane information includes lane width and lane center line point information, and the lane width includes a first preset width and a second preset width;

[0042] The calculation module is specifically configured to:

[0043] Calculate the relative distance between the data point and the lane center line point position according to the first position information of the obstacle envelope points and the lane center line point information;

[0044] Determine the relative distance as the lane distance between the data point and the vehicle.

[0045] In a possible implementation manner, the determining module is specifically configured to:

[0046] Determine the coordinates of the obstacle envelope points according to the obstacle envelope point information;

[0047] Project the coordinates of the obstacle envelope points onto the vehicle body coordinate system to obtain the two-dimensional coordinates of the obstacle envelope points;

[0048] Determine the first position information of the obstacle envelope points according to the two-dimensional coordinates of the obstacle envelope points.

[0049] In a possible implementation manner, the second generating module is specifically configured to:

[0050] Determine the data points with the lane distance less than the first preset lane width as the data points of the lane where the vehicle is located according to the lane distance and the first preset lane width;

[0051] Determine the data points with the lane distance greater than the first preset lane width and less than the second preset lane width as the data points of the adjacent lanes of the lane where the vehicle is located according to the lane distance, the first preset lane width, and the second preset lane width;

[0052] Generate the third position information of the obstacle envelope points according to the data points of the lane where the vehicle is located, the data points of the adjacent lanes of the lane where the vehicle is located, and the two-dimensional coordinates of the obstacle envelope points according to the positive and negative values of the two-dimensional coordinates.

[0053] In a possible implementation manner, the second generating module is specifically configured to:

[0054] For the data points in the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinate in the two-dimensional coordinates as the front obstacles in the lane where the vehicle is located and the data points with positive ordinate in the two-dimensional coordinates as the rear obstacles in the lane where the vehicle is located;

[0055] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinate and positive abscissa in the two-dimensional coordinates as the front obstacles in the adjacent right lane of the lane where the vehicle is located;

[0056] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinate and negative abscissa in the two-dimensional coordinates as the front obstacles in the adjacent left lane of the lane where the vehicle is located;

[0057] For the data point obstacles in the adjacent lane of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacles, the data point obstacles with negative ordinate and positive abscissa in the two-dimensional coordinates are determined as the rear obstacles in the adjacent right lane of the lane where the vehicle is located;

[0058] For the data points in the adjacent lane of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, the data points with negative ordinate and negative abscissa in the two-dimensional coordinates are determined as the rear obstacles in the adjacent left lane of the lane where the vehicle is located.

[0059] In a possible implementation manner, the first generation module is specifically configured to:

[0060] Delete the data points with the lane distance greater than the second preset lane width according to the lane distance and the second preset lane width, and generate the second position information of the obstacle envelope points.

[0061] In a possible implementation manner, the obstacle modeling device further includes a judgment module. Before performing obstacle modeling on the obstacle according to the third position information of the obstacle envelope points, the judgment module is used to:

[0062] Judge whether the number of data points in the obstacle envelope points is greater than a preset number according to the third position information of the obstacle envelope points;

[0063] If the number of data points in the obstacle envelope points is greater than the preset number, sort all the data points in the obstacle envelope points in ascending order according to the lane distance, and determine the position information corresponding to the first preset number of data points as the third position information of the obstacle envelope points.

[0064] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0065] The memory stores computer execution instructions;

[0066] The processor executes the computer execution instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0067] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0068] The obstacle modeling method, device, equipment and medium provided by the embodiments of the present application first project the obstacle envelope points onto the vehicle body coordinate system according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device for each obstacle, and determine the first position information of the obstacle envelope points, so as to convert the position of the obstacle envelope points from the coordinate of the data into the actual coordinates understandable by the vehicle, ensuring the accuracy of subsequent calculations; then, for each data point, calculate the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope points and the lane information; further, filter the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points. In this way, it can be determined whether the data points of the obstacle are within the region of interest, and the number of data points in the modeling process is reduced through filtering, thereby reducing the complexity of obstacle modeling and improving the processing efficiency; then, classify the data points according to different lanes according to the lane distance, lane information and the second position information of the obstacle envelope points to generate the third position information of the obstacle envelope points. Through classification, the subsequent decision-making logic is optimized, enabling the driverless vehicle to judge the lane-changing or following strategy faster without traversing all obstacle envelope points for individual calculations; finally, model the obstacle according to the third position information of the obstacle envelope points, and thus can provide accurate path planning and obstacle avoidance strategies for subsequent vehicles to make road decisions, improving safety. Brief Description of the Drawings

[0069] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0070] Figure 1 Flow schematic of the obstacle modeling method provided by the embodiments of the present application Figure 1 ;

[0071] Figure 2 Flow schematic of the obstacle modeling method provided by the embodiments of the present application Figure 2 ;

[0072] Figure 3 Structural schematic diagram of the obstacle modeling device provided by the embodiments of the present application;

[0073] Figure 4 Structural schematic diagram of the electronic device provided by the embodiments of the present application.

[0074] Through the above drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to explain the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed Description of the Embodiments

[0075] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0076] Environmental modeling refers to the perception ability of an unmanned driving system to the surrounding environment and is one of the key technologies for autonomous driving. Environmental modeling includes two parts: physical modeling and cognitive understanding. Physical modeling refers to modeling the physical characteristics of the road, including information such as the curvature, slope, and width of the road. Cognitive understanding refers to the ability of an autonomous driving vehicle to understand other vehicles, pedestrians, and other obstacles, and can recognize the relative position of the obstacles with other vehicles, and accordingly identify the obstacles with collision risks. Through environmental modeling, it can help the vehicle generate an optimal path based on road obstacles and Internet of Things information, and help the vehicle predict potential risks. Therefore, environmental modeling is not only the basis for autonomous driving vehicles to perceive, understand, and respond to complex environmental roads, but also one of the core technologies to ensure that autonomous driving vehicles can make road decisions efficiently and safely.

[0077] The obstacle modeling method in the prior art first collects road information and obstacle information in real time through sensors, then processes different types of data separately, fuses the processed data to generate an environmental model, and then the vehicle determines its own position and drivable area in the road based on the environmental model to make road decisions to ensure the safety and efficiency of autonomous driving.

[0078] Then, the obstacle modeling method in the prior art is relatively complex in the data processing process. It not only needs to independently process all the collected obstacle data and perform high-precision fusion, which increases the computational overhead. In addition, the orientation of the obstacles is not specifically classified, so that the vehicle needs to traverse all the obstacles during decision-making and calculate their relative positions, lane relationships, and influence ranges with the vehicle one by one. This way of traversing one by one results in a relatively high computational complexity in the decision-making link, thereby reducing the efficiency of the vehicle to make road decisions.

[0079] Based on this, the present application proposes an obstacle modeling method. Since the commonly used obstacle modeling method directly performs high-precision data fusion on all the collected obstacle information, a large amount of heterogeneous data needs to be integrated during the processing, resulting in an increase in computational complexity. And when the vehicle makes a road decision subsequently, it needs to traverse all obstacles before performing path planning, which reduces the processing efficiency. However, if the envelope point information of the obstacles can be reasonably screened and classified before obstacle modeling, the computational burden can be effectively reduced and the processing efficiency can be improved. For example, first, delete the data points in the obstacle envelope points that are far from the lane to avoid irrelevant information interfering with path planning. Secondly, based on the lane information, the obstacle envelope points are finely classified into categories such as the current lane, the left lane, the right lane, etc., and further subdivided into front or rear obstacles, which can quickly identify the data points that have a direct impact on the vehicle's driving path. In the subsequent decision-making stage, the vehicle only needs to analyze the data points of the relevant categories without traversing all the data points, greatly reducing the computational complexity and improving the real-time performance of path planning.

[0080] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0081] Figure 1 Flow schematic of the obstacle modeling method provided by the embodiment of the present application Figure 1 , such as Figure 1 shown, the method includes:

[0082] S101. For each obstacle, project the obstacle envelope points onto the vehicle body coordinate system according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device, and determine the first position information of the obstacle envelope points.

[0083] Among them, the obstacle envelope point information includes at least one data point information that constitutes the outer boundary of the obstacle; the first position information of the obstacle envelope points refers to the positions of all obstacles that can be collected by the data acquisition device in the vehicle body coordinate system.

[0084] It should be noted that the vehicle body coordinate system involved in the embodiments of the present application is a right-handed coordinate system with the ground at the center of the rear axle of the vehicle as the origin, the right side of the vehicle as the positive direction of the X axis, and the front side of the vehicle as the positive direction of the Y axis.

[0085] It can be understood that since the image coordinate system is different from the vehicle body coordinate system, coordinate transformation is required to map the coordinates to the vehicle body coordinate system. By using the obstacle envelope point information collected by the vehicle's data acquisition device, the coordinates of the obstacle envelope points can be transformed into the coordinates in the vehicle body coordinate system, which can enable the vehicle to better understand the position where the obstacle envelope points are located, so as to perform reasonable path planning and decision-making in the subsequent stage.

[0086] In one realizable way, the specific steps for determining the first position information of the obstacle are as follows:

[0087] First, determine the coordinates of the obstacle envelope points according to the obstacle envelope point information; then, project the coordinates of the obstacle envelope points onto the vehicle body coordinate system to obtain the two-dimensional coordinates of the obstacle envelope points; finally, determine the first position information of the obstacle envelope points according to the two-dimensional coordinates of the obstacle envelope points.

[0088] Optionally, when performing coordinate transformation, the internal parameter matrix (focal length, optical center, etc.) and external parameter matrix (the position and orientation of the camera relative to the vehicle body) of the camera can be used, and the perspective projection formula is used to transform the coordinates of the obstacle envelope points into the three-dimensional coordinates in the camera coordinate system. Further, the camera coordinate system is then transformed into the vehicle body coordinate system through the vehicle body coordinate system transformation (based on the rotation matrix and displacement vector). In this way, the position of the obstacle envelope points can be transformed from the camera coordinate system to the vehicle body coordinate system (actual physical coordinates), enabling the position of the obstacle envelope points to be accurately recognized by the vehicle.

[0089] S102. For each data point, calculate the lane distance between the data point and the vehicle according to the first position information of the obstacle envelope points and the lane information.

[0090] Among them, the lane information includes the lane width and the lane center line point information; the lane width includes a first preset width and a second preset width; the lane center line point information is a sequence of coordinate points on the lane center line passed by the vehicle, and each road point is spaced at a certain distance to form a discretized path to help the vehicle perform path tracking and control. For example, in the vehicle body coordinate system, assuming that the interval distance is 5 meters (m), the road point information can be marked as: road point A(0, 5) is located 5m directly in front of the vehicle; road point B(0, 10) is located 10m directly in front of the vehicle.

[0091] It should be noted that the calculation method of the lane distance between the data point and the vehicle can use the Euclidean distance formula, or the Manhattan distance formula, or the Chebyshev distance formula for calculation. The specific calculation method is selected according to the actual situation, and the embodiments of the present application do not make specific limitations here.

[0092] In one implementable manner, first, according to the first position information of the obstacle envelope points and the lane center line waypoint information, calculate the relative distance between the data points and the lane center line waypoints; then, determine the relative distance as the lane distance between the data points and the vehicle.

[0093] It should be understood that in the perception of the autonomous driving environment, accurately judging the relative position between the data points in the obstacle envelope points and the lane is crucial for path planning. Therefore, in the embodiments of the present application, the waypoint information of the lane center line is used to calculate the lane distance between the obstacle and the vehicle, that is, the distance between the obstacle and the nearest lane center point. Specifically, first, according to the first position information of the obstacle envelope points, that is, the two-dimensional coordinates of the obstacle envelope points, and the waypoint coordinates in the lane center line waypoint information, then calculate the relative distance between the data points and all waypoints, and sort the calculated relative distances between the obstacle and all waypoints, and select the minimum relative distance as the lane distance between the data points and the vehicle. Calculating the lane distance through the discrete lane center line waypoints can more accurately judge the position of the data points relative to the lane, thereby further improving the efficiency of data point classification and obstacle avoidance path planning.

[0094] For example, assume that the vehicle is driving along the lane, and the coordinates of the lane center line waypoint positions are: P1(0, 0), P2(0, 5), P3(0, 10), and the two-dimensional coordinates of the data point in the vehicle body coordinate system are (3, 15). If the Euclidean distance formula is used to calculate the relative distance d between the data point and all waypoints, the following can be obtained:

[0095]

[0096]

[0097]

[0098] By sorting the above multiple relative distances d, it can be determined that the lane distance between the data point and the vehicle is 5.8 m, that is, the obstacle is 5.8 m outside the lane.

[0099] S103. Filter the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points.

[0100] Among them, the second position information of the obstacle envelope points is the position of other data points in the vehicle body coordinate system after deleting the data points that are far from the lane according to the lane distance and the lane information.

[0101] In one implementable manner, the specific steps for filtering the data points to generate the second position information of the obstacle envelope points are as follows:

[0102] Delete the data points with lane distances greater than the second preset lane width according to the lane distance and the second preset lane width, and generate the second position information of the obstacle envelope points.

[0103] Continuing with the example in S102, if the lane distance of the data point is 5.8 m, the lane width is 3 m, and the second preset lane width is 1.5 times the lane width, i.e., 4.5 m, then since the lane distance of this data point is greater than the second preset lane width, it indicates that the obstacle is far from the vehicle and is a redundant data point. Therefore, this data point needs to be deleted to reduce the complexity in the obstacle modeling process.

[0104] It should be understood that in this way, redundant data points far from the vehicle can be effectively filtered out, thereby optimizing the computational efficiency of obstacle modeling. At the same time, the vehicle system can process the obstacle data points that truly affect the driving path more quickly, improving the real-time performance of decision-making and reducing the response time.

[0105] S104. Classify the data points according to different lanes based on the lane distance, lane information, and the second position information of the obstacle envelope points, and generate the third position information of the obstacle envelope points.

[0106] It can be understood that by generating the third position information of the obstacle envelope points through lane classification of the data points and performing obstacle modeling, in the subsequent decision-making stage, the vehicle only needs to analyze the data points of the relevant categories, without having to traverse the data point information in all obstacle envelope points, greatly reducing the computational complexity and improving the real-time performance of path planning.

[0107] S105. Model the obstacle according to the third position information of the obstacle envelope points.

[0108] Among them, the third position information of the obstacle envelope points is the position of the data points after precise classification in the vehicle body coordinate system based on the second position information of the obstacle envelope points.

[0109] It can be understood that the obstacle model generated by modeling based on the third position information can effectively improve the efficiency of modeling processing.

[0110] The obstacle modeling method provided by the embodiment of the present application first projects the obstacle envelope points onto the vehicle body coordinate system according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device for each obstacle, and determines the first position information of the obstacle envelope points, so as to convert the coordinates of the obstacle envelope points into actual coordinates that the vehicle can understand, ensuring the accuracy of subsequent calculations. Then, for each data point, the lane distance between the data point and the vehicle is calculated according to the first position information of the obstacle envelope points and the lane information. Further, according to the lane distance and the lane information, the data points are filtered to generate the second position information of the obstacle envelope points. In this way, it can be determined whether the data points of the obstacle are within the region of interest, and the number of data points in the modeling process is reduced through filtering, thereby reducing the complexity of obstacle modeling and improving the processing efficiency. Then, according to the lane distance, lane information, and the second position information of the obstacle envelope points, the data points are classified according to different lanes to generate the third position information of the obstacle envelope points. Through classification, the subsequent decision-making logic is optimized, enabling the driverless vehicle to judge the lane-changing or following strategy faster without traversing all obstacle envelope points for individual calculations. Finally, based on the third position information of the obstacle envelope points, the obstacle is modeled, which can provide accurate path planning and obstacle avoidance strategies for subsequent vehicles on the road, improving safety.

[0111] Figure 2 Schematic flow of the obstacle modeling method provided by the embodiment of the present application Figure 2 , as Figure 2 shown, on the basis of the Figure 2 embodiment, the process of classifying obstacles is described in detail. The method includes:

[0112] S201. Determine the data points with a lane distance less than the first preset lane width as the data points of the lane where the vehicle is located according to the lane distance and the first preset lane width.

[0113] For example, if the lane distance d between the data point and the vehicle is 1 m, the lane width w is 3 m, and the first preset lane width w1 is 0.5w, that is, 1.5 m, then since the lane distance d of this data point is less than the first preset lane width w1, it indicates that this data point is within the current lane range, and this data point is determined as the data point of the lane where the vehicle is located.

[0114] S202. Determine the data points with a lane distance greater than the first preset lane width and less than the second preset lane width as the data points of the lane adjacent to the lane where the vehicle is located according to the lane distance, the first preset lane width, and the second preset lane width.

[0115] Continuing with the example in S201, assume that the second preset lane width w2 is 1.5w, i.e., 3.5m. If the lane distance d between the obstacle and the vehicle is 2m, since the lane distance d of this data point is greater than the first preset lane width w1 and less than the second preset lane width w2, it indicates that this data point is located in the adjacent lane of the vehicle's lane, that is, the left lane or the right lane of the vehicle's lane. Then, determine that this data point is a data point in the adjacent lane of the vehicle's lane.

[0116] S203. Generate the third position information of the obstacle envelope point according to the two-dimensional coordinates of the data points in the vehicle's lane, the data points in the adjacent lane of the vehicle's lane, and the obstacle envelope point, according to the positive and negative values of the two-dimensional coordinates.

[0117] It can be understood that after S201 and S202, the data points in the obstacle envelope point can be classified into the data points in the vehicle's lane and the data points in the adjacent lane of the vehicle's lane, that is, the current lane, the left lane, and the right lane. Since the vehicle needs to observe and judge the vehicles before and after itself when making road decisions (such as lane change), it is also necessary to further classify the data points according to the positive and negative values of the two-dimensional coordinates, and finally generate the third position information of the obstacle envelope point. Through this accurate data point classification method, it is convenient for the vehicle to make more accurate avoidance strategies (such as accelerating, decelerating, and lane changing), improving the safety and stability of vehicle driving.

[0118] In an implementable manner, the specific steps for further classifying the data points according to the positive and negative values of the two-dimensional coordinates of the obstacle envelope point include:

[0119] For the data points in the vehicle's lane, according to the two-dimensional coordinates of the obstacle envelope point, determine the data points with positive ordinate values in the two-dimensional coordinates as the front obstacles in the vehicle's lane and the data points with positive ordinate values in the two-dimensional coordinates as the rear obstacles in the vehicle's lane.

[0120] For example, if the two-dimensional coordinates of the data point in the vehicle's lane are (1, 3), since the ordinate of this two-dimensional coordinate is 3, which is a positive value, and since the vehicle coordinate system is set as a right-handed coordinate system with the ground at the center of the rear axle of the vehicle as the origin, the positive direction of the X-axis on the right side of the vehicle, and the positive direction of the y-axis in the front of the vehicle in this application, then determine this obstacle as the front obstacle in the vehicle's lane; if the two-dimensional coordinates of the data point in the vehicle's lane are (1, -3), since the ordinate of this two-dimensional coordinate is -3, which is a negative value, then determine this obstacle as the rear obstacle in the vehicle's lane.

[0121] Further, for the data points in the adjacent lanes of the lane where the vehicle is located, first, according to the two-dimensional coordinates of the obstacle envelope points, the data points with positive ordinate and positive abscissa in the two-dimensional coordinates are determined as the front obstacles in the adjacent right lane of the lane where the vehicle is located; then, the data points with positive ordinate and negative abscissa in the two-dimensional coordinates are determined as the front obstacles in the adjacent left lane of the lane where the vehicle is located; then, the data points with negative ordinate and positive abscissa in the two-dimensional coordinates are determined as the rear obstacles in the adjacent right lane of the lane where the vehicle is located; finally, the data points with negative ordinate and negative abscissa in the two-dimensional coordinates are determined as the rear obstacles in the adjacent left lane of the lane where the vehicle is located.

[0122] Next, for example, if the two-dimensional coordinates of the data points in the adjacent lane of the lane where the vehicle is located are (1, 3), since the abscissa of this two-dimensional coordinate is 1 and the ordinate is 3, that is, both are positive, then this data point is determined as the front obstacle in the adjacent right lane of the lane where the vehicle is located; and if the two-dimensional coordinates of the data points in the adjacent lane of the lane where the vehicle is located are (-1, 3), since the abscissa of this two-dimensional coordinate is -1 and the ordinate is 3, that is, the ordinate is positive and the abscissa is negative, then this data point is determined as the front obstacle in the adjacent left lane of the lane where the vehicle is located; if the two-dimensional coordinates of the data points in the adjacent lane of the lane where the vehicle is located are (1, -3), since the abscissa of this two-dimensional coordinate is 1 and the ordinate is -3, that is, the ordinate is negative and the abscissa is positive, then this data point is determined as the rear obstacle in the adjacent right lane of the lane where the vehicle is located; finally, if the two-dimensional coordinates of the data points in the adjacent lane of the lane where the vehicle is located are (-1, -3), since the abscissa of this two-dimensional coordinate is -1 and the ordinate is -3, that is, the ordinate is negative and the abscissa is negative, then this data point is determined as the rear obstacle in the adjacent left lane of the lane where the vehicle is located.

[0123] It can be understood that in this way, the data points can be classified into six categories: left front obstacles, left rear obstacles, middle front obstacles, middle rear obstacles, right front obstacles, and right rear obstacles according to the lanes, and the relative position of the obstacles to the vehicle can be determined more accurately. When the vehicle needs to make a road decision, it is not necessary to traverse all obstacles for judgment, but can directly process the obstacles related to the current road decision, reducing unnecessary calculations and improving the real-time response ability.

[0124] In an implementable way, since the obstacle envelope points contain multiple data points, although a certain number of redundant data points can be deleted after filtering, in order to reduce the processing complexity of the data points, it is also necessary to judge the number of data points in the obstacle envelope points before modeling. The specific steps are as follows:

[0125] First, based on the third position information of the obstacle envelope points, determine whether the number of data points in the obstacle envelope points is greater than a preset number; then, if the number of data points in the obstacle envelope points is greater than the preset number, sort all the data points in the obstacle envelope points in ascending order of lane distance, and determine the position information corresponding to the first preset number of data points as the third position information of the obstacle envelope points.

[0126] Among them, the preset number is mainly used to limit the number of data points participating in the modeling in the obstacle envelope points, so as to reduce the modeling calculation complexity and ensure the accuracy of the obstacle model. In practical applications, it can be set according to specific situations, and the embodiments of the present application do not make specific limitations here.

[0127] For example, if according to the third position information of the obstacle envelope points, it is obtained that there are 3 data points in the obstacle envelope points, and their position information is respectively an obstacle in front of the vehicle in the vehicle's own lane with a lane distance of 1m, an obstacle in front of the adjacent left lane of the vehicle with a lane distance of 3m, and an obstacle in front of the adjacent left lane of the vehicle with a lane distance of 2m, and the preset number is 1, then only the obstacle in front of the vehicle in the vehicle's own lane with a lane distance of 1m is retained.

[0128] Optionally, after modeling the obstacle according to the third position information of the obstacle envelope points, the obstacle model can be used to quickly make decisions on vehicle behavior, and its decision-making process can be:

[0129] First, determine whether the conditions for changing lanes to the adjacent left lane are met, that is, there is no obstacle (or there is a high-speed obstacle) in front of the adjacent left lane and no obstacle (or there is a low-speed obstacle) behind the adjacent left lane. If it is met, change lanes and overtake to the adjacent left lane; if it is not met, determine whether the conditions for changing lanes to the adjacent right lane are met, that is, there is no obstacle (or there is a high-speed obstacle) in front of the adjacent right lane and no obstacle (or there is a high-speed obstacle) behind the adjacent right lane. If it is met, change lanes and overtake to the adjacent right lane; if it is not met, keep driving in the current lane.

[0130] Figure 3 It is a schematic structural diagram of the obstacle modeling device provided by the embodiment of the present application; as Figure 3 shown, the obstacle modeling device 30 provided in this embodiment includes:

[0131] A determination module 301, configured to project the obstacle envelope points onto the vehicle body coordinate system for each obstacle according to the obstacle envelope point information and lane information collected by the vehicle's data acquisition device, and determine the first position information of the obstacle envelope points, where the obstacle envelope point information includes at least one data point information constituting the outer boundary of the obstacle;

[0132] The calculation module 302 is configured to calculate the lane distance between a data point and a vehicle according to the first position information of the obstacle envelope point and the lane information for each data point;

[0133] The first generation module 303 is configured to filter the data points according to the lane distance and the lane information, and generate the second position information of the obstacle envelope point;

[0134] The second generation module 304 is configured to classify the data points according to different lanes according to the lane distance, the lane information, and the second position information of the obstacle envelope point, and generate the third position information of the obstacle envelope point;

[0135] The processing module 305 performs obstacle modeling on the obstacle according to the third position information of the obstacle envelope point.

[0136] In a possible implementation manner, the lane information includes the lane width and the lane center line point information, and the lane width includes a first preset width and a second preset width;

[0137] The calculation module 302 is specifically configured to:

[0138] Calculate the relative distance between the data point and the lane center line point position according to the first position information of the obstacle envelope point and the lane center line point information;

[0139] Determine the relative distance as the lane distance between the data point and the vehicle.

[0140] In a possible implementation manner, the determination module 301 is specifically configured to:

[0141] Determine the coordinates of the obstacle envelope point according to the obstacle envelope point information;

[0142] Project the coordinates of the obstacle envelope point onto the vehicle body coordinate system to obtain the two-dimensional coordinates of the obstacle envelope point;

[0143] Determine the first position information of the obstacle envelope point according to the two-dimensional coordinates of the obstacle envelope point.

[0144] In a possible implementation manner, the second generation module 304 is specifically configured to:

[0145] Determine the data points with a lane distance less than the first preset lane width as the data points in the lane where the vehicle is located according to the lane distance and the first preset lane width;

[0146] Determine the data points with a lane distance greater than the first preset lane width and less than the second preset lane width as the data points in the adjacent lane of the lane where the vehicle is located according to the lane distance, the first preset lane width, and the second preset lane width;

[0147] Generate third position information of the obstacle envelope points according to the two-dimensional coordinates of the data points in the lane where the vehicle is located, the data points in the adjacent lanes of the lane where the vehicle is located, and the obstacle envelope points, based on the positive and negative values of the two-dimensional coordinates.

[0148] In a possible implementation manner, the second generation module 304 is specifically configured to:

[0149] For the data points in the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinates in the two-dimensional coordinates as the front obstacles in the lane where the vehicle is located and the data points with positive ordinates in the two-dimensional coordinates as the rear obstacles in the lane where the vehicle is located;

[0150] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinates and positive abscissas in the two-dimensional coordinates as the front obstacles in the adjacent right lane of the lane where the vehicle is located;

[0151] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with positive ordinates and negative abscissas in the two-dimensional coordinates as the front obstacles in the adjacent left lane of the lane where the vehicle is located;

[0152] For the data point obstacles in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacles, determine the data point obstacles with negative ordinates and positive abscissas in the two-dimensional coordinates as the rear obstacles in the adjacent right lane of the lane where the vehicle is located;

[0153] For the data points in the adjacent lanes of the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determine the data points with negative ordinates and negative abscissas in the two-dimensional coordinates as the rear obstacles in the adjacent left lane of the lane where the vehicle is located.

[0154] In a possible implementation manner, the first generation module 303 is specifically configured to:

[0155] Delete the data points with lane distances greater than the second preset lane width according to the lane distance and the second preset lane width, and generate second position information of the obstacle envelope points.

[0156] In a possible implementation manner, the obstacle modeling device further includes a judgment module. Before performing obstacle modeling on the obstacle according to the third position information of the obstacle envelope points, the judgment module is used to:

[0157] According to the third position information of the obstacle envelope points, judge whether the number of data points in the obstacle envelope points is greater than a preset number;

[0158] If the number of data points in the obstacle envelope points is greater than the preset number, then all the data points in the obstacle envelope points are sorted in ascending order according to the lane distance, and the position information corresponding to the first preset number of data points is determined as the third position information of the obstacle envelope points.

[0159] The obstacle modeling device provided in this embodiment can execute the method provided in the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0160] Figure 4 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application; as Figure 4 shown, the electronic device 40 provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. Among them, the processor 401, the memory 402, and the communication component 403 are connected through a bus 404.

[0161] In a specific implementation process, at least one processor 401 executes computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0162] The specific implementation process of the processor 401 can be referred to the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0163] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.

[0164] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0165] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0166] This application also provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the processor executes the computer-executable instructions, the above method is implemented.

[0167] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0168] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0169] The division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in an electrical, mechanical, or other form.

[0170] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0172] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

[0173] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, and other various media that can store program codes.

[0174] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. An obstacle modeling method, characterized in that, Including: For each obstacle, based on the obstacle envelope point information and lane information collected by the vehicle's data acquisition device, project the obstacle envelope points onto the vehicle body coordinate system to determine the first position information of the obstacle envelope points, where the obstacle envelope point information includes at least one data point information constituting the outer boundary of the obstacle; For each data point, calculate the lane distance between the data point and the vehicle based on the first position information of the obstacle envelope points and the lane information; Filter the data points according to the lane distance and the lane information to generate the second position information of the obstacle envelope points; Classify the data points according to different lanes based on the lane distance, the lane information, and the second position information of the obstacle envelope points to generate the third position information of the obstacle envelope points; Perform obstacle modeling on the obstacle based on the third position information of the obstacle envelope points.

2. The method according to claim 1, wherein The lane information includes the lane width and the lane center line point information, and the lane width includes a first preset width and a second preset width; The calculating the lane distance between the data point and the vehicle based on the first position information of the obstacle envelope points and the lane information includes: Calculate the relative distance between the data point and the lane center line point position based on the first position information of the obstacle envelope points and the lane center line point information; Determine the relative distance as the lane distance between the data point and the vehicle.

3. The method according to claim 1, wherein The projecting the obstacle envelope points onto the vehicle body coordinate system to determine the first position information of the obstacle envelope points based on the obstacle envelope point information and lane information collected by the vehicle's image acquisition device includes: Determine the coordinates of the obstacle envelope points according to the obstacle envelope point information; Project the coordinates of the obstacle envelope points onto the vehicle body coordinate system to obtain the two-dimensional coordinates of the obstacle envelope points; Determine the first position information of the obstacle envelope points according to the two-dimensional coordinates of the obstacle envelope points.

4. The method according to any one of claims 1 to 3, characterized in that, The classifying the data points according to different lanes based on the lane distance, the lane information, and the second position information of the obstacle envelope points to generate the third position information of the obstacle envelope points includes: Determine the data points with a lane distance less than the first preset lane width as the data points in the vehicle's lane according to the lane distance and the first preset lane width; Determine the data points with a lane distance greater than the first preset lane width and less than the second preset lane width as the data points in the adjacent lane of the vehicle's lane according to the lane distance, the first preset lane width, and the second preset lane width; Generate the third position information of the obstacle envelope points according to the data points in the vehicle's lane, the data points in the adjacent lane of the vehicle's lane, and the two-dimensional coordinates of the obstacle envelope points according to the positive and negative values of the two-dimensional coordinates.

5. The method according to claim 4, characterized in that, Generating third position information of the obstacle envelope points according to the data points of the lane where the vehicle is located, the data points of the lanes adjacent to the lane where the vehicle is located, and the two-dimensional coordinates of the obstacle envelope points, according to the positive and negative values of the two-dimensional coordinates, includes: For the data points in the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determining the data points with positive ordinate values in the two-dimensional coordinates as the front obstacles in the lane where the vehicle is located and the data points with positive ordinate values in the two-dimensional coordinates as the rear obstacles in the lane where the vehicle is located; For the data points in the lanes adjacent to the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determining the data points with positive ordinate values and positive abscissa values in the two-dimensional coordinates as the front obstacles in the adjacent right lane of the lane where the vehicle is located; For the data points in the lanes adjacent to the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determining the data points with positive ordinate values and negative abscissa values in the two-dimensional coordinates as the front obstacles in the adjacent left lane of the lane where the vehicle is located; For the data points in the lanes adjacent to the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle, determining the data points with negative ordinate values and positive abscissa values in the two-dimensional coordinates as the rear obstacles in the adjacent right lane of the lane where the vehicle is located; For the data points in the lanes adjacent to the lane where the vehicle is located, according to the two-dimensional coordinates of the obstacle envelope points, determining the data points with negative ordinate values and negative abscissa values in the two-dimensional coordinates as the rear obstacles in the adjacent left lane of the lane where the vehicle is located.

6. The method according to claim 1 or 2, characterized in that, Filtering the data points according to the lane distance and the lane information to generate second position information of the obstacle envelope points, includes: Deleting the data points with the lane distance greater than the second preset lane width according to the lane distance and the second preset lane width to generate second position information of the obstacle envelope points.

7. The method according to claim 1, wherein Before performing obstacle modeling on the obstacle according to the third position information of the obstacle envelope points, the method further includes: Judging whether the number of data points in the obstacle envelope points is greater than a preset number according to the third position information of the obstacle envelope points; If the number of data points in the obstacle envelope points is greater than the preset number, sorting all the data points in the obstacle envelope points in ascending order of the lane distance, and determining the position information corresponding to the first preset number of data points as the third position information of the obstacle envelope points.

8. An obstacle modeling device, characterized in that Includes: A determining module, configured to project the obstacle envelope points onto the vehicle body coordinate system according to the obstacle envelope point information and the lane information collected by the data acquisition device of the vehicle for each obstacle, and determine the first position information of the obstacle envelope points, where the obstacle envelope point information includes at least one data point information constituting the outer boundary of the obstacle; A calculation module, configured to calculate the lane distance between the data points and the vehicle according to the first position information of the obstacle envelope points and the lane information for each data point; A first generation module, configured to filter the data points according to the lane distance and the lane information, and generate second position information of the obstacle envelope points; A first generation module, configured to classify the data points according to different lanes according to the lane distance, the lane information, and the second position information of the obstacle envelope points, and generate third position information of the obstacle envelope points; A processing module, configured to perform obstacle modeling on the obstacle according to the third position information of the obstacle envelope points.

9. An electronic device, characterized in that, Comprising: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by the processor, they are used to implement the method according to any one of claims 1-7.

Images