A method, device, electronic device and storage medium for detecting a traversable area

Abstract

The embodiments of the present application disclose a method, device, electronic device and storage medium for detecting a passable area. The method includes: obtaining point cloud data collected by a multi-line laser radar in the intelligent mobile carrier; converting the point cloud data from the laser radar coordinate system to a plane coordinate system to obtain index data; determining the distance threshold corresponding to the scan line of the multi-line laser radar according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar; determining the attributes of the scan line according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line; determining the passable area of ​​the intelligent mobile carrier according to the attributes of the scan line. In the above manner, the embodiments of the present application can realize the passable area detection of the intelligent mobile carrier.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent vehicle technology, and in particular to a traversable area detection method, device, electronic device and storage medium. Background Art

[0002] An intelligent mobile carrier (such as an intelligent driving vehicle) is a comprehensive intelligent system that covers multidisciplinary knowledge such as signal processing technology, multi-sensor fusion technology, computer technology, modern control and artificial intelligence. It can use various sensors it carries to effectively perceive the surrounding environment information and its own state information, and make autonomous analysis and judgment based on the information obtained, and then autonomously control the mobile carrier to move safely from the starting point to the target point. The traversable area detection of an intelligent mobile carrier is the basis for path planning and real-time obstacle avoidance, and is an important part of environmental perception technology. Therefore, it is of great significance to provide a traversable area detection method for an intelligent mobile carrier. Summary of the invention

[0003] The embodiments of the present application provide a traversable area detection method, device, electronic device and storage medium, which can realize the traversable area detection of an intelligent mobile carrier.

[0004] In a first aspect, an embodiment of the present application provides a traversable area detection method, which is applied to an intelligent mobile carrier, and the method includes:

[0005] Acquire point cloud data collected by a multi-line laser radar in the intelligent mobile carrier;

[0006] Convert the point cloud data from the laser radar coordinate system to a plane coordinate system to obtain index data;

[0007] Determine a distance threshold corresponding to a scan line of the multi-line laser radar according to a scan line identifier in the index data, a pitch angle value of the intelligent mobile carrier, and a laser radar parameter of the multi-line laser radar;

[0008] Determine the attribute of the scan line according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line;

[0009] The passable area of ​​the intelligent mobile carrier is determined according to the attribute of the scan line.

[0010] In a second aspect, an embodiment of the present application provides a traversable area processing device, which is configured in an intelligent mobile carrier, and the device includes:

[0011] An acquisition module, used to acquire point cloud data collected by a multi-line laser radar in the intelligent mobile carrier;

[0012] A coordinate system conversion module, used to convert the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data;

[0013] A first determination module is used to determine a distance threshold corresponding to a scan line of the multi-line laser radar according to a scan line identifier in the index data, a pitch angle value of the intelligent mobile carrier, and a laser radar parameter of the multi-line laser radar;

[0014] A second determination module, configured to determine the attribute of the scan line according to a distance threshold corresponding to the scan line, and index data and point cloud data associated with the scan line;

[0015] The third determination module is used to determine the passable area of ​​the intelligent mobile carrier according to the attributes of the scan line.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0017] one or more processors;

[0018] A memory for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the passable area detection method as described in any embodiment of the present application.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the passable area detection method as described in any embodiment of the present application.

[0021] The technical solution provided by the embodiment of the present application converts the point cloud data collected by the multi-line laser radar in the intelligent mobile carrier from the laser radar coordinate system to the plane coordinate system to obtain the corresponding index data. The index data adds ordered features to the disordered point cloud collected by the multi-line laser radar, thereby laying a foundation for determining the passable area of ​​the intelligent mobile carrier; based on the scan line identifier, pitch angle value, and laser radar parameters in the index data, the distance threshold (i.e., theoretical distance) corresponding to the scan line of the multi-line laser radar can be accurately determined; then, according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line, the scan line attribute is determined, and then the passable area of ​​the intelligent mobile carrier is determined based on the scan line attribute, which provides a new idea for the passable area detection of the intelligent mobile carrier. At the same time, because the calculation of the distance threshold corresponding to the scan line introduces the pitch angle value of the intelligent mobile carrier, the anti-interference ability and adaptability of the passable area detection are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1Ais a flow chart of a traversable area detection method provided in Example 1 of the present application;

[0023] Figure 1B is a schematic diagram of a point cloud coordinate conversion provided in Example 1 of the present application;

[0024] Figure 2 is a flow chart of a traversable area detection method provided in Embodiment 2 of the present application;

[0025] Figure 3A is a flow chart of a traversable area detection method provided in Embodiment 3 of the present application;

[0026] Figure 3B It is a schematic diagram of a missing point provided in Example 3 of the present application;

[0027] Figure 4 It is a structural schematic diagram of a traversable area detection device provided in Embodiment 4 of the present application;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided in Example 5 of the present application. DETAILED DESCRIPTION

[0029] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0030] Embodiment 1

[0031] Figure 1A This is a flow chart of a traversable area detection method provided in the first embodiment of the present application. This embodiment is applicable to the situation of how to determine the traversable area of ​​an intelligent mobile carrier. The method can be executed by the traversable area processing device in the embodiment of the present application. The device can be implemented in software and / or hardware. The device can be configured on an intelligent mobile carrier such as an intelligent driving vehicle. Figure 1A The method shown may specifically include:

[0032] S110, obtaining point cloud data collected by a multi-line laser radar in an intelligent mobile carrier.

[0033] Among them, the intelligent mobile carrier is an unmanned mobile device, which can be an autonomous driving vehicle, etc. The so-called multi-line laser radar is a laser radar including at least two laser beams. Specifically, the multi-line laser radar can form multiple scanning lines through the distribution of multiple laser emitters in the vertical direction and the rotation of the motor in one scan. The number of laser beams of the multi-line laser radar determines the number of scanning lines. For example, if the intelligent mobile carrier is an autonomous driving vehicle, the multi-line laser radar can be installed on the roof or windshield of the autonomous driving vehicle.

[0034] Optionally, the multi-line laser radar is usually a three-dimensional laser radar, and the point cloud data collected by it is three-dimensional data. Specifically, point cloud data refers to a set of points consisting of three-dimensional coordinates, which can be used to characterize the outer surface shape of an object. Among them, the three-dimensional spatial geometric position information of each point can be represented by (x, y, z). In this embodiment, the point cloud data collected by the multi-line laser radar can specifically be the point cloud data of the road scene where the intelligent mobile carrier is located, which can include point cloud data of objects on the road such as trees, lights and vehicles, as well as point cloud data of the road surface.

[0035] Specifically, when the intelligent mobile carrier is traveling on a certain road, the road scene is scanned by a multi-line laser radar arranged thereon to obtain point cloud data of the road scene.

[0036] S120, converting the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data.

[0037] Optionally, the point cloud data can be converted from the lidar coordinate system to the plane coordinate system to obtain index data based on the conversion relationship between the lidar coordinate system and the plane coordinate system, as well as the minimum vertical angle value, maximum vertical angle value, number of laser beams and horizontal angle resolution in the lidar parameters.

[0038] Among them, the horizontal angle resolution refers to the minimum interval between two adjacent points in the horizontal direction (the angle between two adjacent points), which is related to the scanning frequency; the minimum vertical angle value refers to the angle value of the bottom laser beam of the multi-line laser radar in the vertical direction, that is, the angle between the bottom laser beam and the horizontal laser beam; correspondingly, the maximum vertical angle value refers to the angle value of the top laser beam of the multi-line laser radar in the vertical direction, that is, the angle between the top laser beam and the horizontal laser beam. Among them, the so-called horizontal laser beam is a laser beam parallel to the ground emitted by the multi-line laser radar when the intelligent mobile carrier is driving on a straight road.

[0039] Since the points collected by the multi-line laser radar are essentially disordered, in order to facilitate data processing, in this embodiment, the index data is introduced to add an ordered feature to the disordered points collected by the multi-line laser radar. Specifically, the index data refers to projecting the point cloud data of the laser radar coordinate system to the plane coordinate system to obtain the coordinate data of the spatial points in the scene in the plane coordinate system, including the scan line identifier, point number and height value. Optionally, the plane coordinate system XOY in this embodiment can also be called a plane index coordinate system, where the X-axis represents the scan line identifier and the Y-axis represents the point number; specifically, for each point, its index data may include the scan line identifier, point number and height value.

[0040] In this embodiment, each laser beam emitted by the multi-line laser radar to the target detection area can form a scan line through one rotation of the motor. Each scan line has a unique identifier, namely the scan line identifier. The identifiers of the points on the same scan line are the same, which are all scan line identifiers. Taking an N-line laser radar as an example, N ≥ 2, then the N-line laser radar includes N laser beams, and the beam numbers of the N laser beams are 0 to N-1. Then, in the plane coordinate system, the scan lines corresponding to the N laser beams with beam numbers 0 to N-1 are converted into concentric circles or concentric sectors with the center of the multi-line laser radar as the origin. The scan line identifier corresponds to the beam number, and the scan line identifier increases in sequence along the direction away from the origin. For example, in the plane coordinate system, the scan line identifiers of the 16-line laser radar are 0 to 15 in the direction away from the origin. The point number refers to the number of the points on the scan line in the horizontal direction. The size of the point number is related to the horizontal field of view angle and the horizontal angle resolution of the multi-line laser radar. For example, the horizontal field of view angle of the multi-line laser radar is 360 degrees, and the horizontal angle resolution is 1 degree. The size of the point number is equal to 360 degrees / 1 degree=360. In the plane coordinate system, along the clockwise direction, the point numbers of the circular scan lines corresponding to each scan line mark are 0 to 359 respectively; the height value refers to the height value of the point on the scan line in the direction perpendicular to the plane (i.e., the Z direction).

[0041] Optionally, the conversion relationship between the laser radar coordinate system and the plane coordinate system can be expressed by the following formula:

[0042]

[0043] Among them, N scan Indicates the number of laser beams. Taking a 16-beam laser radar as an example, N scan is 16; upB represents the maximum vertical angle value; lowB represents the minimum vertical angle value; Δδ is the horizontal angle resolution of the multi-line laser radar.

[0044] Specific, combined Figure 1B, when the number of laser beams, the maximum vertical angle value, the minimum vertical angle value and the horizontal angle resolution are determined, for any point, combined with the cloud data P(x, y, z) of the point in the laser radar coordinate system, the index data P′(k, n, h) of the point in the plane coordinate system can be obtained through the conversion relationship between the laser radar coordinate system and the plane coordinate system. Among them, k represents the scan line identifier, n represents the point number, and h represents the height value.

[0045] S130. Determine a distance threshold corresponding to a scan line of the multi-line laser radar according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar.

[0046] In this embodiment, considering that there will be a sloped road surface in the actual scene, the distance between two adjacent scan lines will change according to the pitch change of the intelligent mobile carrier. Therefore, in order to enhance the anti-interference ability and adaptability of the algorithm, the pitch angle value of the intelligent mobile carrier is introduced. Among them, the pitch angle value can be determined by the posture information obtained by the navigation and positioning system in the intelligent mobile carrier, and can also be obtained by angle sensors such as gyroscopes. Among them, the navigation and positioning system refers to a combination of at least one unit or system with a positioning function, for example, it can be composed of at least one of an inertial navigation system (INS), an inertial measurement unit (IMU), a global positioning system (GPS) and a BeiDou Navigation Satellite System (BDS). It should be noted that the positioning accuracy of the navigation and positioning system composed of a plurality of units or systems with positioning functions is higher than that of a single positioning unit or system. Optionally, according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar, the distance threshold corresponding to the scan line of the multi-line laser radar is determined, which can be specifically divided into the following three steps:

[0047] The first step is to determine the vertical scanning angle value of the scanning line according to the vertical angle resolution and minimum vertical angle value in the laser radar parameters and the scanning line identifier of the index data.

[0048] Among them, the vertical angle resolution refers to the degree of interval between two adjacent laser beams in the vertical direction; for any scanning line, the vertical scanning angle value of the scanning line refers to the angle value of the scanning line in the vertical direction, specifically, the angle between the laser beam emitted by the laser emitter corresponding to the scanning line and the horizontal laser beam.

[0049] Specifically, the vertical scanning angle value of any scanning line can be determined by the following formula:

[0050]

[0051] Wherein, thea represents the vertical scanning angle value; i represents the scanning line identifier, for example, the scanning line identifier of the 0th scanning line is 0, Indicates the vertical scanning angle resolution of the multi-line laser radar; lowB indicates the minimum vertical angle value.

[0052] The second step is to determine the ground scanning line identification of the multi-line laser radar based on the standard line identification and vertical angle resolution in the laser radar parameters, as well as the pitch angle value of the intelligent mobile carrier.

[0053] The standard line identifier refers to the beam number of the laser beam parallel to the ground emitted by the multi-line laser radar when the intelligent mobile carrier is driving on a straight road, that is, the scan line identifier of the scan line corresponding to the vertical angle value of 0 degrees when the multi-line laser radar is horizontal. Taking the 16-line laser radar as an example, the standard line identifier is 7. The ground scan line identifier is used to represent the number of scan lines scanned on the ground by the multi-line laser radar.

[0054] In this embodiment, according to the pitch angle value of the intelligent mobile carrier, the vertical angle resolution and the standard line mark in the laser radar parameters, the ground scanning line mark of the multi-line laser radar is determined by the following formula. ID Indicates the ground scan line identifier of the multi-line laser radar, scan g Indicates the standard line mark. represents the vertical angle resolution, and β represents the pitch angle value.

[0055]

[0056] It can be understood that, based on actual scenarios, when the intelligent mobile carrier is going downhill, the ground scanning line mark of the multi-line laser radar is greater than the standard line mark; correspondingly, when the intelligent mobile carrier is going uphill, the ground scanning line mark of the multi-line laser radar is less than or equal to the standard line mark.

[0057] The third step is to determine the distance threshold corresponding to the scanning line of the multi-line laser radar based on the ground scanning line identification, the vertical scanning angle value of the scanning line, the pitch angle value of the intelligent mobile carrier, and the installation height value and vertical angle resolution in the laser radar parameters.

[0058] Optionally, the installation height value in the laser radar parameters is the actual installation height of the multi-line laser radar. For example, when the multi-line laser radar is installed on the top of the intelligent mobile carrier, the height of the multi-line laser radar itself is ignored, and the installation height value is equal to the height of the intelligent mobile carrier. The actual installation height of the multi-line laser radar can be obtained by manual measurement or sensor measurement. For each scan line whose scan line identifier is not 0, the distance threshold corresponding to the scan line refers to the theoretical distance between the scan line and the projection of the previous scan line on the XOY plane. For example, for the scan line with a scan line identifier of 2, the distance threshold corresponding to the scan line is the theoretical distance between the scan line and the projection of the scan line with a scan line identifier of 1 on the XOY plane. Optionally, when the scan line identifier is 0, the distance threshold corresponding to the scan line is the distance between the projection of the point on the scan line with a scan line identifier of 0 on the XOY plane and the projection of the center point of the multi-line laser radar on the XOY plane.

[0059] Exemplarily, when the vertical scanning angle value, pitch angle value, installation height value and vertical angle resolution in the laser radar parameters, and ground scanning line identification of the scanning line are determined, the distance threshold corresponding to the scanning line under different scanning line identifications can be calculated by the following formula.

[0060]

[0061] Among them, T d represents the distance threshold between adjacent scan lines, μ is a proportional factor used to adjust the fault tolerance of the system, and can generally be set to 0.9 to 0.95 according to the experience of those skilled in the art. represents the vertical angle resolution, β represents the pitch angle value, thea represents the vertical scanning angle value, and H represents the installation height value.

[0062] Specifically, since the ground scan line marks ground ID It is used to represent the number of scan lines scanned by the multi-line laser radar on the ground. For the scan lines scanned by the multi-line laser radar on the ground, the scan lines are marked as 0, 1, ..., ground IDWhen , the distance threshold corresponding to the scan line is the distance between the projections of two adjacent scan lines on the XOY plane. For example, for a scan line of a multi-line laser radar with a scan line identifier of 1, its corresponding distance threshold is the distance between the projection of the point on the scan line with a scan line identifier of 1 on the XOY plane and the projection of the point on the scan line with a scan line identifier of 0 on the XOY plane; for a scan line of a multi-line laser radar with a scan line identifier of 2, its corresponding distance threshold is the distance between the projection of the point on the scan line with a scan line identifier of 2 on the XOY plane and the projection of the point on the scan line with a scan line identifier of 1 on the XOY plane; and so on. Optionally, for scan lines that are not scanned on the ground by the multi-line laser radar, that is, the scan line identifier is greater than the ground ID When , it can be understood that the distance between adjacent scan lines is an infinite value at this time, and the distance threshold corresponding to the scan line can be set to a relatively large value, such as 1000.

[0063] S140 . Determine the attribute of the scan line according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line.

[0064] In this embodiment, for each scan line, the index data and point cloud data associated with the scan line are substantially the index data and point cloud data corresponding to the points on the scan line. Furthermore, the process of determining the scan line attribute is the process of determining the attribute of each point on the scan line.

[0065] For example, taking the scan line identifier equal to 0 as an example, for any point on the scan line, the distance value between the projection of the point on the XOY plane and the origin of the coordinates can be determined based on the point cloud data of the point, and the determined distance value is compared with the distance threshold of the scan line to further determine the attribute of the point, wherein the attribute of the point can be a ground point cloud, an obstacle point cloud or a slope point cloud. Furthermore, if the determined distance is greater than the distance threshold of the scan line, the point is determined to be a ground point cloud; if the determined distance is less than the distance threshold of the scan line, the point is determined to be an obstacle point cloud.

[0066] In addition, the attribute of the point can also be determined based on the index data of the point. For example, the height value of the point can be determined based on the index data of the point, and the determined height value can be compared with the set height threshold to determine the attribute of the point. Alternatively, the index data and point cloud data of the point can be combined to determine the attribute of the point, which will be described in detail in the following embodiments.

[0067] S150: Determine a passable area of ​​the intelligent mobile carrier according to the attributes of the scan line.

[0068] Specifically, the scanning area corresponding to the ground point cloud and the slope point cloud is used as the passable area of ​​the intelligent mobile carrier.

[0069] The technical solution provided by the embodiment of the present application obtains corresponding index data by converting the point cloud data collected by the multi-line laser radar in the intelligent mobile carrier from the laser radar coordinate system to the plane coordinate system. The index data adds ordered features to the disordered point cloud collected by the multi-line laser radar, thereby laying a foundation for determining the passable area of ​​the intelligent mobile carrier; based on the scan line identifier, pitch angle value, and laser radar parameters in the index data, the distance threshold (i.e., theoretical distance) corresponding to the scan line of the multi-line laser radar can be accurately determined; then, according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line, the scan line attribute is determined, and then the passable area of ​​the intelligent mobile carrier is determined based on the scan line attribute, which provides a new idea for the passable area detection of the intelligent mobile carrier. At the same time, since the calculation of the distance threshold corresponding to the scan line introduces the pitch angle value of the intelligent mobile carrier, the anti-interference ability and adaptability of the passable area detection are enhanced.

[0070] Embodiment 2

[0071] Figure 2 This is a flow chart of a traversable area detection method provided in the second embodiment of the present application, which further explains the determination of the scan line attributes based on the above embodiment. Figure 2 The method shown may specifically include:

[0072] S201. Obtain point cloud data collected by a multi-line laser radar in an intelligent mobile carrier.

[0073] S202: Convert the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data.

[0074] S203. Determine the distance threshold corresponding to the scan line of the multi-line laser radar according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar.

[0075] S204: Determine the height difference between two adjacent points on the scan line according to the index data of the two adjacent points on the scan line.

[0076] In this embodiment, the height difference refers to the absolute value of the height difference between two adjacent point clouds on the same scan line. For example, if the index data of two adjacent points on a scan line are P′1(k1, n1, h1) and P′2(k2, n2, h2), the height difference between the two adjacent points is |h1-h2|.

[0077] S205, determining whether the height difference is greater than or equal to a preset height threshold, if so, executing S209; if not, executing S206.

[0078] Among them, the preset height threshold can be adjusted according to needs in the actual process. Usually, the setting range of the preset high threshold is 3-5 cm.

[0079] S206. Determine the interval distance between two adjacent points on the scan line according to the point cloud data corresponding to the two adjacent points on the scan line; and continue to execute S207.

[0080] The interval distance refers to the distance between two adjacent points on the same scan line. In this embodiment, the Euclidean distance between two adjacent points on the same scan line can be used to represent the interval distance between adjacent points. For example, if the point cloud data of two adjacent points on a scan line are P1(x1, y1, z1) and P2(x2, y2, z2), the interval distance between the two adjacent points is

[0081] S207, determine whether the interval distance is less than a preset distance threshold, if so, execute S208; if not, execute S209.

[0082] Among them, the preset distance threshold can be calculated based on the working principle of laser radar through formula D b =ρ*Δδ for calculation. Where, D b represents the preset distance threshold, ρ represents the distance between the projection of the current point on the XOY plane and the projection of the center point of the multi-line laser radar on the XOY plane. Optionally, when the projection of each scan line on the XOY plane is regarded as a ring, ρ represents the radius of the ring, and Δδ represents the horizontal angle resolution.

[0083] S208 , determining whether two adjacent points on the scan line belong to the same sub-segment, and continuing to execute S210 .

[0084] In this embodiment, for any scan line, if the height difference between two adjacent points on the scan line is less than a preset height threshold, and the interval distance is less than a preset distance threshold, the two adjacent points belong to one sub-segment.

[0085] S209 , segmenting the scan line based on two adjacent points on the scan line, so that the two adjacent points on the scan line belong to different sub-segments, and continuing to execute S210 .

[0086] Optionally, for any scan line, if the height difference between two adjacent points on the scan line is greater than or equal to a preset height threshold, the two adjacent points on the scan line belong to different sub-segments. For example, if the height difference between two adjacent points E and F is greater than a preset height threshold, and F is the current point and E is the previous point of F, then E is used as the end point of the current sub-segment and F is used as the starting point of the next sub-segment.

[0087] Optionally, for any scan line, if the height difference between two adjacent points on the scan line is less than a preset height threshold, and the interval distance is greater than a preset distance threshold, the two adjacent points belong to different sub-segments, that is, the previous point is used as the end point of the current sub-segment, and the current point is used as the starting point of the next sub-segment. For example, if the height difference between two adjacent points E and F is less than a preset height threshold, the interval distance is greater than a preset distance threshold, and F is the current point and E is the previous point of F, then E is used as the end point of the current sub-segment and F is used as the starting point of the next sub-segment.

[0088] S210 , determining an attribute of the scan line according to a line segment parameter of each sub-line segment of the scan line and a distance threshold corresponding to the scan line.

[0089] In order to improve the data processing speed, the present embodiment divides the scan line, that is, each scan line is divided into several sub-segments, and each sub-segment is regarded as a whole, and the attributes of each sub-segment are used to characterize the attributes of the points on the sub-segment. Among them, for each sub-segment of each scan line, the segment parameters of the sub-segment may include a distance mean. The so-called distance mean, for each sub-segment with a scan line identifier of 0, the distance between the projection of each point on a certain sub-segment on the XOY plane and the center point of the multi-line laser radar is added and averaged, and the obtained average value is used as the distance mean of the sub-segment. For each sub-segment whose scan line identifier is not equal to 0 (that is, greater than 0), the distance mean of a certain sub-segment is the distance between the sub-segment and the sub-segment in the adjacent scan line that is located at the same horizontal angle as the sub-segment, wherein the scan line identifier of the adjacent scan line is the previous scan line identifier of the scan line identifier of the sub-segment. For example, for each sub-segment in the scan line with the scan line identifier 1, the distance mean of a sub-segment is the distance between the sub-segment and a sub-segment in the scan line with the scan line identifier 0 that is located at the same horizontal angle as the sub-segment.

[0090] In this embodiment, for each sub-segment of each scan line, the distance mean of the sub-segment may be compared with the distance threshold corresponding to the scan line, and then the attribute of the sub-segment may be determined according to the comparison result. Specifically, the following three situations may be included:

[0091] First, if the distance mean of the sub-segment is greater than the distance threshold corresponding to the scan line, the attribute of the sub-segment is determined to be a ground point cloud. Specifically, for each sub-segment whose scan line identifier is not 0, if the distance mean of the sub-segment is greater than the distance threshold, the attribute of the sub-segment is determined to be a ground point cloud.

[0092] Further, when the scan line identifier is equal to 0, that is, for each sub-segment with the scan line identifier of 0, if the distance mean of the sub-segment is greater than the distance threshold, the attribute of the sub-segment can be determined to be a ground point cloud. Exemplarily, for a scan line with a scan line identifier equal to 0, the line segment parameters of each sub-segment of the scan line can also include a height mean, and then the attribute of the sub-segment can also be determined according to the relationship between the height mean of the sub-segment and the starting height. Specifically, the starting height of the scan line is determined. If the height mean of the sub-segment is less than the starting height of the second preset multiple, the attribute of the sub-segment is determined to be a ground point cloud. The height values ​​of each point on the sub-segment are added and averaged, and the obtained average value is used as the height mean of the sub-segment; the point with the smallest height in the scan line with the scan line identifier of 0 is used as the starting ground point, and the height value of the point is used as the starting height. The second preset multiple is set by those skilled in the art according to needs, usually 1.1-1.2.

[0093] Second, if the distance mean of the sub-segment is less than the distance threshold corresponding to the scan line of the first preset multiple, the attribute of the sub-segment is determined to be an obstacle point cloud; wherein the first preset multiple is set by technicians in this field according to needs, and is usually 0.5-0.7.

[0094] Specifically, for each sub-segment whose scan line identifier is 0, if the mean distance of the sub-segment is less than the distance threshold corresponding to the scan line of the first preset multiple, the attribute of the sub-segment is determined to be an obstacle point cloud. In order to ensure that the attribute of each sub-segment can be accurately determined, considering the slope road in the actual scene, for each sub-segment whose scan line identifier is not 0, if the mean distance of the sub-segment is less than the distance threshold corresponding to the scan line of the first preset multiple, the second curvature between the sub-segment and the alternate sub-segment is determined, and then the attribute of the sub-segment is determined according to the second curvature between the sub-segment and the alternate sub-segment; wherein the alternate sub-segment is a sub-segment in the adjacent scan line that is at the same horizontal angle as the sub-segment, and the scan line identifier of the adjacent scan line is the previous scan line identifier of the scan line identifier of the sub-segment, for example, if the scan line identifier of the sub-segment is 8, then the scan line identifier of the adjacent scan line is 7.

[0095] For each sub-segment whose scan line identifier is not 0, specifically, the coordinate mean of the sub-segment and the coordinate mean of the alternate sub-segments are determined respectively, and then the second curvature between the sub-segment and the alternate sub-segments is determined based on the coordinate mean of the sub-segment and the coordinate mean of the alternate sub-segments. Taking into account the positive and negative values ​​of the curvature, for the convenience of calculation, in this embodiment, the absolute value of the second curvature can be used to characterize the curvature between the sub-segment and the alternate sub-segments. Optionally, the coordinate mean of the sub-segment can be determined based on the point cloud data of the points on the sub-segment; similarly, the coordinate mean of the alternate sub-segments can be determined based on the point cloud data of the points on the alternate sub-segments.

[0096] Exemplarily, the attribute of the sub-line segment can be determined according to the second curvature between the sub-line segment and the interlaced sub-line segment, and the maximum tolerable curvature of the intelligent mobile carrier to the ground can be determined according to the maximum climbing angle of the intelligent mobile carrier; if the second curvature is greater than or equal to the maximum tolerable curvature, the attribute of the sub-line segment is determined to be an obstacle point cloud; if the second curvature is less than the maximum tolerable curvature, the attribute of the sub-line segment is determined according to the attributes of the interlaced sub-line segments of the sub-line segment. Specifically, the tangent value of the maximum climbing angle of the intelligent mobile carrier can be used as the maximum tolerable curvature. For each sub-line segment whose scan line identifier is not 0, if the second curvature between the sub-line segment and the interlaced sub-line segment is greater than the maximum tolerable curvature, the attribute of the sub-line segment is determined to be an obstacle point cloud. If the second curvature between the sub-line segment and the interlaced sub-line segment is less than the maximum tolerable curvature, the attribute of the sub-line segment is determined according to the attributes of the interlaced sub-line segment. Specifically, if the attribute of the alternate sub-segment is an obstacle point cloud, then the attribute of the sub-segment is determined to be an obstacle attribute; if the attribute of the alternate sub-segment is a non-obstacle point cloud (such as a slope point cloud), then the attribute of the sub-segment is determined to be a slope point cloud.

[0097] Third, if the distance mean of the sub-line segment is between the distance threshold corresponding to the scan line of the first preset multiple and the distance threshold corresponding to the scan line, the attribute of the sub-line segment is determined according to the first curvature between the sub-line segment and the adjacent sub-line segment. In this embodiment, for each sub-line segment of each scan line, the adjacent sub-line segment of the sub-line segment and the sub-line segment are located in the same scan line, and if the sub-line segment is the current sub-line segment, the adjacent sub-line segment of the sub-line segment is the next sub-line segment.

[0098] Specifically, the attribute of a sub-line segment is determined based on the first curvature of the sub-line segment and the adjacent sub-line segment. This can be done by calculating the absolute value of the first curvature of the sub-line segment and the adjacent sub-line segment based on the point cloud data corresponding to the last point of the sub-line segment (i.e., the end point of the sub-line segment) and the point cloud data corresponding to the first point of the adjacent sub-line segment (i.e., the starting point of the adjacent sub-line segment), and then determining the attribute of the sub-line segment based on the absolute value of the first curvature. For example, the point cloud data of the last point on the sub-line segment is P cl (x1, y1, z1), the point cloud data of the first point on the adjacent sub-segment is P nf (x2, y2, z2), the absolute value crv of the first curvature between the sub-segment and the adjacent sub-segment can be calculated by the following formula:

[0099]

[0100] Furthermore, if the absolute value of the first curvature is greater than or equal to the preset curvature threshold, the attribute of the sub-segment is determined to be an obstacle point cloud; if the absolute value of the first curvature is less than the preset curvature threshold, the attribute of the sub-segment is determined to be a ground point cloud. The preset curvature threshold can be set according to actual needs and can be flexibly adjusted; optionally, the preset curvature value is usually set to 0.6-0.7 through a large number of practices.

[0101] S211. The scanning area corresponding to the ground point cloud and the slope point cloud of the sub-line segment is used as the passable area of ​​the intelligent mobile carrier.

[0102] Optionally, the scanning area corresponding to the obstacle point cloud is the inaccessible area of ​​the intelligent mobile carrier, and the scanning area corresponding to the slope point cloud and the ground point cloud is the accessible area of ​​the intelligent mobile carrier. Furthermore, after determining the attributes of each sub-segment, the accessible area of ​​the intelligent mobile carrier can be determined according to the attributes of each sub-segment.

[0103] The technical solution of the embodiment of the present application combines index data and point cloud data to segment the scan line, and uses the segmented sub-segments as units to determine the attributes of the sub-segments according to the distance mean of the sub-segments and the distance threshold corresponding to the scan line, thereby improving the data processing speed; then, the passable area of ​​the intelligent mobile carrier is determined according to the attributes of the sub-segments. Compared with the prior art, this embodiment introduces the pitch angle value of the intelligent mobile carrier in the process of determining the passable area of ​​the intelligent mobile carrier, which can effectively and accurately determine the passable area of ​​the intelligent mobile carrier when it is on a flat road surface, a sloping road surface, etc., and enhances the adaptability and anti-interference of the algorithm.

[0104] Embodiment 3

[0105] Figure 3A This is a flow chart of a traversable area detection method provided in the third embodiment of the present application. Based on the above embodiment, the determination of missing points is introduced to further optimize the above method. Figure 3A The method shown may specifically include:

[0106] S310, obtaining point cloud data collected by a multi-line laser radar in an intelligent mobile carrier.

[0107] S320, converting the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data.

[0108] S330: Determine missing points according to the index data.

[0109] In this embodiment, the multi-line laser radar may lose index data projected to the plane coordinate system during scanning due to factors such as the reflectivity and distance of the object. If the index data of a spatial point in the scene is missing in the plane coordinate system, the spatial point is determined as a missing point.

[0110] S340: Determine whether the index data in the neighborhood of the missing point is valid.

[0111] In this embodiment, the points in the neighborhood of the missing point (i.e., the points adjacent to the left and right) are used as the associated points of the missing point. Whether the index data in the neighborhood of the missing point is valid is determined to be whether the associated point of the missing point is valid. Specifically, it can be: if the index data of the associated point exists, the associated point is determined to be valid; otherwise, the associated point is invalid; optionally, if the associated point is invalid, the missing point will be discarded; if the associated point is valid, the missing point is supplemented, that is, the operation S350 is executed.

[0112] S350: If valid, fill the missing point with the index data in the neighborhood of the missing point.

[0113] In this embodiment, when the associated points are valid, the point cloud data and index data of the missing points are supplemented according to the horizontal angle resolution of the laser radar parameters and the point cloud data of the associated points. Specifically, the point cloud data of the missing points can be determined according to the point cloud data of the associated points and the horizontal angle resolution of the laser radar parameters, and then, the index data of the missing points can be determined according to the point cloud data of the missing points and step S320. Furthermore, the index data of the missing points can be determined according to the index data of the associated points and the horizontal angle resolution of the laser radar parameters; and then, according to the index data of the missing points, the point cloud data of the missing points can be determined according to the coordinate conversion method of step S320.

[0114] For example, see Figure 3B , solid points represent points on the scan line, and hollow points represent missing points. For example, A is the missing point, B and C are the associated points of the missing point A. In this embodiment, the point cloud data of the missing point can be determined according to the point cloud data of the associated point B or C and the horizontal angle resolution Δδ of the laser radar parameters; then, the index data of the missing point can be determined according to the coordinate conversion method of step S320.

[0115] S360. Determine a distance threshold corresponding to a scan line of the multi-line laser radar according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar.

[0116] S370 , determining the attributes of the scan line according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line.

[0117] S380: Determine the passable area of ​​the intelligent mobile carrier according to the attributes of the scan line.

[0118] The technical solution of the embodiment of the present application can avoid the problem of inaccurate determination of subsequent traversable areas due to missing points by determining missing points and supplementing point cloud data and index data of the missing points.

[0119] Embodiment 4

[0120] Figure 4 This is a schematic diagram of the structure of a traversable area processing device provided in the fourth embodiment of the present application. This embodiment is applicable to the situation of how to determine the traversable area of ​​an intelligent mobile carrier. The device can be implemented in software and / or hardware, and the device can be configured on an intelligent mobile carrier such as an intelligent driving vehicle.

[0121] like Figure 4 The device shown in the figure includes an acquisition module 410, a coordinate system conversion module 420, a first determination module 430, a second determination module 440 and a third determination module 450, wherein:

[0122] An acquisition module 410 is used to acquire point cloud data collected by a multi-line laser radar in an intelligent mobile carrier;

[0123] A coordinate system conversion module 420 is used to convert the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data;

[0124] A first determination module 430 is used to determine a distance threshold corresponding to a scan line of the multi-line laser radar according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameters of the multi-line laser radar;

[0125] A second determination module 440 is used to determine the attribute of the scan line according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line;

[0126] The third determination module 450 is used to determine the passable area of ​​the intelligent mobile carrier according to the attributes of the scan line.

[0127] The technical solution provided by the embodiment of the present application obtains corresponding index data by converting the point cloud data collected by the multi-line laser radar in the intelligent mobile carrier from the laser radar coordinate system to the plane coordinate system. The index data adds ordered features to the disordered point cloud collected by the multi-line laser radar, thereby laying a foundation for determining the passable area of ​​the intelligent mobile carrier; based on the scan line identifier, pitch angle value, and laser radar parameters in the index data, the distance threshold (i.e., theoretical distance) corresponding to the scan line of the multi-line laser radar can be accurately determined; then, according to the distance threshold corresponding to the scan line, and the index data and point cloud data associated with the scan line, the scan line attribute is determined, and then the passable area of ​​the intelligent mobile carrier is determined based on the scan line attribute, which provides a new idea for the passable area detection of the intelligent mobile carrier. At the same time, since the calculation of the distance threshold corresponding to the scan line introduces the pitch angle value of the intelligent mobile carrier, the anti-interference ability and adaptability of the passable area detection are enhanced.

[0128] Furthermore, the first determination module 430 includes a scanning angle value determination unit, a scanning line identification determination unit and a distance threshold determination unit, wherein:

[0129] A scanning angle value determination unit, used to determine the vertical scanning angle value of the scanning line according to the vertical angle resolution and the minimum vertical angle value in the laser radar parameters and the scanning line identifier of the index data;

[0130] A scanning line identification determination unit, used to determine the ground scanning line identification of the multi-line laser radar according to the standard line identification and vertical angle resolution in the laser radar parameters and the pitch angle value of the intelligent mobile carrier;

[0131] The distance threshold determination unit is used to determine the distance threshold corresponding to the scanning line of the multi-line laser radar based on the ground scanning line identification, the vertical scanning angle value of the scanning line, the pitch angle value of the intelligent mobile carrier, and the installation height value and vertical angle resolution in the laser radar parameters.

[0132] Furthermore, the second determination module 440 includes a height difference determination unit, a spacing distance determination unit, a scan line segmentation unit and an attribute determination unit, wherein:

[0133] a height difference determining unit, used to determine a height difference between two adjacent points on the scan line according to index data of the two adjacent points on the scan line;

[0134] A scan line segmentation unit, configured to segment the scan line based on two adjacent points on the scan line if the height difference is greater than or equal to a preset height threshold, so that the two adjacent points on the scan line belong to different sub-segments;

[0135] an interval distance determination unit, for determining the interval distance between two adjacent points on the scan line according to point cloud data corresponding to the two adjacent points on the scan line if the height difference is less than a preset height threshold;

[0136] The scan line segmentation unit is further configured to determine that two adjacent points on the scan line belong to the same sub-segment if the interval distance is less than a preset distance threshold; and segment the scan line based on the two adjacent points on the scan line so that the two adjacent points on the scan line belong to different sub-segments if the interval distance is greater than or equal to the preset distance threshold;

[0137] The attribute determination unit is used to determine the attribute of the scan line according to the line segment parameters of each sub-line segment of the scan line and the distance threshold corresponding to the scan line.

[0138] Further, the line segment parameter includes a distance mean, and the attribute determination unit may include a first attribute determination subunit, a second attribute determination subunit, and a third attribute determination subunit, wherein:

[0139] A first attribute determination subunit is used to determine that the attribute of the sub-segment is a ground point cloud if the distance mean of the sub-segment is greater than the distance threshold corresponding to the scan line;

[0140] A second attribute determination subunit is used to determine that the attribute of the sub-segment is an obstacle point cloud if the distance mean of the sub-segment is less than the distance threshold corresponding to the scan line of the first preset multiple;

[0141] The third attribute determination subunit is used to determine the attribute of the sub-segment according to the first curvature of the sub-segment and the adjacent sub-segment of the sub-segment if the distance mean of the sub-segment is between the distance threshold corresponding to the scan line of the first preset multiple and the distance threshold corresponding to the scan line.

[0142] Furthermore, the line segment parameters also include a height mean. When the scan line identifier is equal to 0, the first attribute determination subunit is specifically used to:

[0143] Determine the starting height of the scan line;

[0144] If the average height of the sub-segment is less than the second preset multiple of the starting height, it is determined that the attribute of the sub-segment is a ground point cloud.

[0145] Furthermore, the third attribute determination subunit is specifically used for:

[0146] Calculate the absolute value of the first curvature of the sub-segment and the adjacent sub-segment according to the point cloud data corresponding to the last point of the sub-segment and the point cloud data corresponding to the first point of the adjacent sub-segment;

[0147] If the absolute value of the first curvature is greater than or equal to a preset curvature threshold, determining that the attribute of the sub-line segment is an obstacle point cloud;

[0148] If the absolute value of the first curvature is less than a preset curvature threshold, it is determined that the attribute of the sub-line segment is a ground point cloud.

[0149] Furthermore, when the scan line identifier is not equal to 0, the third attribute determination subunit is specifically used to:

[0150] If the distance mean of the sub-segment is less than the distance threshold corresponding to the scan line of the first preset multiple, the attribute of the sub-segment is determined according to the second curvature between the sub-segment and the alternate sub-segment; wherein the alternate sub-segment is a sub-segment in the adjacent scan lines that is located at the same horizontal angle as the sub-segment, and the scan line identifier of the adjacent scan line is the previous scan line identifier of the scan line identifier of the sub-segment.

[0151] Further, when the third attribute determination subunit is used to determine the attribute of the sub-line segment according to the second curvature between the sub-line segment and the alternate sub-line segments, it can be specifically used to:

[0152] According to the maximum climbing angle of the intelligent mobile carrier, the maximum tolerable curvature of the intelligent mobile carrier to the ground is determined;

[0153] If the second curvature is greater than or equal to the maximum tolerable curvature, the attribute of the sub-segment is determined to be an obstacle point cloud;

[0154] If the second curvature is less than the maximum tolerable curvature, the attributes of the sub-segment are determined according to the attributes of the alternate sub-segments of the sub-segment.

[0155] Furthermore, when the third attribute determination subunit is used to determine the attributes of the sub-segments according to the attributes of the interlaced sub-segments of the sub-segments, it can also be used to:

[0156] If the attributes of the alternate sub-segments of the sub-segments are obstacle point clouds, then the attributes of the sub-segments are determined to be obstacle point clouds;

[0157] If the attributes of the alternate sub-segments of the sub-segments are non-obstacle point clouds, it is determined that the attributes of the sub-segments are slope point clouds.

[0158] Furthermore, the third determination module 450 is specifically configured to use the scanning area corresponding to the ground point cloud and the slope point cloud as the passable area of ​​the intelligent mobile carrier.

[0159] Furthermore, the above device also includes:

[0160] A missing point determination module is used to determine the missing points according to the index data;

[0161] The validity judgment module is used to judge whether the index data in the neighborhood of the missing point is valid;

[0162] The filling module is used to fill the missing points with the index data in the neighborhood of the missing points if valid.

[0163] The traversable area processing device provided in this embodiment can execute the traversable area detection method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the method.

[0164] Embodiment 5

[0165] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Example 5 of the present application. Figure 5 A block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present application is shown. Figure 5 The electronic device 12 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0166] like Figure 5 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0167] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0168] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0169] The system memory 28 may 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 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0170] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0171] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the device / terminal / server, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0172] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the passable area detection method provided in the embodiment of the present application.

[0173] Embodiment 6

[0174] Embodiment 6 of the present application also provides a computer-readable storage medium on which a computer program (or computer-executable instructions) is stored. When the program is executed by a processor, it is used to execute the passable area detection method provided in the embodiment of the present application.

[0175] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive lists) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by instruction execution systems, devices or devices or used in combination with them.

[0176] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

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

[0178] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and also including conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, 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 it can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0179] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A traversable area detection method, applied to an intelligent mobile carrier, characterized in that: The method comprises: Acquire point cloud data collected by a multi-line laser radar in the intelligent mobile carrier; Convert the point cloud data from the laser radar coordinate system to a plane coordinate system to obtain index data; Determine a distance threshold corresponding to a scan line of the multi-line laser radar according to a scan line identifier in the index data, a pitch angle value of the intelligent mobile carrier, and a laser radar parameter of the multi-line laser radar; Determine a height difference between two adjacent points on the scan line according to index data of the two adjacent points on the scan line; If the height difference is greater than or equal to a preset height threshold, the scan line is segmented based on two adjacent points on the scan line so that the two adjacent points on the scan line belong to different sub-segments; if the height difference is less than the preset height threshold, the interval distance between the two adjacent points on the scan line is determined according to the point cloud data corresponding to the two adjacent points on the scan line; If the interval distance is less than a preset distance threshold, it is determined that the two adjacent points on the scan line belong to the same sub-segment; if the interval distance is greater than or equal to the preset distance threshold, the scan line is segmented based on the two adjacent points on the scan line so that the two adjacent points on the scan line belong to different sub-segments; Determining the attribute of the scan line according to the line segment parameter of each sub-line segment of the scan line and the distance threshold corresponding to the scan line; The line segment parameters include a distance mean, and determining the attribute of the scan line according to the line segment parameters of each sub-segment of the scan line and a distance threshold corresponding to the scan line includes: If the distance mean of the sub-line segment is greater than the distance threshold corresponding to the scan line, determining that the attribute of the sub-line segment is a ground point cloud; If the distance mean of the sub-line segment is less than a distance threshold corresponding to the scan line of a first preset multiple, determining that the attribute of the sub-line segment is an obstacle point cloud; If the distance mean of the sub-line segment is between the distance threshold corresponding to the scan line of the first preset multiple and the distance threshold corresponding to the scan line, determining the attribute of the sub-line segment according to the first curvature of the sub-line segment and an adjacent sub-line segment of the sub-line segment; The passable area of ​​the intelligent mobile carrier is determined according to the attribute of the scan line.

2. The method according to claim 1, The invention is characterized in that, according to the scan line identifier in the index data, the pitch angle value of the intelligent mobile carrier, and the laser radar parameter of the multi-line laser radar, determining the distance threshold corresponding to the scan line of the multi-line laser radar comprises: Determine the vertical scanning angle value of the scanning line according to the vertical angle resolution and the minimum vertical angle value in the laser radar parameters and the scanning line identifier of the index data; Determine the ground scanning line identifier of the multi-line laser radar according to the standard line identifier and the vertical angle resolution in the laser radar parameters and the pitch angle value of the intelligent mobile carrier; Based on the ground scanning line identifier, the distance threshold corresponding to the scanning line of the multi-line laser radar is determined according to the vertical scanning angle value of the scanning line, the pitch angle value of the intelligent mobile carrier, and the installation height value and vertical angle resolution in the laser radar parameters.

3. The method according to claim 1, characterized in that: The line segment parameters also include a height mean value. When the scan line identifier is equal to 0, determining the attributes of the scan line according to the line segment parameters of each sub-segment of the scan line and the distance threshold corresponding to the scan line also includes: Determining a starting height of the scan line; If the average height of the sub-line segment is less than the second preset multiple of the starting height, it is determined that the attribute of the sub-line segment is a ground point cloud.

4. The method according to claim 1, characterized in that: The determining the attribute of the sub-line segment according to the first curvature of the sub-line segment and an adjacent sub-line segment of the sub-line segment includes: Calculate the absolute value of the first curvature of the sub-line segment and the adjacent sub-line segment according to the point cloud data corresponding to the last point of the sub-line segment and the point cloud data corresponding to the first point of the adjacent sub-line segment; If the absolute value of the first curvature is greater than or equal to a preset curvature threshold, determining that the attribute of the sub-line segment is an obstacle point cloud; If the absolute value of the first curvature is less than the preset curvature threshold, it is determined that the attribute of the sub-line segment is a ground point cloud.

5. The method according to any one of claims 1 to 4, characterized in that: When the scan line identifier is not equal to 0, determining the attribute of each sub-segment of the scan line according to the segment parameter of each sub-segment of the scan line and the distance threshold corresponding to the scan line, further includes: If the distance mean of the sub-line segment is less than the distance threshold corresponding to the scan line of the first preset multiple, the attribute of the sub-line segment is determined according to the second curvature between the sub-line segment and the alternate sub-line segment; wherein the alternate sub-line segment is a sub-line segment in an adjacent scan line that is at the same horizontal angle as the sub-line segment, and the scan line identifier of the adjacent scan line is the previous scan line identifier of the scan line identifier of the sub-line segment.

6. The method according to claim 5, characterized in that: The determining the attribute of the sub-line segment according to the second curvature between the sub-line segment and the alternate sub-line segments includes: Determining a maximum tolerable curvature of the intelligent mobile carrier to the ground according to a maximum climbing angle of the intelligent mobile carrier; If the second curvature is greater than or equal to the maximum tolerable curvature, determining that the attribute of the sub-line segment is an obstacle point cloud; If the second curvature is smaller than the maximum tolerable curvature, the attribute of the sub-segment is determined according to the attributes of the alternate sub-segments of the sub-segment.

7. The method according to claim 6, characterized in that: The determining the attributes of the sub-segments according to the attributes of the interlaced sub-segments of the sub-segments comprises: If the attributes of the alternate sub-line segments of the sub-line segments are obstacle point clouds, determining that the attributes of the sub-line segments are obstacle point clouds; If the attributes of the alternate sub-line segments of the sub-line segments are non-obstacle point clouds, it is determined that the attributes of the sub-line segments are slope point clouds.

8. The method according to claim 7, characterized in that: The determining, according to the attributes of the scan line, a passable area of ​​the intelligent mobile carrier includes: The attributes of the sub-line segment are the scanning area corresponding to the ground point cloud and the slope point cloud as the passable area of ​​the intelligent mobile carrier.

9. The method according to claim 1, characterized in that: After converting the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data, the method further includes: Determine missing points according to the index data; Determining whether the index data in the area of ​​the missing point is valid; If valid, the missing point is filled using the index data in the area of ​​the missing point.

10. A traversable area detection device, configured in an intelligent mobile carrier, characterized in that: The device comprises: An acquisition module, used to acquire point cloud data collected by a multi-line laser radar in the intelligent mobile carrier; A coordinate system conversion module, used to convert the point cloud data from the laser radar coordinate system to the plane coordinate system to obtain index data; A first determination module is used to determine a distance threshold corresponding to a scan line of the multi-line laser radar according to a scan line identifier in the index data, a pitch angle value of the intelligent mobile carrier, and a laser radar parameter of the multi-line laser radar; The second determination module includes a height difference determination unit, a spacing distance determination unit, a scan line segmentation unit and an attribute determination unit, wherein: The height difference determining unit is used to determine the height difference between two adjacent points on the scan line according to the index data of the two adjacent points on the scan line; The scan line segmentation unit is configured to segment the scan line based on two adjacent points on the scan line if the height difference is greater than or equal to a preset height threshold, so that the two adjacent points on the scan line belong to different sub-segments; The interval distance determination unit is used to determine the interval distance between two adjacent points on the scan line according to the point cloud data corresponding to the two adjacent points on the scan line if the height difference is less than the preset height threshold; The scan line segmentation unit is further configured to determine that two adjacent points on the scan line belong to the same sub-segment if the interval distance is less than a preset distance threshold; and segment the scan line based on the two adjacent points on the scan line so that the two adjacent points on the scan line belong to different sub-segments if the interval distance is greater than or equal to the preset distance threshold; The attribute determination unit is used to determine the attribute of the scan line according to the line segment parameters of each sub-line segment of the scan line and the distance threshold corresponding to the scan line; The line segment parameter includes a distance mean, the attribute determination unit includes a first attribute determination subunit, a second attribute determination subunit and a third attribute determination subunit, wherein: The first attribute determination subunit is used to determine that the attribute of the sub-line segment is a ground point cloud if the distance mean of the sub-line segment is greater than the distance threshold corresponding to the scan line; The second attribute determination subunit is configured to determine that the attribute of the sub-line segment is an obstacle point cloud if the distance mean of the sub-line segment is less than a distance threshold corresponding to the scan line of a first preset multiple; The third attribute determination subunit is configured to determine the attribute of the sub-line segment according to a first curvature between the sub-line segment and an adjacent sub-line segment of the sub-line segment if the distance mean of the sub-line segment is between the distance threshold corresponding to the scan line of the first preset multiple and the distance threshold corresponding to the scan line; The third determination module is used to determine the passable area of ​​the intelligent mobile carrier according to the attributes of the scan line.

11. An electronic device, characterized in that: include: one or more processors; A memory for storing 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 passable area detection method as described in any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the traversable area detection method as described in any one of claims 1 to 9 is implemented.

Images