Obstacle information determination method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application disclose an obstacle information determination method and device, electronic equipment and a storage medium. The method comprises: obtaining at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin; obtaining at least one obstacle identification condition, and identifying obstacle information of an obstacle within the preset range of the current vehicle based on each obstacle identification condition and each point cloud coordinate; wherein the obstacle identification condition comprises a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and a right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and a left adjacent point coordinate and a right adjacent point coordinate, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate. The accuracy of obstacle determination around the vehicle is improved, thereby improving the safety of vehicle driving.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of intelligent driving, and in particular to an obstacle information determination method and device, an electronic device, and a storage medium. BACKGROUND

[0002] With the rapid development of the automobile industry and the continuous improvement of people's living standards, cars have quickly entered ordinary families. Vehicle driving safety is attracting more and more widespread attention.

[0003] Currently, during driving, the driver often directly observes the obstacles around the vehicle, or the driver determines the obstacles on the left and right sides of the vehicle by observing the rearview mirror of the vehicle, and then the vehicle drives according to the driver's instructions. However, this artificial determination method is easily affected by the subjective experience or environmental factors of the driver, and the safety of vehicle driving is relatively low. SUMMARY

[0004] The present application provides an obstacle information determination method and device, an electronic device, and a storage medium to improve the accuracy of determining obstacles around the vehicle and thus improve the safety of vehicle driving.

[0005] In a first aspect, an embodiment of the present application provides an obstacle information determination method, which comprises:

[0006] obtaining at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin;

[0007] obtaining at least one obstacle recognition condition, and recognizing obstacle information of obstacles within the preset range of the current vehicle based on each obstacle recognition condition and each point cloud coordinate; wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and a right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and a left adjacent point coordinate and a right adjacent point coordinate, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate.

[0008] Optionally, the obstacle information comprises the number of obstacles, the obstacle number, the number of boundary points of the obstacle, the boundary point number of the obstacle, and the boundary point coordinates of the obstacle.

[0009] Optionally, the obtaining at least one point cloud data within a preset range of a current vehicle comprises:

[0010] scanning the preset range of the current vehicle based on a preset radar sensor, and obtaining each initial point cloud coordinate in the scanning result;

[0011] Respectively, the initial point cloud coordinates are pre-processed to obtain each target point cloud coordinate within the preset range of the current vehicle.

[0012] Optionally, the pre-processing of the initial point cloud coordinates to obtain the target point cloud coordinates within the preset range of the current vehicle includes:

[0013] A preset coordinate storage matrix is obtained, each column of coordinate data in the preset coordinate storage matrix is shifted right by one column, and the corresponding column of coordinate data in the initial point cloud coordinates is stored in the first column of the preset coordinate storage matrix to obtain a coordinate adjustment matrix.

[0014] The coordinate data in the coordinate adjustment matrix is sorted according to a preset sorting rule to obtain a coordinate sorting matrix.

[0015] At least two columns of coordinate data in the coordinate sorting matrix are obtained, the row coordinate mean of each row of coordinate data in the at least two columns of coordinate data is determined, and each row coordinate mean is taken as the corresponding point cloud coordinate in the target point cloud coordinate.

[0016] Optionally, the obtaining of at least one obstacle recognition condition and the identification of the obstacle information of the obstacle within the preset range of the current vehicle based on each obstacle recognition condition and each point cloud coordinate includes:

[0017] For any point cloud coordinate, if the distance between the current point cloud coordinate and the current vehicle meets the detection distance condition, a current first adjacent distance between the current point cloud coordinate and the right adjacent point of the current point cloud coordinate is obtained.

[0018] If the current first adjacent distance does not meet the first adjacent distance condition, the number of obstacles, the number of obstacle numbers, the number of boundary points, and the number of boundary point numbers are accumulated, and the boundary point coordinate is determined based on the current point cloud coordinate.

[0019] Optionally, the obtaining of at least one obstacle recognition condition and the identification of the obstacle information of the obstacle within the preset range of the current vehicle based on each obstacle recognition condition and each point cloud coordinate further includes:

[0020] If the current first adjacent distance meets the first adjacent distance condition, a current adjacent angle between the current point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate of the current point cloud coordinate is obtained.

[0021] If the current adjacent angle does not meet the adjacent angle condition, the current boundary point number of the obstacle is matched with a preset number threshold; if the current boundary point number is within the preset number threshold range, the boundary point number is accumulated, and the boundary point coordinates are determined; if the current boundary point number is not within the preset number threshold range, the obstacle number, the obstacle number, the boundary point number, and the boundary point number are accumulated, and the boundary point coordinates are determined.

[0022] Optionally, the at least one obstacle identification condition is obtained, and based on each of the obstacle identification conditions and each of the point cloud coordinates, obstacle information of an obstacle within a preset range of the current vehicle is identified, and the method further comprises:

[0023] If the current adjacent angle meets the adjacent angle condition, a current second adjacent distance between the current point cloud coordinate and a left adjacent point of the current point cloud coordinate is obtained.

[0024] If the current second adjacent distance does not meet the second adjacent condition, the boundary point number is accumulated.

[0025] If the current second adjacent distance meets the second adjacent condition, and it is determined that the current point cloud data identification is completed, other point cloud coordinates are traversed, and the obstacle number, the obstacle number, the boundary point number, the boundary point number, and the boundary point coordinates of each obstacle identified are stored.

[0026] Optionally, after identifying the obstacle information of the obstacle within the preset range of the current vehicle, the method further comprises:

[0027] A global coordinate system is obtained, and based on the boundary point coordinates of each of the boundary points in the local coordinate system and a preset coordinate conversion method, global boundary point coordinates of each of the boundary points in the global coordinate system are determined.

[0028] Global boundary point coordinates within the preset range of the current vehicle at a next time are determined, and based on a comparison result of a global coordinate difference between the global boundary point coordinates at the current time and the global boundary point coordinates at the next time and a preset coordinate threshold, a boundary point type of each of the boundary points is determined.

[0029] Optionally, the boundary point type comprises a dynamic boundary point and a dynamic boundary point.

[0030] Correspondingly, after determining the boundary point type of each of the boundary points, the method further comprises:

[0031] if the boundary point type is a dynamic boundary point, updating a global boundary point coordinate of each of the boundary points in real time, and updating a driving track of the current vehicle in real time based on the real-time updated boundary points until the boundary point is not within the detection distance condition range, or the current vehicle passes through the boundary point;

[0032] if the boundary point type is a static boundary point, determining a driving track of the current vehicle based on each of the boundary points until the boundary point is not within the detection distance condition range, or the current vehicle passes through the boundary point.

[0033] In a second aspect, an embodiment of the present application further provides an obstacle information determination device, which comprises:

[0034] a point cloud data acquisition module, configured to acquire at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin;

[0035] an obstacle information identification module, configured to acquire at least one obstacle identification condition, and identify obstacle information of an obstacle within the preset range of the current vehicle based on each of the obstacle identification conditions and each of the point cloud coordinates; wherein the obstacle identification condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates respectively, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.

[0036] In a third aspect, an embodiment of the present application further provides an electronic device, which comprises:

[0037] one or more processors;

[0038] a storage device, configured to store one or more programs,

[0039] when the one or more programs are executed by the one or more processors, the one or more processors implement the obstacle information determination method provided by any embodiment of the present application.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the obstacle information determination method provided by any embodiment of the present application.

[0041] The technical scheme of the embodiment obtains at least one point cloud data in a preset range of a current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin, so that more accurate radar data is obtained to provide necessary information for automatic driving vehicle to slow down and avoid obstacles and to plan a path for obstacle bypassing, at least one obstacle identification condition is obtained, and obstacle information of obstacles in the preset range of the current vehicle is identified based on each obstacle identification condition and each point cloud coordinate, wherein the obstacle identification condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, the scanned point cloud data is identified through the plurality of obstacle identification conditions, the obstacle information around the vehicle is determined, and the accuracy of obstacle identification is improved, so that the safety of vehicle driving is improved. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical scheme of the exemplary embodiments of the present application, the drawings needed in the description of the embodiments are briefly introduced as follows. Obviously, the drawings introduced are only a part of the drawings of the embodiments to be described by the present application, and not all the drawings. Those skilled in the art can obtain other drawings according to these drawings without creating creative labor.

[0043] Figure 1 is a flowchart of the obstacle information determination method provided by the first embodiment of the present application;

[0044] Figure 2 is a structure diagram of the local coordinate system provided by the first embodiment of the present application;

[0045] Figure 3 is a flowchart of the obstacle information determination method provided by the second embodiment of the present application;

[0046] Figure 4 is a structure diagram of the global coordinate system provided by the second embodiment of the present application;

[0047] Figure 5 is a structure diagram of the obstacle information determination device provided by the third embodiment of the present application;

[0048] Figure 6 is a structure diagram of the electronic device provided by the fourth embodiment of the present application. DETAILED DESCRIPTION

[0049] The application will be described in further detail below with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are intended to be illustrative only and not limiting of the application. It is also to be understood that the terminology used herein is for the purpose of describing the specific embodiments only and is not intended to be limiting.

[0050] Embodiment one

[0051] Figure 1 A flow chart of an obstacle information determination method provided for embodiment one of the application, the embodiment can be applied to determine the obstacles around the vehicle when the vehicle is automatically driving; and is more suitable for determining the obstacles around the vehicle when the camera is not used or is damaged or has limited functions. The method can be executed by an obstacle information determination device, which can be realized by software and / or hardware.

[0052] Before the technical solutions of the embodiments of the application are introduced, the application scenarios of the technical solutions are exemplarily introduced. Of course, the following application scenarios are only optional application scenarios, and the embodiments of the application can also be implemented in other application scenarios, and the embodiments of the application do not limit the application scenarios of the technical methods. Specifically, the application scenarios include: at present, during driving, the driver often directly observes the obstacles around the vehicle, or the driver determines the obstacles on the left and right sides of the vehicle by observing the rearview mirror of the vehicle, and then the vehicle drives according to the indication of the driver. However, this artificial determination method is easily affected by the subjective experience of the driver or environmental factors, and the safety of the vehicle driving is relatively low. Moreover, during automatic driving, the obstacle information around the vehicle is mostly obtained based on the camera installed on the vehicle, but the camera can be damaged or have limited functions, so that the vehicle controller cannot obtain the obstacle information around the vehicle, thereby causing a great safety risk of the automatic driving of the vehicle.

[0053] In view of the above technical problems, the technical solutions in the embodiments calculate the obstacle state information around the automatic driving vehicle based on the radar data obtained, to provide necessary information for the automatic driving vehicle to slow down and avoid obstacles and to plan a path around the obstacles.

[0054] Based on the above technical ideas, the technical scheme of the embodiment obtains at least one point cloud data in a preset range of the current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin; thereby obtaining more accurate radar data to provide necessary information for automatic driving vehicle speed reduction obstacle avoidance and obstacle bypass planning path; at least one obstacle recognition condition is obtained, and based on each obstacle recognition condition and each point cloud coordinate, obstacle information of obstacles in the preset range of the current vehicle is recognized; wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate; the scanned point cloud data is identified through the plurality of obstacle recognition conditions to determine the obstacle information around the vehicle, thereby improving the accuracy of obstacle recognition and improving the safety of vehicle driving.

[0055] As shown in the method specifically comprises the following steps: Figure 1

[0056] S110, at least one point cloud data in a preset range of the current vehicle is obtained.

[0057] In the embodiment, the vehicle around can be detected based on various radar detection devices, so as to obtain the point cloud data in the preset range around the vehicle.

[0058] Optionally, the method of obtaining point cloud data can comprise: based on a preset radar sensor, scanning the preset range of the current vehicle, and obtaining each initial point cloud coordinate in the scanning result.

[0059] The installation position of the preset radar sensor on the current vehicle determines the sensing range and capability of the sensor obstacle detection, in order to reduce the shielding as much as possible and increase the detection range of the laser radar. Optionally, it can be installed above the roof of the current vehicle or under the vehicle. The installation position of the above-mentioned radar sensor is only an exemplary installation position, and the embodiment does not limit the installation position of the radar sensor. The type of the preset radar sensor can be a laser radar, a vehicle millimeter wave radar, and of course other types of radar sensors.

[0060] Specifically, the radar sensor continuously scans the vehicle around and stores the scanned point cloud data in real time. The scanning angle of the radar sensor can be 360 degrees, and of course it can also be set in real time according to the environment of the current vehicle. In the embodiment, the stored point cloud data can include point cloud coordinates in a local coordinate system with the current vehicle as the origin.

[0061] Exemplarily as Figure 2 ​As shown, taking the point cloud information of the current vehicle front ± 45° as an example, the data density of the point cloud data is defined as FSP_0~90 in sequence with every 1 degree as an interval. Each point cloud data packet can include (X, Y) coordinate information based on the local coordinate system of the current vehicle. Specifically, the origin of the local coordinate system is the center point of the current vehicle, and the X positive direction is the direction of the current vehicle, and the Y direction is the left direction of the current vehicle.

[0062] Because the initial point cloud data of radar scanning may have single-frame false positives or multi-frame jitter, before identifying the obstacle information based on the initial point cloud data, the initial point cloud data needs to be preprocessed to eliminate these accidental factors as much as possible, thereby improving the accuracy of obstacle information identification. Therefore, after obtaining the initial point cloud data scanned by the radar sensor, the technical solution of the embodiment also pre-processes each initial point cloud coordinate to obtain each target point cloud coordinate within the preset range of the current vehicle.

[0063] Optionally, the method for pre-processing the initial point cloud data can include: obtaining a preset coordinate storage matrix, shifting each column of coordinate data in the preset coordinate storage matrix by one column to the right, and storing the corresponding column of coordinate data in the initial point cloud coordinate in the first column of the preset coordinate storage matrix to obtain a coordinate adjustment matrix; sorting the coordinate data in the coordinate adjustment matrix according to a preset sorting rule to obtain a coordinate sorting matrix; obtaining at least two columns of coordinate data in the coordinate sorting matrix, determining the row coordinate mean of each row of coordinate data in the at least two columns of coordinate data, and taking each row coordinate mean as a corresponding point cloud coordinate in the target point cloud coordinate.

[0064] In the embodiment, the above 90 point cloud data is taken as an example to exemplarily introduce the data preprocessing method. Specifically, the initial point cloud data of the current vehicle FSP_0~FSP_90 at the current time is read and stored in a newly created initial point cloud data matrix. The matrix name of the initial point cloud data matrix can be FSP_n_XY, and the matrix is a 90x2 coordinate matrix. Specifically, the initial coordinate data information in FSP_n_XY is shown in the following table:

[0065] Table 1 Initial coordinate data information table

[0066] FSP_0_X FSP_0_Y FSP_1_X FSP_1_Y … … FSP_90_X FSP_90_Y

[0067] The preprocessing method of the embodiment is to eliminate single-frame false positives while smoothing multi-frame jitter, so it needs to follow the principle that error generation and distribution follow normal distribution, thereby eliminating error points through median mean filtering.

[0068] Before the data is preprocessed, a data storage matrix is established in advance for storing the point cloud data after data preprocessing at the previous time. Specifically, in order to facilitate data preprocessing of the X coordinate data and the Y coordinate data in the coordinate data at the same time, the data storage matrix is divided into an X coordinate data storage sub-matrix and a Y coordinate data storage sub-matrix. Specifically, the matrix name of the X coordinate data storage sub-matrix can be FSP_save_X, and the matrix name of the Y coordinate data storage sub-matrix can be FSP_save_Y. The size of the data storage matrix is introduced taking the X coordinate data storage sub-matrix as an example. The matrix size of the X coordinate data storage sub-matrix is a 90xN matrix, where the size of N is the key of the median filtering. In order to ensure the timeliness and accuracy of the data preprocessing, the value of N is not less than 10 and not more than 50 in principle; in the example, N can be 30 in the technical solution of the embodiment, and N can also be other values, and the value of N is not limited in the embodiment.

[0069] The method of processing the coordinate data in the X coordinate data storage sub-matrix is used to introduce the data preprocessing method of the initial point cloud data, for example. Specifically, each column of coordinate data in the X coordinate data storage sub-matrix is moved one column to the right, and each coordinate data in the first column of coordinate data, i.e., the X column of coordinate data, in the initial point cloud data matrix is stored in the X coordinate data storage sub-matrix to obtain the coordinate data after data adjustment.

[0070] Further, the coordinate data after data adjustment in the X coordinate data storage sub-matrix is sorted. Optionally, for each row of data, each row of data can be sorted in descending order to obtain the sorted coordinate data. The beneficial effect of sorting the coordinate data in the embodiment is that the invalid coordinate data in the current matrix can be screened out according to the sorted coordinate data, the reliability of the data is improved, and the accuracy of the obstacle information recognition is improved.

[0071] Further, at least one column of data in the sorted coordinate data in the X coordinate data storage sub-matrix is obtained. Optionally, the obtained mode can be to obtain at least one column in the middle, or to randomly obtain at least one column. In the embodiment, in order to obtain reliable data, the column coordinate data of the middle preset number of columns of the X coordinate data storage sub-matrix can be selected, the mean value of each row of coordinate data in the selected column coordinate data is calculated, and each row of coordinate mean value is taken as the corresponding point cloud coordinate in the target point cloud coordinate.

[0072] For example, the first column information of the preprocessed FSP_n_XY matrix is introduced as an example:

[0073] 1) For the coordinate data of the current frame, each column of data in the FSP_save_X matrix is moved one column to the right, and the first column of data is set to 0.

[0074] 2) The coordinate data in the first column of the FSP_n_XY matrix is stored in the first column of the FSP_save_X matrix, and the data update input is completed.

[0075] 3) The coordinate data in each row of the FSP_save_X matrix is arranged in descending order or ascending order, and is filled in the calculation matrix FSP_n_X in order of size. The sorting of the coordinate data in this embodiment is to facilitate the screening of invalid coordinate data, and the storage of the sorted data in the FSP_n_X matrix is to distinguish between screened data and unfiltered data.

[0076] 4) The row coordinate average of each row of coordinate data in the middle M columns of the FSP_n_X matrix is taken, and is filled in the first column of the FSP_n_XY matrix. The value of M relates to the stability and timeliness of the preprocessed data, and in this scheme, M is temporarily taken as 10, that is, the average of each row from the 11th column to the 20th column of the FSP_n_X calculation matrix.

[0077] 5) The first column information preprocessing of the FSP_n_XY matrix of the current frame is completed, and the processed data is updated to the FSP_save_X matrix, which facilitates the preprocessing of subsequent frame data.

[0078] It should be noted that the method of data preprocessing in this embodiment is introduced by taking the X coordinate data storage sub-matrix as an example, and the coordinate data in the Y coordinate data storage sub-matrix can also be preprocessed by the same method.

[0079] For example, the data preprocessing process of the second column information of the FSP_n_XY matrix includes:

[0080] 1) For the coordinate data of the current frame, the data in each column of the FSP_save_Y matrix is shifted one column to the right, and the data in the first column is set to 0.

[0081] 2) The coordinate data in the second column of the FSP_n_XY matrix is stored in the first column of the FSP_save_Y matrix, and the data update input is completed.

[0082] 3) The coordinate data in each row of the FSP_save_Y matrix is arranged in descending order or ascending order, and is filled in the calculation matrix FSP_n_Y in order of size. The sorting of the coordinate data in this embodiment is to facilitate the screening of invalid coordinate data, and the storage of the sorted data in the FSP_n_Y matrix is to distinguish between screened data and unfiltered data.

[0083] 4) Take the mean of the row coordinates of each row of the middle M columns of the FSP_n_Y matrix, and fill it into the second column of the FSP_n_XY matrix. The value of M affects the stability and timeliness of the preprocessed data. In this scheme, M is temporarily taken as 10, that is, the mean of each row of the 11th to 20th columns of the FSP_n_X calculation matrix is taken.

[0084] 5) Complete the second column information preprocessing of the FSP_n_XY matrix of the current frame, and update the processed data to the FSP_save_Y matrix for subsequent frame data preprocessing.

[0085] S120, obtain at least one obstacle recognition condition, and identify the obstacle information of the obstacles in the preset range of the current vehicle based on the obstacle recognition conditions and the point cloud coordinates.

[0086] In this embodiment, the obstacle recognition condition is used to identify the point cloud data in the above embodiment, and determine whether the target corresponding to the point cloud data is an obstacle.

[0087] In this embodiment, the obstacle information includes the number of obstacles, the obstacle number, the number of boundary points of the obstacle, the boundary point number of the obstacle, and the boundary point coordinates of the obstacle. The boundary point of the obstacle can be understood as the inflection point of the obstacle, that is, the point cloud scanned by the radar sensor during scanning around the vehicle.

[0088] The number of obstacle recognition conditions is multiple, so as to ensure the accuracy of the identification result. Specifically, the obstacle recognition condition includes a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and the left adjacent point coordinates and the right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.

[0089] It is worth noting that if the current point cloud coordinate is the rightmost starting point, there is no right adjacent point, and the distance between the point cloud coordinate and the right adjacent point is set to 0; correspondingly, if the current point cloud data is the leftmost end point, there is no left adjacent point, and the distance between the point cloud coordinate and the left adjacent point is set to 0. Moreover, because the starting point and the end point cannot form an angle, the adjacent angle of the point cloud coordinates corresponding to FSP_90 and FSP_0 is set to 180°.

[0090] Further, after obtaining each obstacle recognition condition, the obstacle information of the obstacles in the preset range of the current vehicle is identified based on each obstacle recognition condition and each point cloud coordinate.

[0091] Optionally, the identification method of the obstacle information of the obstacle in the preset range of the current vehicle comprises: for any point cloud coordinate, if the distance between the current point cloud coordinate and the current vehicle meets the detection distance condition, a current first adjacent distance between the current point cloud coordinate and the right adjacent point of the current point cloud coordinate is obtained; if the current first adjacent distance does not meet the first adjacent distance condition, the obstacle number, the obstacle number, the boundary point number, the boundary point number and the boundary point coordinate are determined based on the current point cloud coordinate.

[0092] Specifically, any point cloud coordinate scanned by the current vehicle is obtained, the current distance between the current point cloud coordinate and the vehicle is obtained, and then the current distance is matched with the preset detection distance condition. If the current distance meets the detection distance condition, that is, the distance is within the detection distance condition, it means that the point cloud data is within the identification range of the current vehicle for identifying obstacles. Further, the right adjacent point coordinate of the current point cloud coordinate is obtained, and the current first adjacent distance between the right adjacent point coordinate is obtained, and then the current first adjacent distance is matched with the preset first adjacent distance condition. If the current first adjacent distance does not meet the first adjacent condition, that is, the distance between the right adjacent point of the current point cloud coordinate and the current point cloud coordinate is not within the preset distance range, the current point cloud coordinate is determined as an obstacle, and the obstacle information of the obstacle is further updated. Specifically, the current point is the starting point of the obstacle boundary, the obstacle number is accumulated by 1, the obstacle number is added by 1 to be a new target obstacle number, the boundary point number is accumulated by 1, and the current point cloud coordinate is taken as the coordinate of the boundary point.

[0093] It should be noted that if the current point cloud coordinate is the rightmost point cloud coordinate, the current first adjacent distance between the current point cloud coordinate and the right adjacent point is 0 by default, that is, the current first adjacent distance does not meet the preset first adjacent distance condition, and the identification steps corresponding to the first adjacent distance condition are continued to be executed.

[0094] Optionally, if the current first adjacent distance meets the first adjacent distance condition, the current adjacent angle between the current point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate of the current point cloud coordinate is obtained; if the current adjacent angle does not meet the adjacent angle condition, the current boundary point number of the obstacle is matched with the preset number threshold; if the current boundary point number is within the preset number threshold, the boundary point number is accumulated, and the boundary point coordinate is determined; if the current boundary point number is not within the preset number threshold, the obstacle number, the obstacle number, the boundary point number, the boundary point number and the boundary point coordinate are accumulated.

[0095] Specifically, if the current first adjacent distance meets the first adjacent condition, i.e., the distance between the right adjacent point of the current point cloud coordinate and the current point cloud coordinate is within the preset distance range, the current point cloud coordinate is further identified as an obstacle based on other obstacle identification conditions. Specifically, the current adjacent angle between the current point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate of the current point cloud coordinate is obtained, and then the current adjacent angle is matched with the preset adjacent angle condition. If the current adjacent angle does not meet the adjacent angle condition, i.e., the angle of the current adjacent angle is not within the preset adjacent angle threshold range, the boundary point number of the boundary point in the identified obstacle is further obtained, and the boundary point number is matched with the preset number threshold. If the boundary point number is within the preset number threshold range, the boundary point number is continuously accumulated, and the current point cloud coordinate is determined as the boundary point coordinate corresponding to the new boundary point number. On the contrary, if the boundary point number is not within the preset number threshold range, the current point cloud coordinate is determined as a new obstacle, and the obstacle information of the obstacle is further updated. Specifically, the current point is the starting point of the obstacle boundary, the obstacle number is accumulated by 1, the obstacle number is increased by 1 to be a new target obstacle number, the boundary point number is accumulated by 1, and the current point cloud coordinate is taken as the coordinate of the boundary point.

[0096] It should be noted that if the current point cloud coordinate is the rightmost point cloud coordinate or the leftmost point cloud coordinate, the angle between the left adjacent point coordinate and the right adjacent point coordinate of the current point cloud coordinate is 180° by default, i.e., the current adjacent angle does not meet the preset adjacent angle condition, and the identification step corresponding to the condition that the adjacent angle does not meet the condition is continued.

[0097] Optionally, if the current adjacent angle meets the adjacent angle condition, the current second adjacent distance between the current point cloud coordinate and the left adjacent point of the current point cloud coordinate is obtained. If the current second adjacent distance does not meet the second adjacent condition, the boundary point number is accumulated. If the current second adjacent distance meets the second adjacent condition and it is determined that the current point cloud data identification is completed, the other point cloud coordinates are traversed, and the obstacle number, obstacle number, boundary point number, boundary point number and boundary point coordinate of each obstacle identified are stored.

[0098] Specifically, if the current adjacent angle meets the adjacent angle condition, i.e., the angle of the current adjacent angle is within the preset adjacent angle threshold range, the current point cloud coordinate is further identified as an obstacle based on other obstacle identification conditions. Specifically, the left adjacent point coordinate of the current point cloud coordinate is obtained, and the current second adjacent distance between the left adjacent point coordinate is obtained. Then, the current adjacent distance is matched with the preset second adjacent distance condition. If the current second adjacent distance does not meet the second adjacent condition, i.e., the distance between the right adjacent point of the current point cloud coordinate and the current point cloud coordinate is not within the preset distance range, the boundary point number of the boundary point in the identified obstacle is further obtained, and the boundary point number is added by 1. On the contrary, if the current second adjacent distance meets the second adjacent condition and there are other obstacle identification conditions, the current point cloud coordinate is further identified as an obstacle based on the other obstacle identification conditions. Optionally, if the current second adjacent distance meets the second adjacent condition and there are no other obstacle identification conditions, it is determined that the current point cloud data identification is completed.

[0099] It should be noted that if the current point cloud coordinate is the leftmost point cloud coordinate, the current second adjacent distance between the current point cloud coordinate and the left adjacent point is 0 by default, i.e., the current second adjacent distance does not meet the preset second adjacent distance condition, and the identification step corresponding to the condition that the second adjacent distance does not meet the condition is continued.

[0100] Further, each point cloud data is identified based on the above identification conditions, and the obstacle number, obstacle number, boundary point number, boundary point number and boundary point coordinate of each identified obstacle are stored. Specifically, the obstacle information of the current frame can be stored in the obstacle information matrix. In this scheme, the matrix size of the obstacle matrix is initially set to 30x7. Among them, in the row information of the obstacle information matrix, from the first row to the thirtieth row, each row respectively represents the corresponding information of the obstacle with the current number; in the column information of the obstacle information matrix, the first column represents the number ID of the obstacle, the second column represents the boundary point number of the corresponding obstacle, and the third column to the seventh column represent the information ID of each boundary point. Specifically, the obstacle information is shown in the following table:

[0101] Table 2 Obstacle information table

[0102] Obstacle number 1 Boundary point number 3 Boundary point 1 Boundary point 2 Boundary point 3 Obstacle number 2 Boundary point number 2 Boundary point 1 Boundary point 2 Obstacle number 3 Boundary point number 4 Boundary point 1 Boundary point 2 Boundary point 3 Boundary point 4 Obstacle number 4 Boundary point number 5 Boundary point 1 Boundary point 2 Boundary point 3 Boundary point 4 Boundary point 5 … … … … … … … Obstacle number 30

[0103] At this point, the obstacle information calculation is completed, and the vehicle controller can complete the obstacle avoidance function of the vehicle according to the obstacle information provided by the embodiment of the application.

[0104] The technical scheme of the embodiment obtains at least one point cloud data in a preset range of a current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin, so that more accurate radar data is obtained to provide necessary information for automatic driving vehicle deceleration obstacle avoidance and obstacle bypass planning path, at least one obstacle recognition condition is obtained, and obstacle information of obstacles in the preset range of the current vehicle is recognized based on each obstacle recognition condition and each point cloud coordinate, wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates. The scanned point cloud data is recognized through the plurality of obstacle recognition conditions to determine the obstacle information around the vehicle, and the accuracy of obstacle recognition is improved, thereby improving the safety of vehicle driving.

[0105] Embodiment two

[0106] Figure 3 A flowchart of an obstacle information determination method provided for the second embodiment of the application is provided. The embodiment increases "obtaining a global coordinate system, and determining global boundary point coordinates of each boundary point in the global coordinate system based on the boundary point coordinates of each boundary point in the local coordinate system and a preset coordinate conversion method" after "recognizing obstacle information of obstacles in the preset range of the current vehicle" in the above-mentioned embodiments. The explanations of the same or corresponding terms in the above-mentioned embodiments are not repeated here. See Figure 3 The obstacle information determination method provided by the embodiment comprises:

[0107] S210, obtaining at least one point cloud data in a preset range of a current vehicle.

[0108] S220, obtaining at least one obstacle recognition condition, and recognizing obstacle information of obstacles in the preset range of the current vehicle based on each obstacle recognition condition and each point cloud coordinate.

[0109] S230, obtaining a global coordinate system, and determining global boundary point coordinates of each boundary point in the global coordinate system based on the boundary point coordinates of each boundary point in the local coordinate system and a preset coordinate conversion method.

[0110] In the embodiment of the application, sometimes the appearance of the obstacle will hinder the current vehicle from driving according to the original planned route, but if the current vehicle modifies the original planned route to bypass the obstacle, the current vehicle can also continue to drive. Of course, to complete the bypass of the current vehicle, the coordinate position of the obstacle needs to be determined to assist the current vehicle in planning the bypass route.

[0111] In the embodiment, the coordinate position of the obstacle is the coordinate position of the obstacle in the global coordinate system in which the current route is located, rather than the coordinate position in the local coordinate system in which the current vehicle is located.

[0112] Optionally, the method for obtaining the coordinate position of the obstacle in the global coordinate system can comprise: obtaining the global coordinate system, and determining the global boundary point coordinates of each boundary point in the global coordinate system based on the boundary point coordinates of each boundary point in the local coordinate system and the preset coordinate conversion method.

[0113] Specifically, the global coordinate system is obtained in advance, as shown in the following table: Figure 4 The global coordinate system can be taken as the origin point of the starting point of the route on which the current vehicle is located, the positive direction of the X axis is the initial driving direction of the vehicle, and the left side of the vehicle when the vehicle is initially driving is the positive direction of the Y axis. In other words, the positive directions of the X axis and the Y axis of the global coordinate system are the same.

[0114] At the current time, the local coordinate system in which the current vehicle is located is obtained, the lateral distance and the longitudinal distance between the origin point of the local coordinate system and the origin point of the global coordinate system are determined, and the direction angle between the X axis direction of the local coordinate system and the X axis direction of the global coordinate system is determined. The coordinate conversion method between the local coordinate system and the global coordinate system is determined based on the above lateral distance, longitudinal distance and direction angle. Further, the global boundary point coordinates of each boundary point in the global coordinate system are determined based on the boundary point coordinates of each boundary point of the obstacle in the local coordinate system and the preset coordinate conversion method.

[0115] For example, the conversion method of the boundary point 2 in the following table is used to determine the conversion steps of the boundary point in the local coordinate system and the global coordinate system. Figure 4

[0116] First, a global coordinate system XY-O which is the same as the origin point and direction in the local coordinate system is defined, the lateral and longitudinal movement distances a and b of the vehicle of each frame are received and accumulated, and the rotation angle a is positive counterclockwise and negative clockwise, and the conversion of the obstacle information and the boundary point of the obstacle from the local coordinate system to the global coordinate system is completed.

[0117] Specifically, the coordinate information of the boundary point 2 of the obstacle recognized in the local coordinate system is (x2, y2), when the vehicle needs to detour the obstacle, the vehicle moves b in the positive direction of the X axis, a in the positive direction of the Y axis, and the angle of rotation is a, and the coordinate conversion calculation is performed based on the determined coordinate conversion method. Specifically, the coordinate conversion formula is as follows:

[0118] X_2=x2×cos(-α)+y2×sin(-α)+b ​

[0119] Y_2 = y2 * cos(-a) - x2 * sin(-a) + a

[0120] Based on the above expression, the coordinate information of the boundary point 2 is converted, that is, in the global coordinate system XY-O, the coordinates of the boundary point 2 are (X_2, Y_2).

[0121] Further, the global boundary point coordinates of the next moment within the preset range of the current vehicle are determined respectively, and based on the comparison result between the global coordinate difference between the global boundary point coordinates of the current moment and the global boundary point coordinates of the next moment and the preset coordinate threshold, the boundary point type of each boundary point is determined.

[0122] Specifically, the global boundary point coordinates of the next moment within the preset range of the current vehicle are obtained, and the global boundary point coordinates of the current moment and the global boundary point coordinates of the next moment are matched, and based on the comparison result between the global coordinate difference between the global boundary point coordinates of the current moment and the global boundary point coordinates of the next moment and the preset coordinate threshold, the boundary point type of each boundary point is determined. If the global coordinate difference is within the preset coordinate threshold, the boundary point is determined to be a static boundary point, and the obstacle information is filled into the static boundary point information matrix in the global coordinate system; on the contrary, if the global coordinate difference is not within the preset coordinate threshold, the boundary point is determined to be a dynamic boundary point, and the obstacle information is filled into the dynamic boundary point information matrix in the global coordinate system.

[0123] Further, if the boundary point type is a dynamic boundary point, the global boundary point coordinates of each boundary point are updated in real time, and based on the real-time updated boundary point, the driving trajectory of the current vehicle is updated in real time until the boundary point is not within the detection distance condition range, or the current vehicle passes through the boundary point; on the contrary, if the boundary point type is a static boundary point, the driving trajectory of the current vehicle is determined based on each boundary point until the boundary point is not within the detection distance condition range, or the current vehicle passes through the boundary point.

[0124] In this embodiment, when the vehicle completes the detour, the vehicle controller cancels the obstacle detour, and the obstacle information conversion is no longer performed, and the current vehicle continues to travel according to the predetermined driving route.

[0125] The technical scheme of the embodiment obtains at least one point cloud data in a preset range of a current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin, so that more accurate radar data is obtained to provide necessary information for automatic driving vehicle deceleration obstacle avoidance and obstacle bypass planning path, at least one obstacle recognition condition is obtained, and obstacle information of obstacles in the preset range of the current vehicle is recognized based on each obstacle recognition condition and each point cloud coordinate, wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates. The point cloud data scanned is recognized through the plurality of obstacle recognition conditions, the obstacle information around the vehicle is determined, the accuracy of obstacle recognition is improved, and the safety of vehicle driving is improved.

[0126] The following is an embodiment of the obstacle information determination device provided by the embodiment of the application. The device and the obstacle information determination method of each embodiment described above belong to the same inventive concept. Details not described in the embodiment of the obstacle information determination device can be referred to the embodiment of the obstacle information determination method described above.

[0127] Embodiment three

[0128] Figure 5 The structure diagram of the obstacle information determination device provided by the third embodiment of the application. The embodiment can be applied to the case of determining the obstacles around the vehicle during automatic driving of the vehicle, and is more suitable for the case of determining the obstacles around the vehicle without using a camera or when the camera is damaged or its function is limited. Referring to Figure 5 The specific structure of the obstacle information determination device comprises a point cloud data acquisition module 310 and an obstacle information recognition module 320, wherein

[0129] The point cloud data acquisition module 310 is configured to obtain at least one point cloud data in a preset range of a current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin.

[0130] The obstacle information recognition module 320 is configured to obtain at least one obstacle recognition condition, and recognize obstacle information of obstacles in the preset range of the current vehicle based on each obstacle recognition condition and each point cloud coordinate, wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and the right adjacent point coordinates.

[0131] The technical scheme of the embodiment obtains at least one point cloud data in a preset range of a current vehicle, wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin; thereby obtaining more accurate radar data to provide necessary information for automatic driving vehicle deceleration obstacle avoidance and obstacle bypass planning path; at least one obstacle recognition condition is obtained, and based on each obstacle recognition condition and each point cloud coordinate, obstacle information of obstacles in the preset range of the current vehicle is recognized; wherein the obstacle recognition condition comprises a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and a right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and a left adjacent point coordinate and a right adjacent point coordinate, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate; the scanned point cloud data is identified through multiple obstacle recognition conditions to determine the obstacle information around the vehicle, and the accuracy of obstacle recognition is improved, thereby improving the safety of vehicle driving.

[0132] On the basis of each of the above embodiments, the obstacle information comprises the number of obstacles, the obstacle number, the number of boundary points of the obstacle, the boundary point number of the obstacle, and the boundary point coordinates of the obstacle.

[0133] On the basis of each of the above embodiments, the point cloud data acquisition module 310 comprises:

[0134] An initial point cloud coordinate acquisition unit is configured to scan a preset range of the current vehicle based on a preset radar sensor, and acquire each initial point cloud coordinate in the scanning result.

[0135] A target point cloud coordinate acquisition unit is configured to respectively perform data preprocessing on each initial point cloud coordinate to obtain each target point cloud coordinate in the preset range of the current vehicle.

[0136] On the basis of each of the above embodiments, the target point cloud coordinate acquisition unit comprises:

[0137] A coordinate adjustment matrix acquisition subunit is configured to acquire a preset coordinate storage matrix, right-shift each column coordinate data in the preset coordinate storage matrix by one column, and store the corresponding column coordinate data in the initial point cloud coordinate in the first column of the preset coordinate storage matrix to obtain a coordinate adjustment matrix.

[0138] A coordinate sorting matrix acquisition subunit is configured to sort the coordinate data in the coordinate adjustment matrix according to a preset sorting rule to obtain a coordinate sorting matrix.

[0139] The point cloud coordinate acquisition subunit is configured to acquire at least two columns of coordinate data in the coordinate ordering matrix, determine a row coordinate mean value of each row of coordinate data in the at least two columns of coordinate data, and take each row coordinate mean value as a corresponding point cloud coordinate in the target point cloud coordinate.

[0140] On the basis of the above embodiments, the obstacle information identification module 320 comprises:

[0141] The current first adjacent distance acquisition unit is configured to, for any point cloud coordinate, if a distance between the current point cloud coordinate and the current vehicle meets the detection distance condition, acquire a current first adjacent distance between the current point cloud coordinate and a right adjacent point of the current point cloud coordinate.

[0142] The first obstacle information acquisition unit is configured to, if the current first adjacent distance does not meet the first adjacent distance condition, accumulate the obstacle number of the obstacle, accumulate the obstacle number, accumulate the boundary point number, accumulate the boundary point number, and determine the boundary point coordinate based on the current point cloud coordinate.

[0143] On the basis of the above embodiments, the obstacle information identification module 320 comprises:

[0144] The current adjacent angle acquisition unit is configured to, if the current first adjacent distance meets the first adjacent distance condition, acquire a current adjacent angle between the current point cloud coordinate and a left adjacent point coordinate and a right adjacent point coordinate of the current point cloud coordinate, respectively.

[0145] The second obstacle information acquisition unit is configured to, if the current adjacent angle does not meet the adjacent angle condition, match the current boundary point number of the obstacle with a preset number threshold value; if the current boundary point number is within the preset number threshold value range, accumulate the boundary point number, and determine the boundary point coordinate; if the current boundary point number is not within the preset number threshold value range, accumulate the obstacle number, accumulate the obstacle number, accumulate the boundary point number, accumulate the boundary point number, and determine the boundary point coordinate.

[0146] On the basis of the above embodiments, the obstacle information identification module 320 comprises:

[0147] The current second adjacent distance acquisition unit is configured to, if the current adjacent angle meets the adjacent angle condition, acquire a current second adjacent distance between the current point cloud coordinate and a left adjacent point of the current point cloud coordinate.

[0148] The third obstacle information acquisition unit is configured to, if the current second adjacent distance does not meet the second adjacent condition, accumulate the boundary point number.

[0149] an obstacle information storage unit, configured to, if the current second adjacent distance meets the second adjacent condition and it is determined that the current point cloud data recognition is completed, traverse other point cloud coordinates, and store the obstacle number, obstacle number, boundary point number, boundary point number and boundary point coordinates of each obstacle identified.

[0150] On the basis of each of the above embodiments, the device comprises:

[0151] a global boundary point coordinate determination module, configured to, after identifying the obstacle information of the obstacles in the preset range of the current vehicle, acquire a global coordinate system, and determine the global boundary point coordinates of each boundary point in the global coordinate system based on the boundary point coordinates of each boundary point in the local coordinate system and a preset coordinate conversion method;

[0152] a boundary point type determination module, configured to determine the global boundary point coordinates in the preset range of the current vehicle at the next moment, and determine the boundary point type of each boundary point based on the comparison result of the global coordinate difference between the global boundary point coordinates at the current moment and the global boundary point coordinates at the next moment and the preset coordinate threshold.

[0153] On the basis of each of the above embodiments, the boundary point type comprises a dynamic boundary point and a dynamic boundary point;

[0154] Correspondingly, the device further comprises:

[0155] a first driving trajectory updating module, configured to, after determining the boundary point type of each boundary point, if the boundary point type is a dynamic boundary point, update the global boundary point coordinates of each boundary point in real time, and update the driving trajectory of the current vehicle based on the real-time updated boundary point until the boundary point is not within the detection distance condition range or the current vehicle passes through the boundary point by detouring;

[0156] a second driving trajectory updating module, configured to, after determining the boundary point type of each boundary point, if the boundary point type is a static boundary point, determine the driving trajectory of the current vehicle based on each boundary point until the boundary point is not within the detection distance condition range or the current vehicle passes through the boundary point by detouring.

[0157] The obstacle information determination device provided in the embodiments of the present application can perform the obstacle information determination method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0158] It is worth noting that the above-mentioned embodiments of the obstacle information determination device are divided according to the functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0159] Embodiment four

[0160] Figure 6 A structural schematic diagram of an electronic device provided for embodiment four of the present application. Figure 6 A block diagram of an exemplary electronic device 12 suitable for implementing an embodiment of the present application is shown. Figure 6 The electronic device 12 shown is merely an example and should not limit the function and use range of the embodiment of the present application.

[0161] As shown in Figure 6 , the electronic device 12 is in the form of a general-purpose computing electronic device. The components of the electronic device 12 can include but are not limited to one or more processors or processing units 16, system memory 28, and bus 18 connecting the different system components, including the system memory 28 and the processing unit 16.

[0162] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0163] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that is accessible by the electronic device 12 and includes both volatile and non-volatile media, removable and non-removable media.

[0164] The system memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 can be used for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 6 Not shown, is a generally-rectangularly-shaped "hard disk drive", commonly referred to as a "hard drive". Although Figure 6A disk drive, a floppy disk drive, a CD-ROM drive, a DVD-ROM drive, or other removable media drive, a flash memory card drive (such as a compact flash drive), and a tape drive, a tape drive, and a RAID storage system. Such computer readable media can further include non-transitory media such as hard disks, floppy disks, floppy diskettes, compact floppy diskettes, CD-ROMs, DVD-ROMs, tape, magnetic tape, magnetic disk storage, and the like, as well as any and all computer readable media then available. System memory 28 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

[0165] Program / utility 40 having a set (at least one) of program modules 42 can be stored in system memory 28 by way of example, such programs / modules include an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof, can include implementation of a networking environment. Program modules 42 generally carry out the functions and / or methodologies of embodiments of the application as described herein.

[0166] Electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or pointing device, a display 24, etc. ; other devices such as are necessary equivalents or play back devices, etc. that facilitate interaction with the electronic device 12. Such communication can be facilitated by an input / output (I / O) interface 22. Further, electronic device 12 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the public network, such as the Internet, through a network adapter 20. As will be appreciated, one or more parts of an embodiment of the application can be distributed across one or more electronic, opto-electronic, and / or electro-optical devices. Note also that one or more of the electronic devices 12 can be mobile devices, such as a mobile telephone, smart phone, tablet, laptop, etc. Figure 6 As shown, network adapter 20 communicates with the other components of electronic device 12 via bus 18. It will be appreciated that although not shown, other hardware and / or software well known in the art could be utilized in electronic device 12, such as an operating system; middleware; device drivers; one or more application programs; and / or other software. Furthermore, electronic device 12 could be a component of a larger system, which includes many of these same components, such as a server bank, a network storage device, etc. Figure 6 As shown, network adapter 20 communicates with the other components of electronic device 12 via bus 18. It will be appreciated that although not shown, other hardware and / or software well known in the art could be utilized in electronic device 12, such as an operating system; middleware; device drivers; one or more application programs; and / or other software. Furthermore, electronic device 12 could be a component of a larger system, which includes many of these same components, such as a server bank, a network storage device, etc.

[0167] Processing unit 16 performs various functions by executing programs stored in system memory 28, such as implementing a method for determining obstacle information, which includes:

[0168] obtaining at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin;

[0169] obstacle information of an obstacle in the preset range of the current vehicle is identified based on each of the obstacle identification conditions and each of the point cloud coordinates; wherein the obstacle identification conditions include a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate respectively, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate.

[0170] Of course, those skilled in the art can understand that the processor can also implement the technical solutions of the sample data acquisition method provided by any embodiment of the application.

[0171] Embodiment five

[0172] The embodiment five provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to implement, for example, a step of a method for determining obstacle information provided by the embodiment, and the method for determining obstacle information comprises:

[0173] At least one point cloud data in a preset range of a current vehicle is acquired; wherein the point cloud data comprises a point cloud coordinate in a local coordinate system with the current vehicle as an origin;

[0174] At least one obstacle identification condition is acquired, and obstacle information of an obstacle in the preset range of the current vehicle is identified based on each of the obstacle identification conditions and each of the point cloud coordinates; wherein the obstacle identification conditions include a detection distance condition between the point cloud coordinate and the current vehicle, a first adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate, an adjacent angle condition between the point cloud coordinate and the left adjacent point coordinate and the right adjacent point coordinate respectively, and a second adjacent distance condition between the point cloud coordinate and the right adjacent point coordinate.

[0175] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0176] The computer readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which computer readable program code is embodied. Such propagated data signals can take a wide variety of forms, including but not limited to electro-magnetic signals, optical signals, or any suitable combination thereof. Computer readable signal medium can also be any computer readable medium that is not a storage medium, that is capable of storing the program for use by or in connection with the instruction execution system, apparatus or device.

[0177] The program code embodied on the computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0178] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, application specific circuitry, or field programmable gate array (FPGA) circuitry can execute the computer program code.

[0179] Those skilled in the art should understand that the modules or steps of the present application described above can be realized by general computing devices, which can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and optionally, they can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, or they can be respectively manufactured into individual integrated circuit modules, or multiple modules or steps among them can be manufactured into a single integrated circuit module to realize. Thus, the present application is not limited to any specific combination of hardware and software.

[0180] It is noted that the above merely describes the preferred embodiments of the present application and the principles of the applied technology. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and more other equivalent embodiments can be included without departing from the concept of the present application, and the scope of the present application is determined by the appended claims.

Claims

1. An obstacle information determination method characterized by comprising: The method comprises: acquiring at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as the origin; acquiring at least one obstacle recognition condition, and identifying obstacle information of an obstacle within the preset range of the current vehicle based on each of the obstacle recognition conditions and each of the point cloud coordinates; wherein the obstacle recognition conditions comprise a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and left adjacent point coordinates; the acquiring at least one obstacle recognition condition, and identifying the obstacle information of the obstacle within the preset range of the current vehicle based on each of the obstacle recognition conditions and each of the point cloud coordinates, comprises: for any point cloud coordinate, if the distance between the current point cloud coordinate and the current vehicle meets the detection distance condition, then acquiring a current first adjacent distance between the current point cloud coordinate and the right adjacent point of the current point cloud coordinate; if the current first adjacent distance does not meet the first adjacent distance condition, then adding the number of obstacles, adding the obstacle number, adding the number of boundary points, adding the boundary point number, and determining the boundary point coordinates based on the current point cloud coordinates; the acquiring at least one obstacle recognition condition, and identifying the obstacle information of the obstacle within the preset range of the current vehicle based on each of the obstacle recognition conditions and each of the point cloud coordinates, further comprises: if the current first adjacent distance meets the first adjacent distance condition, then acquiring a current adjacent angle between the current point cloud coordinate and the left adjacent point coordinates and the right adjacent point coordinates of the current point cloud coordinate; if the current adjacent angle does not meet the adjacent angle condition, then matching the current boundary point number of the obstacle with a preset number threshold; if the current boundary point number is within the preset number threshold, then adding the boundary point number and determining the boundary point coordinates; if the current boundary point number is not within the preset number threshold, then adding the number of obstacles, adding the obstacle number, adding the number of boundary points, adding the boundary point number, and determining the boundary point coordinates; the acquiring at least one obstacle recognition condition, and identifying the obstacle information of the obstacle within the preset range of the current vehicle based on each of the obstacle recognition conditions and each of the point cloud coordinates, further comprises: if the current adjacent angle meets the adjacent angle condition, then acquiring a current second adjacent distance between the current point cloud coordinate and the left adjacent point of the current point cloud coordinate; if the current second adjacent distance does not meet the second adjacent condition, then adding the boundary point number; If the current second adjacent distance meets the second adjacent condition, and it is determined that the current point cloud data recognition is completed, other point cloud coordinates are traversed, and the obstacle number, obstacle number, boundary point number, boundary point number and boundary point coordinates of each obstacle recognized are stored.

2. The method of claim 1, wherein, The obstacle information includes the number of obstacles, the number of obstacles, the number of boundary points of the obstacle, the number of boundary points of the obstacle, and the boundary point coordinates of the obstacle.

3. The method of claim 1, wherein, The at least one point cloud data in the preset range of the current vehicle includes: The preset radar sensor scans the preset range of the current vehicle and obtains each initial point cloud coordinate in the scanning result. Each initial point cloud coordinate is respectively preprocessed to obtain each target point cloud coordinate in the preset range of the current vehicle.

4. The method of claim 3, wherein, The data preprocessing of each initial point cloud coordinate to obtain each target point cloud coordinate in the preset range of the current vehicle includes: Obtain a preset coordinate storage matrix, move each column coordinate data in the preset coordinate storage matrix by one column, and store the corresponding column coordinate data in the initial point cloud coordinate in the first column of the preset coordinate storage matrix to obtain a coordinate adjustment matrix. Sort the coordinate data in the coordinate adjustment matrix according to a preset sorting rule to obtain a coordinate sorting matrix. The preset sorting rule includes: Arrange each row of coordinate data in the coordinate adjustment matrix in descending or ascending order to obtain the coordinate sorting matrix. Obtain at least two column coordinate data in the coordinate sorting matrix, determine the row coordinate mean of each row coordinate data in the at least two column coordinate data, and take each row coordinate mean as the corresponding point cloud coordinate in the target point cloud coordinate.

5. The method of claim 2, wherein, After identifying the obstacle information of the obstacle in the preset range of the current vehicle, it also includes: Obtain a preset global coordinate system, and determine the global boundary point coordinates of each boundary point in the global coordinate system based on the boundary point coordinates of each boundary point in the local coordinate system and a preset coordinate conversion method. Determine the global boundary point coordinates in the preset range of the current vehicle at the next moment, and determine the boundary point type of each boundary point based on the comparison result of the global coordinate difference between the global boundary point coordinates at the current moment and the global boundary point coordinates at the next moment and the preset coordinate threshold.

6. The method of claim 5, wherein, The boundary point type includes dynamic boundary point and dynamic boundary point. Correspondingly, after determining the boundary point type of each boundary point, it also includes: If the boundary point type is a dynamic boundary point, the global boundary point coordinates of each boundary point are updated in real time, and the driving track of the current vehicle is updated in real time based on the real-time updated boundary point until the boundary point is not in the detection distance condition range, or the current vehicle passes through the boundary point by detouring; If the boundary point type is a static boundary point, the driving track of the current vehicle is determined based on each boundary point until the boundary point is not in the detection distance condition range, or the current vehicle passes through the boundary point by detouring.

7. An obstacle information determination device characterized by comprising: It includes: The point cloud data acquisition module is configured to acquire at least one point cloud data within a preset range of a current vehicle; wherein the point cloud data comprises point cloud coordinates in a local coordinate system with the current vehicle as an origin; The obstacle information identification module is configured to acquire at least one obstacle identification condition, and identify obstacle information of an obstacle within the preset range of the current vehicle based on each of the obstacle identification conditions and each of the point cloud coordinates; wherein the obstacle identification condition comprises a detection distance condition between the point cloud coordinates and the current vehicle, a first adjacent distance condition between the point cloud coordinates and right adjacent point coordinates, an adjacent angle condition between the point cloud coordinates and left adjacent point coordinates and right adjacent point coordinates, and a second adjacent distance condition between the point cloud coordinates and left adjacent point coordinates. The obstacle information identification module comprises: The current first adjacent distance acquisition unit is configured to, for any point cloud coordinate, if a distance between the current point cloud coordinate and the current vehicle meets the detection distance condition, acquire a current first adjacent distance between the current point cloud coordinate and right adjacent point coordinates of the current point cloud coordinate; The first obstacle information acquisition unit is configured to, if the current first adjacent distance does not meet the first adjacent distance condition, accumulate the number of obstacles, the number of obstacle, the number of boundary points, the number of boundary points of the obstacle, and determine the boundary point coordinates based on the current point cloud coordinates; The current adjacent angle acquisition unit is configured to, if the current first adjacent distance meets the first adjacent distance condition, acquire a current adjacent angle between the current point cloud coordinate and left adjacent point coordinates and right adjacent point coordinates of the current point cloud coordinate; The second obstacle information acquisition unit is configured to, if the current adjacent angle does not meet the adjacent angle condition, match the current boundary point number of the obstacle with a preset number threshold; if the current boundary point number is within the preset number threshold, accumulate the boundary point number, and determine the boundary point coordinates; if the current boundary point number is not within the preset number threshold, accumulate the number of obstacles, the number of obstacle, the number of boundary points, the number of boundary points, and determine the boundary point coordinates; The current second adjacent distance acquisition unit is configured to, if the current adjacent angle meets the adjacent angle condition, acquire a current second adjacent distance between the current point cloud coordinate and left adjacent point of the current point cloud coordinate; The third obstacle information acquisition unit is configured to, if the current second adjacent distance does not meet the second adjacent condition, accumulate the boundary point number; The obstacle information storage unit is configured to, if the current second adjacent distance meets the second adjacent condition, and it is determined that the current point cloud data identification is completed, traverse other point cloud coordinates, and store the number of obstacles, the number of obstacle, the number of boundary points, the number of boundary points, and the boundary point coordinates of each obstacle identified.

8. An electronic device, comprising: The one or more processors; The storage device is configured to store one or more programs, ​ When the one or more programs are executed by the one or more processors, the one or more processors implement the obstacle information determination method as claimed in any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by a processor, implements the obstacle information determination method as claimed in any one of claims 1-6.

Images