Anti-collision detection method, device, equipment and medium

Abstract

The invention relates to the technical field of engineering machinery, in particular to an anti-collision detection method, device and equipment and a medium. In the embodiment of the invention, electronic equipment scans point cloud data of a cantilever crane and point cloud data of an obstacle in different postures in real time based on a laser radar sensor; determining a first bounding box corresponding to each sub-boom of the boom and a second bounding box of the sensing area corresponding to each sub-boom; according to the first bounding box, the point cloud data of the sub-arm support in the sensing range of the laser radar is filtered and removed, the false alarm rate of anti-collision detection is effectively reduced, according to the second bounding box, target point cloud data which may collide with the sub-arm support in the sensing area is determined, and anti-collision detection is performed according to the target point cloud data. And the anti-collision detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of engineering machinery, and in particular to an anti-collision detection method, device, equipment and medium. Background Art

[0002] Intelligent and safe operation is the current technical hotspot in the industry. For the operation scenarios of mechanical equipment with multi-joint arms such as pump trucks and concrete placing machines, there is a risk of collision between the multi-joint arms and obstacles in the operation scene during operation due to blind spots in the driver's field of vision.

[0003] The current anti-collision detection method is prone to false alarms, that is, the existing technology easily misinterprets the arm's own point cloud as the obstacle's point cloud, thereby generating false alarms. In addition, the current anti-collision detection uses a distance sensor to detect the distance between each object and the sub-arm, and determines whether a collision will occur based on the distance, which has low anti-collision detection efficiency. Summary of the invention

[0004] The present application provides an anti-collision detection method, device, equipment and medium to solve the problems of easy false alarm of the main body and low detection efficiency in the prior art during anti-collision detection.

[0005] In a first aspect, an embodiment of the present application provides an anti-collision detection method, the method comprising:

[0006] Acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom;

[0007] For each sub-boom, a first bounding box corresponding to the sub-boom is determined according to pre-saved first size information of the sub-boom, and a second bounding box corresponding to the sensing area is determined according to pre-set second size information of the sensing area corresponding to the sub-boom;

[0008] Determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data;

[0009] Anti-collision detection is performed on the sub-boom according to the target point cloud data.

[0010] In a second aspect, an embodiment of the present application further provides an anti-collision detection device, the device comprising:

[0011] An acquisition module, used to acquire point cloud data sent by the laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom;

[0012] A processing module is used to determine, for each sub-arm, a first bounding box corresponding to the sub-arm according to pre-saved first size information of the sub-arm, and a second bounding box corresponding to the sensing area according to pre-set second size information of the sensing area corresponding to the sub-arm; and determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data;

[0013] The anti-collision detection module is used to perform anti-collision detection on the sub-arm according to the target point cloud data.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising a processor, the processor being configured to implement the steps of any of the above-mentioned anti-collision detection methods when executing a computer program stored in a memory.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the steps of any of the above-mentioned anti-collision detection methods when executed by a processor.

[0016] In an embodiment of the present application, an electronic device obtains point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom; for each sub-boom, a first bounding box corresponding to the sub-boom is determined based on pre-saved first size information of the sub-boom, and a second bounding box corresponding to the perception area is determined based on pre-set second size information of a perception area corresponding to the sub-boom; target point cloud data located outside the first bounding box and within the second bounding box is determined from the point cloud data; and anti-collision detection is performed on the sub-boom based on the target point cloud data. In an embodiment of the present application, the electronic device scans the point cloud data of the boom and the point cloud data of obstacles in different postures in real time based on the laser radar sensor, determines the first bounding box corresponding to each sub-boom of the boom and the second bounding box corresponding to the perception area of ​​each sub-boom; and based on the first bounding box, filters and eliminates the point cloud data of the sub-boom within the perception range of the laser radar, effectively reducing the false alarm rate of anti-collision detection, and determines the target point cloud data that may collide with the sub-boom in the perception environment based on the second bounding box, and performs anti-collision detection based on the target point cloud data, thereby improving the efficiency of anti-collision detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of a collision avoidance detection method provided in an embodiment of the present application;

[0019] Figure 2 A flowchart of an anti-collision detection method provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of the structure of an anti-collision detection device provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0023] In order to avoid false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, the embodiments of the present application provide an anti-collision detection method, device, equipment and medium.

[0024] In an embodiment of the present application, an electronic device obtains point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom; for each sub-boom, a first bounding box corresponding to the sub-boom is determined based on pre-saved first size information of the sub-boom, and a second bounding box corresponding to the perception area is determined based on pre-set second size information of a perception area corresponding to the sub-boom; target point cloud data located outside the first bounding box and within the second bounding box is determined from the point cloud data; and anti-collision detection is performed on the sub-boom based on the target point cloud data.

[0025] Embodiment 1:

[0026] Figure 1 A schematic diagram of an anti-collision detection process provided in an embodiment of the present application, the process includes:

[0027] S101: Acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom.

[0028] An anti-collision detection method provided in an embodiment of the present application is applied to an electronic device, wherein the electronic device may be an industrial computer, a personal computer, or a server.

[0029] In an embodiment of the present application, a laser radar sensor can be used to collect data on the boom and objects around the boom, wherein the boom includes at least one sub-boom, and the laser radar sensor can be fixed on the boom or at other locations other than the boom.

[0030] In the embodiment of the present application, the laser radar sensor emits laser light and determines point cloud data based on the received reflected laser light. The laser radar sensor sends the point cloud data to the electronic device, and the electronic device performs anti-collision detection based on the point cloud data.

[0031] In the embodiment of the present application, one laser radar sensor may be fixed on each sub-arm or only one sub-arm may be fixed on the laser radar sensor, which is not limited here.

[0032] S102: For each sub-boom, determine a first bounding box corresponding to the sub-boom according to pre-saved first size information of the sub-boom, and determine a second bounding box corresponding to the perception area according to pre-set second size information of the perception area corresponding to the sub-boom; determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data.

[0033] In an embodiment of the present application, the electronic device stores the first size information of each sub-arm and the second size information of the sensing area corresponding to each sub-arm. The electronic device can filter out the target point cloud data corresponding to the object that may collide with each sub-arm based on the first size information and the second size information. The electronic device performs further anti-collision detection based on the target point cloud data. The sensing area is the area where the object that may collide with the boom is located, which is determined by the technician based on experience.

[0034] Specifically, in the embodiment of the present application, for each sub-arm, the electronic device obtains the pre-saved first size information of the sub-arm and determines the first bounding box corresponding to the sub-arm. The electronic device also determines the second bounding box corresponding to the sensing area according to the pre-set second size information of the sensing area corresponding to the sub-arm. The electronic device determines the target point cloud data located outside the first bounding box and inside the second bounding box based on the first bounding box and the second bounding box, and the target point cloud data is the point cloud data corresponding to the object that may collide with the sub-arm.

[0035] In the embodiment of the present application, the electronic device can filter the point cloud data according to the first bounding box, filter out the point cloud data corresponding to each sub-arm, obtain candidate point cloud data, and effectively reduce the false alarm rate of the main body during anti-collision detection. The electronic device also filters out the point cloud data that is not located in the sensing area according to the second bounding box to obtain the target point cloud data, thereby reducing the data volume and redundancy of the original point cloud scanned by the laser radar, and effectively improving the efficiency of anti-collision detection.

[0036] In the embodiment of the present application, the first bounding box and the second bounding box determined by the electronic device may be an oriented bounding box (OBB), an axis aligned bounding box (AABB), or other types of bounding boxes, which are not limited here. The OBB is closer to the shape of the spatial object or point cloud data, and has less spatial redundancy.

[0037] If the first bounding box and the second bounding box are OBBs, the electronic device may determine the candidate point cloud data by the following procedure:

[0038] IF point in joint_OBB_range: filter and remove the point

[0039] ELSE: Keep the point

[0040] Among them, point represents the point cloud data acquired in real time, and joint_OBB_range is the spatial range corresponding to each first OBB.

[0041] The electronic device can determine the target point cloud data through the following procedures:

[0042] IF Point in ROI_OBB_range: Keep the Point

[0043] ELSE: Filter and remove the Point

[0044] Where Point represents the candidate point cloud data, and ROI_OBB_range is the spatial range corresponding to the second bounding box.

[0045] S103: performing anti-collision detection on the sub-boom according to the target point cloud data.

[0046] In an embodiment of the present application, after the electronic device determines the target point cloud data that is outside the first bounding box and inside the second bounding box, the electronic device may perform anti-collision detection on the sub-boom according to the target point cloud data.

[0047] In the embodiment of the present application, the electronic device can perform anti-collision detection based on the distance between each target point cloud data and the sub-arm.

[0048] Specifically, the electronic device can calculate the distance between each target point cloud data and the sub-arm, and determine the target point cloud data corresponding to the distance less than the distance threshold based on a pre-saved distance threshold. The target point cloud data corresponding to the distance less than the distance threshold is the point cloud data determined by the electronic device to be likely to collide with the sub-arm.

[0049] In an embodiment of the present application, the electronic device scans the point cloud data of the boom in different postures and the point cloud data of obstacles in real time based on the laser radar sensor, determines the first bounding box corresponding to each sub-boom of the boom and the second bounding box of the perception area corresponding to each sub-boom; and based on the first bounding box, filters and eliminates the point cloud data of the sub-boom within the perception range of the laser radar, effectively reducing the false alarm rate of anti-collision detection, and determines the target point cloud data in the perception area that may collide with the sub-boom, and performs anti-collision detection based on the target point cloud data, thereby improving the efficiency of anti-collision detection.

[0050] Embodiment 2:

[0051] In order to avoid the occurrence of false alarms of the main body during anti-collision detection, based on the above embodiment, in the embodiment of the present application, the determining of the first bounding box corresponding to the sub-arm according to the pre-saved first size information of the sub-arm includes:

[0052] Acquire a first height carried in the first size information, and perform incremental processing on the first height to obtain a second height of the first bounding box;

[0053] Acquire a first width carried in the first size information, and perform incremental processing on the first width to obtain a second width of the first bounding box;

[0054] Acquire a first depth carried in the first size information, and perform incremental processing on the first depth to obtain a second depth of the first bounding box;

[0055] The first bounding box is constructed according to the second height, the second width and the second depth.

[0056] In the embodiment of the present application, the bounding box is a box of the minimum size that encloses an object, wherein the size of the first bounding box corresponding to the sub-arm should ideally be consistent with the size of the sub-arm. However, during the movement of the arm, there are usually problems with arm shaking and deflection. Based on this, in the embodiment of the present application, when the electronic device determines the first bounding box for the sub-arm, the electronic device will perform incremental processing on the first size information of the sub-arm, and determine the first bounding box based on the first size information after the incremental processing.

[0057] Specifically, in the embodiment of the present application, the electronic device obtains the first height carried in the first size information, and performs incremental processing on the first height to obtain the second height of the first bounding box; the electronic device obtains the first width carried in the first size information, and performs incremental processing on the first width to obtain the second width of the first bounding box; the electronic device obtains the first depth carried in the first size information, and performs incremental processing on the first depth to obtain the second depth of the first bounding box. The electronic device determines the second height, second width, and second depth as the first size information after increment, and constructs the first bounding box according to the first size information after increment.

[0058] In the embodiment of the present application, the electronic device stores a height compensation value, a width compensation value, and a depth compensation value, wherein the height compensation value, the width compensation value, and the depth compensation value are all greater than 0. The electronic device can perform incremental processing on the first height, the first width, and the first depth according to the height compensation value, the width compensation value, and the depth compensation value.

[0059] The electronic device can perform incremental processing on the first height by using the following formula:

[0060] joint_OBB_width=joint_width+joint_width_offset

[0061] Among them, joint_OBB_width represents the second width, joint_width represents the first width, and joint_width_offset represents the width compensation value.

[0062] The electronic device may increment the first height by the following formula:

[0063] joint_OBB_height=joint_height+joint_height_offset

[0064] Among them, joint_OBB_height represents the second height, joint_height represents the first height, and joint_height_offset represents the height compensation value.

[0065] The electronic device may perform increment processing on the first depth by the following formula:

[0066] joint_OBB_depth=joint_depth+joint_depth_offset

[0067] Among them, joint_OBB_depth represents the second depth, joint_depth represents the first depth, and joint_depth_offset represents the depth compensation value.

[0068] Embodiment 3:

[0069] In order to avoid the occurrence of false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, on the basis of the above embodiments, in the embodiment of the present application, the second bounding box corresponding to the sensing area is determined according to the preset second size information of the sensing area corresponding to the sub-arm, including:

[0070] Obtaining a third height, a third width, and a third depth carried in the second size information;

[0071] The second bounding box is constructed according to the third height, the third width, and the third depth.

[0072] After the electronic device constructs the first bounding box corresponding to the sub-arm, the electronic device can filter out the point cloud data belonging to the sub-arm in the point cloud data according to the first bounding box. However, the remaining point cloud data in the point cloud data except the point cloud data belonging to the sub-arm still contains information of a large environmental scene, and the data volume is large, which will affect the efficiency of subsequent obstacle detection calculations. In addition, for the anti-collision detection of the multi-joint arm, the main focus is on the environmental information within a certain range around the current arm. Therefore, it is necessary to limit the sensing area of ​​the multi-joint arm, thereby reducing the data volume and redundancy of the original point cloud data scanned by the lidar sensor, and effectively improving the efficiency of anti-collision detection.

[0073] Specifically, in an embodiment of the present application, the electronic device stores second size information of the perception area corresponding to the sub-arm, and the second size information includes a third height, a third width and a third depth. The electronic device can construct a second bounding box corresponding to the perception area based on the third height, the third width and the third depth.

[0074] Among them, in the embodiment of the present application, the second size information corresponding to the sensing area of ​​the sub-arm is mainly set manually by a technician, and different second size information can be configured for different sub-arms.

[0075] Specifically, the electronic device may store the second size information of the sensing area corresponding to each sub-arm in the following form:

[0076]

[0077] Among them, each row of the matrix corresponds to a sub-arm, and the data in each row is the second size information of the sensing area of ​​the corresponding sub-arm, wherein ROI_OBB_width_i represents the third width of sub-arm i, ROI_OBB_height_i represents the third height of sub-arm i, and ROI_OBB_depth_i represents the third depth of sub-arm i.

[0078] Embodiment 4:

[0079] In order to avoid the occurrence of false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, on the basis of the above embodiments, in an embodiment of the present application, the target point cloud data located outside the first bounding box and within the second bounding box is determined to include:

[0080] Obtaining current posture information of each of the sub-arms;

[0081] Determine the first posture information of the sub-arm in the radar coordinate system according to the first size information and the current posture information of each sub-arm; wherein the posture information at least includes the coordinates of the midpoint and the rotation amount;

[0082] Determining, according to the first pose information, second pose information corresponding to the first bounding box and third pose information of the second bounding box in a radar coordinate system corresponding to the point cloud data;

[0083] Target point cloud data located outside the first bounding box and inside the second bounding box is determined according to the second pose information and the third pose information.

[0084] In an embodiment of the present application, when an electronic device determines target point cloud data located outside a first bounding box and within a second bounding box, the electronic device may first determine the position and posture information of the first bounding box and the second bounding box in the radar coordinate system, and determine the target point cloud data based on the position and posture information.

[0085] Wherein, when determining the position and posture information of the first bounding box and the second bounding box in the radar coordinate system, it is determined according to the first size information of the sub-boom and the current posture information of the sub-boom.

[0086] Specifically, in the embodiment of the present application, the electronic device determines the first pose information of the sub-arm in the radar coordinate system based on the first size information of the sub-arm and the current pose information of the sub-arm. Based on the first pose information, the electronic device determines the second pose information corresponding to the first bounding box and the third pose information of the second bounding box in the radar coordinate system corresponding to the point cloud data; and based on the second pose information and the third pose information, determines the target point cloud data located outside the first bounding box and within the second bounding box.

[0087] Among them, in the embodiment of the present application, the posture information at least includes the coordinates of the midpoint and the rotation amount. The coordinates of the midpoint of the sub-arm can be determined based on the coordinates of the two ends of the sub-arm. The process of determining the coordinates of the two ends of the sub-arm is a prior art. Specifically, the electronic device can determine the coordinates of the two ends of the sub-arm based on the rotation amount carried in the current posture information of the sub-arm, and based on the rotation amount and the pre-stored position information of the laser radar sensor.

[0088] The electronic device can determine the coordinates of the midpoint of the sub-arm by the following formula:

[0089] joint_center_x=(joint_start_x+joint_end_x) / 2

[0090] joint_center_y=(joint_start_y+joint_end_y) / 2

[0091] joint_center_z=(joint_start_z+joint_end_z) / 2

[0092] Among them, joint_center_x is the x-axis coordinate in the coordinates of the midpoint of the sub-boom, joint_center_y is the y-axis coordinate in the coordinates of the midpoint of the sub-boom, joint_center_z is the z-axis coordinate in the coordinates of the midpoint of the sub-boom, joint_start_x is the x-axis coordinate in the coordinates of one end of the sub-boom, joint_start_y is the y-axis coordinate in the coordinates of one end of the sub-boom, joint_start_z is the z-axis coordinate in the coordinates of one end of the sub-boom, joint_end_x is the x-axis coordinate in the coordinates of the other end of the sub-boom, joint_end_y is the y-axis coordinate in the coordinates of the other end of the sub-boom, and joint_end_y is the z-axis coordinate in the coordinates of the other end of the sub-boom.

[0093] Among them, in the embodiment of the present application, the rotation amount carried in the current posture information of the sub-arm can be determined according to the joint angle of the sub-arm, and the joint angle is the angle between the sub-arm and other adjacent sub-arms. The joint angle can be obtained by measuring the angle sensor, or by measuring the inclination angle of each sub-arm through an inclination sensor, and then converting the inclination angle into the angle between adjacent sub-arms, which is not limited here.

[0094] Specifically, in the embodiment of the present application, the electronic device converts the joint angle into a three-axis rotation angle according to a saved angle conversion algorithm, and converts the rotation angle of each axis into a quaternion, and the quaternion is the sub-rotation amount of the sub-arm on the axis. The electronic device determines the sub-rotation amount of the sub-arm on each axis as the rotation amount of the sub-nose tip. Among them, the process of converting the joint angle into a three-axis rotation angle and converting the rotation angle of each axis into a quaternion is a prior art and will not be repeated here.

[0095] Embodiment 5:

[0096] In order to avoid the occurrence of false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, on the basis of the above embodiments, in an embodiment of the present application, the second pose information corresponding to the first bounding box and the third pose information of the second bounding box are determined in the radar coordinate system corresponding to the point cloud data according to the first pose information, including:

[0097] Acquire the coordinates of the midpoint of the sub-arm carried in the first pose information, and determine the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information and the coordinates of the midpoint of the second bounding box carried in the third pose information;

[0098] The rotation amount of the sub-arm carried in the first posture information is obtained, and the rotation amount is determined as the rotation amount of the first bounding box carried in the second posture information and the rotation amount of the second bounding box carried in the third posture information.

[0099] In the embodiment of the present application, the bounding box includes three core elements: center position, rotation amount, and bounding box size. Based on this, after the electronic device constructs the first bounding box and the second bounding box respectively according to the first size information and the second size information, the electronic device will further determine the position information of the bounding box in the radar coordinate system, and the position information includes the coordinates of the midpoint and the rotation amount. Among them, the first bounding box and the second bounding box share a midpoint and a rotation amount.

[0100] Specifically, in an embodiment of the present application, the electronic device obtains the coordinates of the midpoint of the sub-arm carried in the first pose information, and determines the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information corresponding to the first bounding box, and the coordinates of the midpoint of the second bounding box carried in the third pose information corresponding to the second bounding box; the electronic device obtains the rotation amount of the sub-arm carried in the first pose information, and determines the rotation amount as the rotation amount of the first bounding box carried in the second pose information, and the rotation amount of the second bounding box carried in the third pose information.

[0101] Embodiment 6:

[0102] In order to avoid the occurrence of false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, on the basis of the above embodiments, in an embodiment of the present application, the anti-collision detection of the sub-arm according to the target point cloud data includes:

[0103] Determine each subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-boom;

[0104] Determine the spatial distance between each subspace body and the target space body;

[0105] If the minimum spatial distance is less than a preset threshold, the anti-collision detection result is determined to be a collision.

[0106] In an embodiment of the present application, after the electronic device determines the target point cloud data, the electronic device can perform obstacle detection modeling and anti-collision distance calculation, grid modeling of the target point cloud data, and the modeling result is used as input for anti-collision distance calculation.

[0107] Specifically, the electronic device determines each subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-arm. Since each subspace volume has the same size, the electronic device can use an octree data structure to determine each subspace volume. The octree data structure has the characteristics of fast retrieval and can improve the efficiency of grid modeling.

[0108] In an embodiment of the present application, after the electronic device determines each subspace body corresponding to each target point cloud data, and the target space body corresponding to the sub-arm, the electronic device determines the spatial distance between each subspace body and the target space body, and determines the minimum spatial distance. The electronic device can perform anti-collision detection based on the minimum spatial distance and perform anti-collision warning. Specifically, a preset threshold value can be stored in the electronic device, and if the minimum spatial distance is less than the preset threshold value, the anti-collision detection result is determined to be a collision.

[0109] In addition, the electronic device can also control the sub-arm to stop or detour according to the minimum spatial distance.

[0110] In order to avoid the occurrence of false alarms of the main body during anti-collision detection and improve the efficiency of anti-collision detection, on the basis of the above embodiments, in the embodiment of the present application, the determination of each subspace body corresponding to each target point cloud data and the target space body corresponding to the sub-arm includes:

[0111] According to the octree algorithm, the point cloud data is voxelized and meshed;

[0112] Determine a first voxel grid including each target point cloud data as each subspace volume;

[0113] The target space body is determined according to the first size information of the sub-booms and the current posture information of each of the sub-booms.

[0114] In an embodiment of the present application, the electronic device performs voxel grid division on the point cloud data according to the octree algorithm; the electronic device identifies the first voxel grid containing the target point cloud data, and determines the first voxel grid containing each target point cloud data as each subspace volume.

[0115] Furthermore, in the embodiment of the present application, the electronic device determines the target space body according to the first size information of the sub-arms and the current posture information of each sub-arm.

[0116] Figure 2 A schematic diagram of the anti-collision detection process provided in the embodiment of the present application, such as the Figure 2 As shown, the process includes:

[0117] S201: Acquire the point cloud data of the boom sent by the laser radar sensor.

[0118] S202: Calculate the sub-arm bounding box.

[0119] Determine the first bounding box corresponding to the sub-arm.

[0120] S203: Sub-arm point cloud data filtering.

[0121] Determine candidate point cloud data located outside the first bounding box in the point cloud data.

[0122] S204: Calculate the perception area bounding box.

[0123] Determine a second bounding box of the sensing area corresponding to the sub-arm.

[0124] S205: Environmental point cloud data filtering.

[0125] Target point cloud data located within the second bounding box in the candidate point cloud data is determined.

[0126] S206: Octree point cloud mesh voxel modeling.

[0127] Determine the subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-arm.

[0128] S207: Calculate the spatial anti-collision distance.

[0129] The spatial distance between each sub-space volume and the target space volume is determined.

[0130] Embodiment 7:

[0131] Based on the above embodiments, Figure 3 A schematic diagram of the structure of an anti-collision detection device provided in an embodiment of the present application, the device comprises:

[0132] An acquisition module 301 is used to acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom;

[0133] The processing module 302 is used to determine, for each sub-arm, a first bounding box corresponding to the sub-arm according to pre-saved first size information of the sub-arm, and a second bounding box corresponding to the sensing area according to pre-set second size information of the sensing area corresponding to the sub-arm; and determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data;

[0134] The anti-collision detection module 303 is used to perform anti-collision detection on the sub-boom according to the target point cloud data.

[0135] In a possible implementation, the processing module 302 is specifically used to obtain a first height carried in the first size information, and perform incremental processing on the first height to obtain a second height of the first bounding box; obtain a first width carried in the first size information, and perform incremental processing on the first width to obtain a second width of the first bounding box; obtain a first depth carried in the first size information, and perform incremental processing on the first depth to obtain a second depth of the first bounding box; and construct the first bounding box according to the second height, the second width, and the second depth.

[0136] In a possible implementation, the processing module 302 is specifically configured to obtain a third height, a third width, and a third depth carried in the second size information; and construct the second bounding box according to the third height, the third width, and the third depth.

[0137] In a possible implementation, the processing module 302 is specifically used to obtain current posture information of each of the sub-arms; determine the first posture information of the sub-arm in the radar coordinate system based on the first size information and the current posture information of each of the sub-arms; wherein the posture information includes at least the coordinates and the rotation amount of the midpoint; according to the first posture information, determine the second posture information corresponding to the first bounding box and the third posture information of the second bounding box in the radar coordinate system corresponding to the point cloud data; according to the second posture information and the third posture information, determine the target point cloud data located outside the first bounding box and inside the second bounding box.

[0138] In a possible implementation, the processing module 302 is specifically used to obtain the coordinates of the midpoint of the sub-arm carried in the first pose information, and determine the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information, and the coordinates of the midpoint of the second bounding box carried in the third pose information; obtain the rotation amount of the sub-arm carried in the first pose information, and determine the rotation amount as the rotation amount of the first bounding box carried in the second pose information, and the rotation amount of the second bounding box carried in the third pose information.

[0139] In a possible implementation, the anti-collision detection module 303 is specifically used to determine each sub-space body corresponding to each target point cloud data, and the target space body corresponding to the sub-arm; determine the spatial distance between each sub-space body and the target space body; if the minimum spatial distance is less than a preset threshold, determine that the anti-collision detection result is a collision.

[0140] In a possible implementation, the anti-collision detection module 303 is specifically used to perform voxel grid division on the point cloud data according to an octree algorithm; determine the first voxel grid containing each target point cloud data as each sub-space volume; and determine the target space volume according to the first size information of the sub-arm and the current posture information of each sub-arm.

[0141] Embodiment 8:

[0142] Based on the above embodiments, the present application also provides an electronic device, Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, it includes: a processor 41, a communication interface 42, a memory 43 and a communication bus 44, wherein the processor 41, the communication interface 42, and the memory 43 communicate with each other through the communication bus 44;

[0143] The memory 43 stores a computer program. When the program is executed by the processor 41, the processor 41 performs the following steps:

[0144] Acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom;

[0145] For each sub-boom, a first bounding box corresponding to the sub-boom is determined according to pre-saved first size information of the sub-boom, and a second bounding box corresponding to the sensing area is determined according to pre-set second size information of the sensing area corresponding to the sub-boom;

[0146] Determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data;

[0147] Anti-collision detection is performed on the sub-boom according to the target point cloud data.

[0148] In a possible implementation, the processor is further configured to:

[0149] Acquire a first height carried in the first size information, and perform incremental processing on the first height to obtain a second height of the first bounding box;

[0150] Acquire a first width carried in the first size information, and perform incremental processing on the first width to obtain a second width of the first bounding box;

[0151] Acquire a first depth carried in the first size information, and perform incremental processing on the first depth to obtain a second depth of the first bounding box;

[0152] The first bounding box is constructed according to the second height, the second width and the second depth.

[0153] In a possible implementation, the processor is further configured to:

[0154] Obtaining a third height, a third width, and a third depth carried in the second size information;

[0155] The second bounding box is constructed according to the third height, the third width, and the third depth.

[0156] In a possible implementation, the processor is further configured to:

[0157] Obtaining current posture information of each of the sub-arms;

[0158] Determine the first posture information of the sub-arm in the radar coordinate system according to the first size information and the current posture information of each sub-arm; wherein the posture information at least includes the coordinates of the midpoint and the rotation amount;

[0159] Determining, according to the first pose information, second pose information corresponding to the first bounding box and third pose information of the second bounding box in a radar coordinate system corresponding to the point cloud data;

[0160] Target point cloud data located outside the first bounding box and inside the second bounding box is determined according to the second pose information and the third pose information.

[0161] In a possible implementation, the processor is further configured to:

[0162] Acquire the coordinates of the midpoint of the sub-arm carried in the first pose information, and determine the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information and the coordinates of the midpoint of the second bounding box carried in the third pose information;

[0163] The rotation amount of the sub-arm carried in the first posture information is obtained, and the rotation amount is determined as the rotation amount of the first bounding box carried in the second posture information and the rotation amount of the second bounding box carried in the third posture information.

[0164] In a possible implementation, the processor is further configured to:

[0165] Determine each subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-boom;

[0166] Determine the spatial distance between each subspace body and the target space body;

[0167] If the minimum spatial distance is less than a preset threshold, the anti-collision detection result is determined to be a collision.

[0168] In a possible implementation, the processor is further configured to:

[0169] According to the octree algorithm, the point cloud data is voxelized and meshed;

[0170] Determine a first voxel grid including each target point cloud data as each subspace volume;

[0171] The target space body is determined according to the first size information of the sub-booms and the current posture information of each of the sub-booms.

[0172] Since the principle of solving the problem by the above electronic device is similar to that of the anti-collision detection method, the implementation of the above electronic device can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0173] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface 42 is used for communication between the above electronic device and other devices. The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk storage. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0174] The processor may be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it may also be a digital signal processing (DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. Since the principle of solving the problem by the electronic device is similar to the action recognition method, the implementation of the electronic device may refer to the embodiment of the method, and the repeated parts will not be repeated.

[0175] Embodiment 9:

[0176] On the basis of the above embodiments, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program executable by a processor is stored. When the program runs on the processor, the processor implements the following steps when executing:

[0177] Acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom;

[0178] For each sub-boom, a first bounding box corresponding to the sub-boom is determined according to pre-saved first size information of the sub-boom, and a second bounding box corresponding to the sensing area is determined according to pre-set second size information of the sensing area corresponding to the sub-boom;

[0179] Determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data;

[0180] Anti-collision detection is performed on the sub-boom according to the target point cloud data.

[0181] In a possible implementation, determining the first bounding box corresponding to the sub-arm according to the pre-saved first size information of the sub-arm includes:

[0182] Acquire a first height carried in the first size information, and perform incremental processing on the first height to obtain a second height of the first bounding box;

[0183] Acquire a first width carried in the first size information, and perform incremental processing on the first width to obtain a second width of the first bounding box;

[0184] Acquire a first depth carried in the first size information, and perform incremental processing on the first depth to obtain a second depth of the first bounding box;

[0185] The first bounding box is constructed according to the second height, the second width and the second depth.

[0186] In a possible implementation manner, determining the second bounding box corresponding to the sensing area according to the preset second size information of the sensing area corresponding to the sub-arm includes:

[0187] Obtaining a third height, a third width, and a third depth carried in the second size information;

[0188] The second bounding box is constructed according to the third height, the third width, and the third depth.

[0189] In a possible implementation, determining the target point cloud data located outside the first bounding box and within the second bounding box includes:

[0190] Obtaining current posture information of each of the sub-arms;

[0191] Determine the first posture information of the sub-arm in the radar coordinate system according to the first size information and the current posture information of each sub-arm; wherein the posture information at least includes the coordinates of the midpoint and the rotation amount;

[0192] Determining, according to the first pose information, second pose information corresponding to the first bounding box and third pose information of the second bounding box in a radar coordinate system corresponding to the point cloud data;

[0193] Target point cloud data located outside the first bounding box and inside the second bounding box is determined according to the second pose information and the third pose information.

[0194] In a possible implementation, determining, according to the first pose information, second pose information corresponding to the first bounding box and third pose information of the second bounding box in a radar coordinate system corresponding to the point cloud data includes:

[0195] Acquire the coordinates of the midpoint of the sub-arm carried in the first pose information, and determine the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information and the coordinates of the midpoint of the second bounding box carried in the third pose information;

[0196] The rotation amount of the sub-arm carried in the first posture information is obtained, and the rotation amount is determined as the rotation amount of the first bounding box carried in the second posture information and the rotation amount of the second bounding box carried in the third posture information.

[0197] In a possible implementation, performing anti-collision detection on the sub-boom according to the target point cloud data includes:

[0198] Determine each subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-boom;

[0199] Determine the spatial distance between each subspace body and the target space body;

[0200] If the minimum spatial distance is less than a preset threshold, the anti-collision detection result is determined to be a collision.

[0201] In a possible implementation manner, determining each subspace volume corresponding to each target point cloud data and the target space volume corresponding to the sub-boom includes:

[0202] According to the octree algorithm, the point cloud data is voxelized and meshed;

[0203] Determine a first voxel grid including each target point cloud data as each subspace volume;

[0204] The target space body is determined according to the first size information of the sub-booms and the current posture information of each of the sub-booms.

[0205] Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the anti-collision detection method, the implementation of the above-mentioned computer-readable storage medium can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0206] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0207] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0208] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0209] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0210] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An anti-collision detection method, characterized in that: The method comprises: Acquire point cloud data sent by a laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom; For each sub-boom, a first bounding box corresponding to the sub-boom is determined according to pre-saved first size information of the sub-boom, and a second bounding box corresponding to the sensing area is determined according to pre-set second size information of the sensing area corresponding to the sub-boom; Determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data; Anti-collision detection is performed on the sub-boom according to the target point cloud data.

2. The method according to claim 1, characterized in that The determining, according to the pre-saved first size information of the sub-arm, a first bounding box corresponding to the sub-arm comprises: Acquire a first height carried in the first size information, and perform incremental processing on the first height to obtain a second height of the first bounding box; Acquire a first width carried in the first size information, and perform incremental processing on the first width to obtain a second width of the first bounding box; Acquire a first depth carried in the first size information, and perform incremental processing on the first depth to obtain a second depth of the first bounding box; The first bounding box is constructed according to the second height, the second width, and the second depth.

3. The method according to claim 1, characterized in that The determining, according to the preset second size information of the sensing area corresponding to the sub-arm, a second bounding box corresponding to the sensing area comprises: Obtaining a third height, a third width, and a third depth carried in the second size information; The second bounding box is constructed according to the third height, the third width, and the third depth.

4. The method according to claim 1, characterized in that: The determining of the target point cloud data located outside the first bounding box and within the second bounding box comprises: Obtaining current posture information of each of the sub-arms; Determine the first posture information of the sub-arm in the radar coordinate system according to the first size information and the current posture information of each sub-arm; wherein the posture information at least includes the coordinates of the midpoint and the rotation amount; Determining, according to the first pose information, second pose information corresponding to the first bounding box and third pose information of the second bounding box in a radar coordinate system corresponding to the point cloud data; Target point cloud data located outside the first bounding box and inside the second bounding box is determined according to the second pose information and the third pose information.

5. The method according to claim 4, characterized in that The determining, according to the first pose information, in the radar coordinate system corresponding to the point cloud data, second pose information corresponding to the first bounding box and third pose information of the second bounding box includes: Acquire the coordinates of the midpoint of the sub-arm carried in the first pose information, and determine the coordinates of the midpoint as the coordinates of the midpoint of the first bounding box carried in the second pose information and the coordinates of the midpoint of the second bounding box carried in the third pose information; The rotation amount of the sub-arm carried in the first posture information is obtained, and the rotation amount is determined as the rotation amount of the first bounding box carried in the second posture information and the rotation amount of the second bounding box carried in the third posture information.

6. The method according to claim 1, characterized in that The performing anti-collision detection on the sub-boom according to the target point cloud data comprises: Determine each subspace volume corresponding to each target point cloud data, and the target space volume corresponding to the sub-boom; Determine the spatial distance between each subspace body and the target space body; If the minimum spatial distance is less than a preset threshold, the anti-collision detection result is determined to be a collision.

7. The method according to claim 6, characterized in that The determining each subspace volume corresponding to each target point cloud data and the target space volume corresponding to the sub-boom comprises: According to the octree algorithm, the point cloud data is voxelized and meshed; Determine a first voxel grid including each target point cloud data as each subspace volume; The target space body is determined according to the first size information of the sub-booms and the current posture information of each of the sub-booms.

8. An anti-collision detection device, characterized in that: The device comprises: An acquisition module, used to acquire point cloud data sent by the laser radar sensor, wherein the point cloud data includes a point cloud of a boom, and the boom includes at least one sub-boom; A processing module is used to determine, for each sub-arm, a first bounding box corresponding to the sub-arm according to pre-saved first size information of the sub-arm, and a second bounding box corresponding to the sensing area according to pre-set second size information of the sensing area corresponding to the sub-arm; and determine target point cloud data located outside the first bounding box and within the second bounding box from the point cloud data; The anti-collision detection module is used to perform anti-collision detection on the sub-arm according to the target point cloud data.

9. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is used to implement the steps of the anti-collision detection method according to any one of claims 1 to 7 when executing a computer program stored in a memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the anti-collision detection method as claimed in any one of claims 1 to 7.

Images