Anti-collision detection method and apparatus for boom, and device and storage medium

Abstract

Disclosed in the present application are an anti-collision detection method and apparatus for a boom, and a device and a storage medium. The method comprises: acquiring first point cloud data of a boom (101); performing curve fitting on the first point cloud data, so as to obtain a boom curve of the boom (102); on the basis of the boom curve, determining a target curvature for the boom (103); on the basis of the target curvature, determining a target modeling parameter value (104); on the basis of the target modeling parameter value, performing spatial modeling on the first point cloud data, so as to obtain a boom-curvature boom spatial model (105); and on the basis of the boom spatial model, performing anti-collision detection to generate an anti-collision detection result of the boom (106), wherein the anti-collision detection result is used for indicating an obstacle that poses a risk of collision with the boom. In this way, the accuracy of anti-collision detection of booms can be improved.

Description

Collision avoidance detection methods, devices, equipment and storage media for booms

[0001] Cross-reference to related applications

[0002] This application claims the benefit of Chinese Patent Application No. 202411478138.2, filed on October 22, 2024, the contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of construction machinery technology, and in particular relates to a method, device, equipment and storage medium for anti-collision detection of booms. Background Technology

[0004] With the rapid development of construction machinery technology, intelligent and high-safety operation have become the design goals of construction machinery. Among them, construction machinery with long and flexible booms, such as cranes, aerial ladder fire trucks, and pump trucks, are widely used engineering machinery. During operation, there is a risk of collision between the boom and obstacles in the work environment, which affects the operational safety of the construction machinery.

[0005] In related technologies, to avoid collisions between the boom and obstacles during operation, image recognition technology is typically used. This involves detecting the distance between the boom and surrounding obstacles based on images of the boom's movement, thereby identifying obstacles that pose a collision risk. However, image recognition technology may have low detection accuracy in certain scenarios, such as low visibility or long detection distances.

[0006] It is evident that the collision avoidance detection of booms in related technologies suffers from low detection accuracy. Summary of the Invention

[0007] This application provides a method, apparatus, device, and storage medium for collision avoidance detection of booms, which can improve the detection accuracy of collision avoidance detection of booms.

[0008] In a first aspect, embodiments of this application provide a method for collision avoidance detection of a boom, including:

[0009] Obtain the first point cloud data of the boom;

[0010] Curve fitting is performed on the first point cloud data to obtain the boom curve of the boom;

[0011] Based on the boom curve, determine the target curvature of the boom;

[0012] Based on the target curvature, target modeling parameter values ​​are determined, which are parameter values ​​of modeling parameters used for spatial modeling;

[0013] Spatial modeling is performed on the first point cloud data based on the target modeling parameter values ​​to obtain the boom spatial model of the boom;

[0014] Collision avoidance detection is performed based on the boom space model to generate collision avoidance detection results for the boom. These results are used to indicate obstacles that pose a collision risk to the boom.

[0015] In some implementations, determining the target curvature of the boom based on the boom curve includes:

[0016] The boom curve is divided to obtain multiple sub-boom curves;

[0017] Based on each of the sub-boom curves, the curvature of the sub-boom curves is determined, and the target curvature includes the curvature of the plurality of sub-boom curves;

[0018] The process of determining the parameter values ​​of the target modeling parameters based on the target curvature includes:

[0019] Based on the curvature of each sub-boom curve, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve;

[0020] The boom space model includes space models of multiple sub-booms, the multiple sub-booms correspond to the curves of the multiple sub-booms, and the space model of each sub-boom is constructed based on the sub-modeling parameters corresponding to the sub-boom.

[0021] In some embodiments, dividing the boom curve to obtain the plurality of sub-boom curves includes:

[0022] Based on the length of the boom and the preset maximum error, a first quantity is determined, wherein the preset maximum error is the maximum allowable error for boom anti-collision calculation;

[0023] The boom curve is divided into equal intervals to obtain the first number of sub-boom curves.

[0024] In some implementations, before determining the sub-modeling parameter value corresponding to each sub-boom curve based on the curvature of each sub-boom curve, the method further includes:

[0025] Multiple sampling points were determined in the boom curve;

[0026] Determine the curvature of at least one of the plurality of sampling points;

[0027] The step of determining the sub-modeling parameter values ​​corresponding to the sub-boom curves based on the curvature of each sub-boom curve includes:

[0028] Based on the curvature of each of the sub-boom curves and the curvature of the at least one sampling point, the sub-modeling parameter values ​​corresponding to the sub-boom curves are determined.

[0029] In some implementations, multiple sampling points are determined in the boom curve, including:

[0030] Based on the length of the boom and the preset minimum error, a second quantity is determined, wherein the preset minimum error is the minimum allowable error for boom anti-collision calculation.

[0031] A second number of sampling points are selected at equal intervals along the boom curve.

[0032] In some implementations, determining the sub-modeling parameter value corresponding to the sub-boom curve based on the curvature of each of the sub-boom curves and the curvature of the plurality of sampling points includes:

[0033] Among the curvatures of each of the plurality of sampling points, determine the maximum curvature and the minimum curvature;

[0034] Based on the curvature of each sub-boom curve, as well as the maximum curvature and the minimum curvature, the sub-modeling parameter values ​​corresponding to the sub-boom curves are determined.

[0035] In some implementations, the number of sub-boom curves is a first number, and the number of sampling points is a second number.

[0036] The determination of sub-modeling parameter values ​​corresponding to each sub-boom curve based on the curvature of each sub-boom curve, as well as the maximum curvature and the minimum curvature, includes:

[0037] Based on the curvature of each sub-boom curve, as well as the maximum curvature, the minimum curvature, the preset minimum error, and the preset maximum error, the sub-modeling parameter values ​​corresponding to the sub-boom curve are calculated.

[0038] In some implementations, before performing collision avoidance detection based on the boom space model and generating the collision avoidance detection result for the boom, the method further includes:

[0039] Acquire second point cloud data of obstacles around the boom;

[0040] An obstacle space model of the obstacle is generated based on the second point cloud data;

[0041] The step of performing collision avoidance detection based on the boom space model and generating collision avoidance detection results for the boom includes:

[0042] Collision avoidance detection is performed on the boom space model and the obstacle space model to generate the collision avoidance detection results for the boom.

[0043] In some implementations, the modeling parameters include model mesh resolution, which is negatively correlated with the target curvature.

[0044] Secondly, embodiments of this application also provide a collision avoidance detection device for a boom, comprising:

[0045] The point cloud data acquisition module is used to acquire the first point cloud data of the boom;

[0046] The curve fitting module is used to perform curve fitting on the first point cloud data to obtain the boom curve of the boom.

[0047] A curvature determination module is used to determine the target curvature of the boom based on the boom curve;

[0048] The modeling parameter value determination module is used to determine target modeling parameter values ​​based on the target curvature, wherein the target modeling parameter values ​​are parameter values ​​for modeling parameters used in spatial modeling;

[0049] The modeling module is used to perform spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain the boom curvature boom spatial model.

[0050] The collision avoidance detection module is used to perform collision avoidance detection based on the boom space model and generate collision avoidance detection results for the boom. The collision avoidance detection results are used to indicate obstacles that pose a collision risk with the boom.

[0051] Thirdly, embodiments of this application provide an electronic device, the device including: a processor and a memory storing computer program instructions;

[0052] When the processor executes computer program instructions, it implements the anti-collision detection method for the boom as described in the first aspect.

[0053] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the anti-collision detection method for the boom as described in the first aspect.

[0054] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the anti-collision detection method for the boom as described in the first aspect.

[0055] In a sixth aspect, embodiments of this application provide a working machine, including a boom, a point cloud acquisition device, and electronic equipment as described in the third aspect.

[0056] The present application discloses a method, apparatus, device, and computer storage medium for anti-collision detection of a boom, which acquires first point cloud data of the boom; performs curve fitting on the first point cloud data to obtain a boom curve; determines a target curvature of the boom based on the boom curve; determines target modeling parameter values ​​based on the target curvature, the target modeling parameter values ​​being parameter values ​​for modeling parameters used in spatial modeling; performs spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain a boom curvature boom spatial model; performs anti-collision detection based on the boom spatial model to generate anti-collision detection results of the boom, the anti-collision detection results being used to indicate obstacles that pose a collision risk with the boom. Thus, since the boom space model is constructed based on the boom's point cloud data, the acquisition of point cloud data is less affected by scene changes compared to image recognition technology. This improves the detection accuracy of obstacles that pose a collision risk with the boom, thereby enhancing the accuracy of boom collision avoidance detection. Furthermore, since the modeling parameter values ​​used in the model construction are determined based on the boom's target curvature, the impact of boom deformation during operation on the accuracy of the constructed boom space model is considered, further improving the accuracy of the constructed boom space model, and consequently further enhancing the detection accuracy of obstacles that pose a collision risk with the boom. Attached Figure Description

[0057] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 is a flowchart illustrating an embodiment of the anti-collision detection method for boom provided in this application;

[0059] Figure 2 is a flowchart illustrating an application example of the anti-collision detection method for the boom provided in this application;

[0060] Figure 3 is a structural schematic diagram of an embodiment of the anti-collision detection device for the boom provided in this application;

[0061] Figure 4 is a structural schematic diagram of an embodiment of the electronic device provided in this application. Detailed Implementation

[0062] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0063] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0064] Figure 1 shows a flowchart of an embodiment of the anti-collision detection method for a boom provided in this application. The anti-collision detection method for a boom provided in this application can be applied to electronic devices, which may be central control devices within the operating machinery including the boom, or smartphones, laptops, or servers (such as cloud servers) outside the operating machinery. As shown in Figure 1, the anti-collision detection method for a boom provided in this application includes the following steps:

[0065] Step S101: Obtain the first point cloud data of the boom;

[0066] Step S102: Perform curve fitting on the first point cloud data to obtain the boom curve of the boom;

[0067] Step S103: Determine the target curvature of the boom based on the boom curve;

[0068] Step S104: Based on the target curvature, determine the target modeling parameter values, which are the parameter values ​​of the modeling parameters used for spatial modeling;

[0069] Step S105: Perform spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain the boom curvature boom spatial model;

[0070] Step S106: Perform collision avoidance detection based on the boom space model to generate collision avoidance detection results for the boom. The collision avoidance detection results are used to indicate obstacles that pose a collision risk with the boom.

[0071] In this embodiment, the process involves: acquiring first point cloud data of the boom; performing curve fitting on the first point cloud data to obtain the boom curve; determining the target curvature of the boom based on the boom curve; determining target modeling parameter values ​​based on the target curvature, where the target modeling parameter values ​​are the parameter values ​​of the modeling parameters used for spatial modeling; performing spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain a boom curvature boom spatial model; and performing collision avoidance detection based on the boom spatial model to generate collision avoidance detection results for the boom, where the collision avoidance detection results are used to indicate obstacles that pose a collision risk with the boom. Thus, since the boom space model is constructed based on the boom's point cloud data, the acquisition of point cloud data is less affected by scene changes compared to image recognition technology. This improves the detection accuracy of obstacles that pose a collision risk with the boom, thereby enhancing the accuracy of boom collision avoidance detection. Furthermore, since the modeling parameter values ​​used in the model construction are determined based on the boom's target curvature, the impact of boom deformation during operation on the accuracy of the constructed boom space model is considered, further improving the accuracy of the constructed boom space model, and consequently further enhancing the detection accuracy of obstacles that pose a collision risk with the boom.

[0072] In step 101 above, the acquisition of the first point cloud data of the boom can be achieved by real-time point cloud sensing and detection of point cloud data through a point cloud acquisition device during boom movement. The point cloud data includes the first point cloud data of the boom, and the point cloud acquisition device transmits the detected point cloud data to an electronic device.

[0073] The boom described above is a structure in operating machinery, which can be a crane, a ladder fire truck, or a pump truck, etc.

[0074] The aforementioned point cloud acquisition device can be any device capable of point cloud sensing to detect point cloud data, and may include at least one of radars such as ultrasonic radar, lidar, and millimeter-wave radar. The point cloud data detected by this acquisition device (including the first point cloud data) can also be referred to as a 3D point cloud or simply a point cloud. It is a discrete dataset composed of a series of 3D coordinate points, each including coordinate values ​​in the X, Y, and Z directions, used to describe the geometric features of an object, such as its surface shape, spatial location, and dimensions. It should be noted that the point cloud acquisition device can be mounted on a boom or at other locations on the operating machinery, without limitation.

[0075] The aforementioned first point cloud data may include point cloud data of preset key parts in the boom, such as the location of hinge points, endpoints, and center of gravity.

[0076] The electronic device can acquire the first point cloud data by extracting the point cloud data of the preset key parts from the point cloud data detected by the point cloud acquisition device through feature extraction; or it can be based on the positioning of the key parts of the boom, that is, radar sensors are set in advance at the preset key parts to collect the point cloud data of the preset key parts, and the electronic device can directly obtain the point cloud data of the preset key parts from the point cloud data.

[0077] In step 102 above, when the electronic device acquires the first point cloud data, the electronic device can perform curve fitting on the first point cloud data to obtain the boom curve of the boom.

[0078] The above-mentioned curve fitting of the first point cloud data to obtain the boom curve can be achieved by electronic equipment using a preset curve fitting equation to fit the first point cloud data to obtain the boom curve.

[0079] In step 103 above, after fitting the boom curve, the electronic device can use the boom curve to determine the target curvature of the table.

[0080] The above-mentioned determination of the target curvature of the boom based on the boom curve can be achieved by acquiring an image of the boom curve and using image recognition technology to identify the curvature of the boom curve as the target curvature. The curvature of the boom curve can be understood as an approximate curvature or as the true curvature.

[0081] The target curvature can be the overall curvature of the boom curve. For example, it can be the approximate curvature of multiple nodes of the boom curve identified by image recognition technology, and the average of the approximate curvatures can be used as the target curvature. Alternatively, it can be the overall arc of the boom curve identified by image recognition technology, and the overall arc can be used as the target curvature.

[0082] In step 104 above, given the target curvature of the boom, the electronic device can determine the target modeling parameter value of the modeling parameters based on the target curvature.

[0083] The aforementioned modeling parameters can be any parameters in a target space modeling strategy (method) based on point cloud data, and when the parameter value of the modeling parameter changes, the three-dimensional space model constructed by the target space modeling strategy will also change.

[0084] The aforementioned target space modeling strategy may include at least one of the following: Boundary Representation Scheme (BRS), scan representation, constructive solid geometry, and spatial element representation. For example, when the aforementioned space modeling strategy is scan representation, the modeling parameter value may be the parameter value of at least one of the following: trajectory parameter, cross-section parameter, and scan type.

[0085] Furthermore, the aforementioned target space modeling strategy is an octree subdivision spatial meshing modeling strategy, and the aforementioned modeling parameters include the resolution (i.e., the minimum voxel size) of the octree subdivision spatial meshing modeling strategy, etc.

[0086] The above-mentioned determination of target modeling parameter values ​​based on target curvature can be achieved by having a pre-defined correspondence between curvature and modeling parameter values ​​in the electronic device, and the electronic device determining the modeling parameter values ​​that correspond to the target curvature as the target modeling parameter values.

[0087] For example, when the target space modeling strategy is a scanning representation, the electronic device may have a pre-defined correspondence between cross-sectional parameter values ​​and curvature. The electronic device can determine the cross-sectional parameter value corresponding to the target curvature as the target cross-sectional parameter value (i.e., the target modeling parameter value). Alternatively, when the target space modeling strategy is an octree subdivision spatial meshing modeling strategy, the electronic device may have a pre-defined correspondence between resolution and curvature. The electronic device can determine the resolution corresponding to the target curvature as the target resolution (i.e., the target modeling parameter value). In step 105 above, when the target modeling parameter value is determined, the electronic device can update the parameter values ​​of the modeling parameters of the target space modeling strategy to the target modeling parameter values, and use the updated target modeling strategy to model the first point cloud data to obtain the boom space model of the boom.

[0088] For example, when the target modeling strategy is the scanning representation, the electronic device updates the cross-sectional parameter values ​​of the scanning representation to the target cross-sectional parameter values ​​and uses the updated scanning representation to construct the boom space model; while when the spatial modeling strategy is the octree subdivision spatial meshing modeling strategy, the electronic device updates the resolution of the octree subdivision spatial meshing modeling strategy to the target resolution and uses the updated octree subdivision spatial meshing modeling strategy to construct the boom space model.

[0089] When the target modeling parameter values ​​mentioned above are determined by the overall curvature of the boom curve, the boom space model constructed above can be a three-dimensional space model of the entire boom.

[0090] In step 106 above, after generating the above boom space model, the electronic device performs collision avoidance detection based on the boom space model and generates collision avoidance detection results to identify obstacles that pose a collision risk with the boom.

[0091] The above-mentioned collision avoidance detection based on the boom space model and the generation of collision avoidance detection results can also be achieved by the electronic device acquiring the obstacle space model of the obstacles around the boom, performing collision avoidance detection on the boom space model and the obstacle space model, and obtaining the collision avoidance detection results.

[0092] The obstacle space model of the obstacles around the boom can be obtained by scanning with a scanning device (such as a scanner installed on the boom; or it can be a drone independent of the boom).

[0093] The above-mentioned collision avoidance detection of the boom space model and obstacle space model can be performed by calculating the minimum distance between the boom space model and each obstacle space model, and comparing the minimum distance between the boom space model and each obstacle space model with a preset distance threshold to obtain a comparison result; if the comparison result indicates that there is an obstacle space model whose minimum distance with the boom space model is less than or equal to the preset distance, a collision avoidance detection result is generated.

[0094] It should be noted that after generating the collision avoidance detection result, the electronic device may display the collision avoidance detection result; it may also generate alarm information based on the collision avoidance detection result and output the alarm information; furthermore, it may also perform collision avoidance operations based on the collision avoidance detection result, such as controlling the boom to stop moving or performing obstacle avoidance control, etc.

[0095] In some implementations, the target curvature of the boom is determined based on the boom curve, including:

[0096] The boom curve is divided into multiple sub-boom curves;

[0097] Based on each sub-boom curve, determine the curvature of the sub-boom curve, and the target curvature includes the curvature of multiple sub-boom curves;

[0098] Based on the target curvature, determine the parameter values ​​for the target modeling parameters, including:

[0099] Based on the curvature of each sub-boom curve, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve;

[0100] The boom space model includes multiple sub-boom space models, with multiple sub-boom curves corresponding to multiple sub-boom curves, and the space model of each sub-boom is constructed based on the sub-modeling parameters corresponding to the sub-boom.

[0101] In this embodiment, the boom curve can be divided into multiple sub-boom curves, and sub-modeling parameter values ​​corresponding to the curvature of each sub-boom curve can be determined. This allows the corresponding spatial model of the sub-boom to be constructed based on each sub-modeling parameter value during the modeling process, thereby realizing segmented modeling of the boom. This takes into account the impact of boom bending deformation on the computational redundancy of the modeling process. Compared with overall modeling, this can reduce the computational redundancy of the modeling and improve modeling efficiency.

[0102] The above-mentioned division of the boom curve into multiple sub-boom curves can be achieved by dividing the boom curve into multiple sub-boom curves according to a preset curve division rule. For example, the sub-boom curves can be irregularly divided according to key parts; or, the number of divisions can be preset, dividing the boom curve into the preset number of sub-boom curves at equal intervals.

[0103] The above method of determining the curvature of each sub-boom curve can be based on image recognition technology to identify the curvature of each sub-boom curve.

[0104] Alternatively, in some implementations, determining the curvature of a sub-boom curve based on each sub-boom curve may include: acquiring point cloud data of the two endpoints of the target sub-boom curve and acquiring point cloud data of the center point of the target sub-boom curve, wherein the target sub-boom curve is any one of multiple sub-boom curves; and calculating the curvature of the target sub-boom curve based on the point cloud data of the two endpoints and the center point of the target sub-boom curve. This can further improve the accuracy of the curvature calculation of the target sub-boom curve.

[0105] The curvature of the target sub-boom curve, calculated from the point cloud data of its two endpoints and the point cloud data of its center point, can be achieved using the following formula (1):

[0106] In the above formula (1), v1=[x i-1 -x i ,y i-1 -y i ,z i-1 -z i ];

[0107] v2 = [x i+1 -x i ,y i+1 -y i ,z i+1 -z i ];

[0108] (x i-1 ,y i-1,z i-1 ) and x i+1 ,y i+1 ,z i+1 These represent the point cloud data at the two endpoints respectively;

[0109] (x i ,y i ,z i () represents the point cloud data of the center point.

[0110] In some implementations, the boom curve is divided to obtain multiple sub-boom curves, including:

[0111] The first quantity is determined based on the boom length and the preset maximum error, where the preset maximum error is the maximum allowable error for boom anti-collision calculation.

[0112] The boom curve is divided into equal intervals to obtain the first number of sub-boom curves.

[0113] In this embodiment, a first number can be determined based on the boom length and a preset maximum error, and the boom curve can be divided into a first number of sub-boom curves at equal intervals, thereby making the divided sub-boom curves more suitable.

[0114] The determination of the first quantity based on the boom length and the preset maximum error can be achieved using the following formula (2):

[0115] In formula (2) above, Ceiling(·) represents the rounding up operation;

[0116] arm_length represents the length of the boom;

[0117] res_max represents the maximum allowable error in the boom collision avoidance calculation.

[0118] The res_max mentioned above can be set according to actual needs, or it can be determined based on experimental data; no restrictions are imposed here.

[0119] In the above implementation, the sub-modeling parameter value corresponding to the sub-boom curve is determined based on the curvature of each sub-boom curve. This can be achieved by pre-setting a correspondence between curvature and modeling parameter values ​​in the electronic device. The electronic device directly determines the modeling parameter value that corresponds to the curvature of the sub-boom curve as the sub-modeling parameter value corresponding to that sub-boom curve. In this case, the determination of the sub-modeling parameter value can depend only on the curvature of the corresponding sub-boom curve.

[0120] In some implementations, before determining the sub-modeling parameter values ​​corresponding to each sub-boom curve based on the curvature of each sub-boom curve, the method further includes:

[0121] Multiple sampling points were determined in the boom curve;

[0122] Determine the curvature of at least one of multiple sampling points;

[0123] Based on the curvature of each sub-boom curve, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve, including:

[0124] Based on the curvature of each sub-boom curve and the curvature of at least one sampling point, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve.

[0125] In this embodiment, the curvature of at least one sampling point among multiple sampling points in the boom curve can also be determined, and the curvature of each sub-boom curve and the curvature of at least one sampling point can be combined to determine the sub-modeling parameter value corresponding to the sub-boom curve, thereby making the determined sub-modeling parameter value more accurate.

[0126] The aforementioned determination of multiple sampling points in the boom curve can be achieved by selecting multiple sampling points in the boom curve according to preset sampling point selection rules. For example, the points where key parts are located can be determined as sampling points; or, the endpoints of the aforementioned multiple sub-boom curves can be determined as sampling points, and so on.

[0127] The determination of the curvature of at least one sampling point among multiple sampling points can be achieved by identifying the curvature of each sampling point using the aforementioned image recognition technology. The at least one sampling point can be all or some of the multiple sampling points.

[0128] Alternatively, in some implementations, determining the curvature of each sampling point among multiple sampling points may include: acquiring point cloud data of a target sampling point, and acquiring point cloud data of two neighboring sampling points on the boom curve adjacent to the target sampling point, wherein the target sampling point is a sampling point among multiple sampling points; and determining the curvature of the target sampling point based on the point cloud data of the target sampling point and the point cloud data of the two neighboring sampling points. This can improve the accuracy of determining the curvature of the sampling point.

[0129] The curvature of the target sampling point, based on the point cloud data of the target sampling point and the point cloud data of two neighboring sampling points, can be determined by the following formula (3):

[0130] In the above formula (3), v3=[x j-1 -x j ,y j-1 -y j ,z j-1 -z j V4 = [x] j+1 -x j ,y j+1 -yj ,z j+1 -z j ];

[0131] (x j-1 ,y j-1 ,z j-1 ) and (x j+1 ,y j+1 ,z j+1 () represent point cloud data of two adjacent sampling points respectively;

[0132] (x j ,y j ,z j ) represents the point cloud data of the target sampling point.

[0133] The above-mentioned determination of the sub-modeling parameter value corresponding to the sub-boom curve based on the curvature of each sub-boom curve and the curvature of at least one sampling point can be achieved by determining the average curvature of the at least one sampling point and determining the sub-modeling parameter value according to the pre-configured correspondence between the curvature of the sub-boom curve, the average curvature of the sampling point and the modeling parameter value.

[0134] In some implementations, multiple sampling points are determined in the boom curve, including:

[0135] Based on the boom length and the preset minimum error, a second quantity is determined, where the preset minimum error is the minimum allowable error for boom collision avoidance calculation.

[0136] A second number of sampling points are selected at equal intervals along the boom curve.

[0137] In this embodiment, a second quantity can be determined based on the boom length and a preset minimum error, and a second quantity of sampling points can be selected at equal intervals along the boom curve, thereby making the selected sampling points more suitable.

[0138] The second quantity, determined based on the boom length and the preset minimum error, can be achieved through the following formula (4):

[0139] In the above formula (4), res_min represents the maximum allowable error in the boom collision avoidance calculation.

[0140] The res_min mentioned above is less than the res_max mentioned above, and res_min can be set according to actual needs, or it can be determined based on experimental data, which is not limited here.

[0141] In some implementations, the sub-modeling parameter values ​​corresponding to the sub-boom curves are determined based on the curvature of each sub-boom curve and the curvature of multiple sampling points, including:

[0142] Among the curvatures at each of the multiple sampling points, determine the maximum and minimum curvatures;

[0143] Based on the curvature of each sub-boom curve, as well as the maximum and minimum curvature, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve.

[0144] In this embodiment, the sub-modeling parameter values ​​corresponding to the sub-boom curves can be determined based on the curvature of each sub-boom curve, as well as the maximum and minimum curvatures. This allows the influence of extreme curvatures at various positions in the sub-boom curves on the constructed boom space model to be considered, making the constructed boom space model more accurate.

[0145] The above-mentioned determination of the sub-modeling parameter values ​​corresponding to the sub-boom curves based on the curvature, maximum curvature, and minimum curvature of each sub-boom curve can be achieved through a pre-configured correspondence to determine the sub-modeling parameter values ​​corresponding to the curvature, maximum curvature, and minimum curvature of each sub-boom curve.

[0146] In some implementations, the number of sub-boom curves is a first number, and the number of sampling points is a second number.

[0147] Based on the curvature of each sub-boom curve, as well as its maximum and minimum curvature, determine the sub-modeling parameter values ​​corresponding to the sub-boom curves, including:

[0148] Based on the curvature of each sub-boom curve, as well as the maximum curvature, minimum curvature, preset minimum error, and preset maximum error, the sub-modeling parameter values ​​corresponding to the sub-boom curve are calculated.

[0149] In this embodiment, the sub-modeling parameter values ​​corresponding to each sub-boom curve can be calculated based on the curvature of each sub-boom curve, as well as the maximum curvature, minimum curvature, preset minimum error, and preset maximum error. This makes the calculated sub-modeling parameter values ​​more accurate and further improves the accuracy of the constructed boom space model.

[0150] The sub-modeling parameter values ​​corresponding to the sub-boom curves are calculated based on the curvature of each sub-boom curve, as well as the maximum curvature, minimum curvature, preset minimum error, and preset maximum error. This can be achieved through the following formula (5):

[0151] In the above formula (5), res_sub i This represents the sub-modeling parameter value corresponding to the i-th sub-boom curve;

[0152] cur_sub i Represents the curvature of the curve of the i-th sub-boom;

[0153] cur_min represents the maximum curvature among the curvatures of at least one of the above sampling points;

[0154] cur_max represents the maximum curvature among the curvatures of at least one of the above sampling points.

[0155] In some implementations, the method prior to step 106 includes:

[0156] Acquire second point cloud data of obstacles around the boom;

[0157] An obstacle spatial model of obstacles is generated based on the second point cloud data;

[0158] Collision avoidance detection is performed based on the boom spatial model, and the collision avoidance detection results of the boom are generated, including:

[0159] Collision avoidance detection is performed on the boom space model and obstacle space model to generate the boom collision avoidance detection results.

[0160] In this embodiment, three-dimensional spatial modeling can be performed using the second point cloud data of obstacles around the boom to obtain an obstacle spatial model, thereby making the constructed obstacle spatial model more accurate and further improving the detection accuracy of obstacles that pose a collision risk with the boom.

[0161] The electronic device acquires the second point cloud data by first constructing a bounding box of the boom based on the first point cloud data, removing the first point cloud data from the point cloud data detected by the point cloud acquisition device, and retaining the center point position of the bounding box of the boom; then, expanding the size range of the bounding box based on the center point position to construct a bounding box for the obstacle perception range of the boom, retaining the point cloud data of the obstacles around the boom; finally, removing the point cloud data of obstacles whose spatial distance from the boom exceeds a preset distance to obtain the second point cloud data, thereby avoiding interference from the point cloud data of the boom on the construction of the obstacle spatial model.

[0162] It should be noted that the spatial modeling strategy used to construct the obstacle space model and the spatial modeling strategy used to construct the boom space model can be the same. For example, both the boom space model and the obstacle space model can be constructed using the octree subdivision spatial meshing modeling strategy in spatial unit representation. Alternatively, the spatial modeling strategies used to construct the boom space model and the obstacle space model can also be different. For example, the boom space model can be constructed using the octree subdivision spatial meshing modeling strategy, while the obstacle space model can be constructed using the solid geometry method. This is not a limitation.

[0163] In addition, the aforementioned obstacle space model can be an obstacle space model that includes one or more obstacles located within a preset detection range around the boom, that is, the obstacle space model generated by the electronic device includes at least one obstacle.

[0164] In some implementations, the parameter values ​​of the modeling parameters may include the model mesh resolution (e.g., the resolution of the octree subdivision spatial meshing modeling strategy), which is negatively correlated with the target curvature. That is, the larger the target curvature, the smaller the model mesh resolution, thereby further reducing the impact of boom deformation on the accuracy of the constructed boom spatial model.

[0165] To facilitate understanding of the anti-collision detection method for the boom of this application, an application example of the anti-collision detection method for the boom is provided here, as shown in Figure 2, as follows:

[0166] Based on a lidar sensor (i.e., a point cloud acquisition device) mounted on the boom, the system scans the boom and its surrounding environment in real time to acquire point cloud information (i.e., point cloud data). Then, data processing and algorithm analysis are performed simultaneously to achieve boom body modeling, obstacle detection, and collision avoidance calculation. Specifically, it includes two parts: long and flexible boom body modeling and obstacle detection and collision avoidance calculation.

[0167] 1. Spatial modeling of the long flexible boom body

[0168] Due to their own weight and load, long flexible boom machinery will experience a certain degree of deflection deformation during actual operation. To account for the impact of boom deformation on collision avoidance calculations, a flexible boom body is constructed using boom deformation data. Collision avoidance calculations are then performed based on information about surrounding obstacles and the environment, which can significantly improve the accuracy of calculations for long flexible booms. The specific process is as follows:

[0169] Step 1.1: Based on the lidar sensor installed at the starting end of the long flexible boom, scan the boom body in real time and acquire point cloud data to obtain the real-time orientation of the key positions of the boom (including the end and middle key position points). Optionally, the implementation method may include: (1) non-contact measurement: target identification and positioning of the key position point cloud of the boom based on feature extraction analysis; (2) contact measurement: positioning based on the position of the key position marker points of the boom.

[0170] Step 1.2: Based on the real-time orientation of the key positions of the boom (including the end and middle key positions) obtained in Step 1.1, construct the boom curve equation (i.e. boom curve) from the start end to the end end of the boom through curve fitting, and realize the mathematical modeling of boom deformation.

[0171] Step 1.3: Based on the boom curve equation output in Step 1.2, the long flexible boom is spatially modeled using the octree subdivision spatial meshing modeling method. The octree subdivision spatial meshing modeling method can use a uniform octree resolution (i.e., model mesh resolution).

[0172] Considering that the degree of bending deformation varies greatly at different locations of the boom during actual operation, a multi-scale octree spatial modeling method based on the change of boom deformation curvature is adopted. For locations with smaller boom deformation curvature, i.e., lower degree of boom deformation bending, a larger octree resolution is used for boom spatial modeling. Conversely, for locations with larger boom deformation curvature, i.e., higher degree of boom deformation bending, a smaller octree resolution is used for boom spatial modeling.

[0173] Step 1.4: Set the octree resolution range, where res_min and res_max are the minimum and maximum octree resolutions, respectively. The curvature setting criteria for this range are: res_min is the minimum allowable error for boom collision avoidance calculation, and res_max is the maximum allowable error for boom collision avoidance calculation.

[0174] Step 1.5: Based on the boom curve equation output in Step 1.2, select j sampling points at equal intervals. The calculation method for the number of sampling points is shown in Formula (4).

[0175] Step 1.6: Calculate the curvature of the j sampling points in Step 1.5, and obtain the curvature ranges cur_min and cur_max. The curvature calculation formula for each sampling point is shown in Formula (3).

[0176] Step 1.7: Octree spatial modeling of the long flexible boom. The segmented spatial modeling method with equal interval sampling is adopted. Based on the boom curve equation output in Step 1.2, the current boom is divided into equal intervals, which are divided into N groups of sub-boom spaces (i.e. sub-boom curves). The calculation method of N is shown in Formula (2).

[0177] Step 1.8: For the N groups of sub-boom spaces divided in Step 1.7, calculate the curvature of each group of sub-booms. Refer to Formula (1) for the calculation formula to obtain the curvature cur_sub of the sub-boom space. i .

[0178] Step 1.9: Based on the calculated spatial curvature cur_sub of the sub-arm i Based on the octree resolution allocation principle in step 1.3, the current subspace octree modeling resolution res_sub is calculated, and the calculation formula is referenced in formula (5).

[0179] Step 1.10: Based on the above steps, complete the octree space modeling of the overall long flexible boom and generate the boom space model.

[0180] 2. Obstacle detection and collision avoidance calculation

[0181] Based on the spatial modeling results of the long flexible boom output from the aforementioned steps, anti-collision calculations are performed with obstacles in the space surrounding the boom, and the anti-collision distance is output to control the boom to stop or bypass.

[0182] Step 2.1: Based on the boom deformation data and boom space modeling results from the previous steps, construct the boom body bounding box, remove the boom body point cloud data within the LiDAR scanning range, and eliminate the interference of the boom body on obstacle detection.

[0183] Step 2.2: Based on the bounding box of the boom body constructed in Step 2.1, retain the position of its center point, expand the size range of the bounding box, construct the bounding box of the boom obstacle perception range, retain the point cloud data of obstacles around the boom, remove the data of obstacles that are far away from the boom, and improve the efficiency of collision avoidance calculation.

[0184] Step 2.3: Based on the obstacle point cloud data obtained in Step 2.2, set the octree resolution and output the obstacle octree spatial modeling result (i.e., generate the obstacle spatial model).

[0185] Step 2.4: Based on the overall long flexible boom octree space modeling and obstacle octree space modeling results output from the above steps, perform collision avoidance calculations, output the collision avoidance distance and the location of the nearest obstacle to the boom, and guide the boom control system to implement boom stopping and obstacle avoidance control.

[0186] The anti-collision detection method for booms provided in this application can be executed by an anti-collision detection device for the boom. This application uses an anti-collision detection device for the boom to execute the anti-collision detection method as an example to illustrate the anti-collision detection device for the boom provided in this application.

[0187] Figure 3 shows a schematic diagram of the anti-collision detection device for the boom provided in an embodiment of this application. As shown in Figure 3, the anti-collision detection device 300 for the boom of this application includes:

[0188] Point cloud data acquisition module 301 is used to acquire the first point cloud data of the boom;

[0189] The curve fitting module 302 is used to perform curve fitting on the first point cloud data to obtain the boom curve of the boom.

[0190] The curvature determination module 303 is used to determine the target curvature of the boom based on the boom curve;

[0191] The modeling parameter value determination module 304 is used to determine the target modeling parameter values ​​based on the target curvature. The target modeling parameter values ​​are the parameter values ​​of the modeling parameters used for spatial modeling.

[0192] Modeling module 305 is used to perform spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain the boom curvature boom spatial model.

[0193] The collision avoidance detection module 306 is used to perform collision avoidance detection based on the boom space model and generate collision avoidance detection results for the boom. The collision avoidance detection results are used to indicate obstacles that pose a collision risk with the boom.

[0194] In some implementations, the modeling parameter value determination module 304 is specifically used for:

[0195] The boom curve is divided into multiple sub-boom curves;

[0196] Based on each sub-boom curve, determine the curvature of the sub-boom curve, and the target curvature includes the curvature of multiple sub-boom curves;

[0197] Based on the curvature of each sub-boom curve, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve;

[0198] The boom space model includes multiple sub-boom space models, with multiple sub-boom curves corresponding to multiple sub-boom curves, and the space model of each sub-boom is constructed based on the sub-modeling parameters corresponding to the sub-boom.

[0199] In some implementations, the modeling parameter value determination module 304 is specifically used for:

[0200] The first quantity is determined based on the boom length and the preset maximum error, where the preset maximum error is the maximum allowable error for boom anti-collision calculation.

[0201] The boom curve is divided into equal intervals to obtain the first number of sub-boom curves.

[0202] In some implementations, the modeling parameter value determination module 304 is also specifically used for:

[0203] Multiple sampling points were determined in the boom curve;

[0204] Determine the curvature of at least one of multiple sampling points;

[0205] Based on the curvature of each sub-boom curve and the curvature of at least one sampling point, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve.

[0206] In some implementations, the modeling parameter value determination module 304 is specifically used for:

[0207] Based on the boom length and the preset minimum error, a second quantity is determined, where the preset minimum error is the minimum allowable error for boom collision avoidance calculation.

[0208] A second number of sampling points are selected at equal intervals along the boom curve.

[0209] In some implementations, the modeling parameter value determination module 304 is specifically used for:

[0210] Among the curvatures at each of the multiple sampling points, determine the maximum and minimum curvatures;

[0211] Based on the curvature of each sub-boom curve, as well as the maximum and minimum curvature, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve.

[0212] In some implementations, the number of sub-boom curves is a first number, and the number of sampling points is a second number.

[0213] Modeling parameter value determination module 304 is specifically used for:

[0214] Based on the curvature of each sub-boom curve, as well as the maximum curvature, minimum curvature, preset minimum error, and preset maximum error, the sub-modeling parameter values ​​corresponding to the sub-boom curve are calculated.

[0215] In some implementations, the point cloud data acquisition module 301 is further used for:

[0216] Acquire second point cloud data of obstacles around the boom;

[0217] Modeling module 305 is also used for:

[0218] An obstacle spatial model of obstacles is generated based on the second point cloud data;

[0219] The anti-collision detection module 306 is specifically used for:

[0220] Collision avoidance detection is performed on the boom space model and obstacle space model to generate the boom collision avoidance detection results.

[0221] In some implementations, the modeling parameters include the model mesh resolution, which is negatively correlated with the target curvature.

[0222] The anti-collision detection device for the boom provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0223] Figure 4 shows a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application.

[0224] An electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0225] Specifically, the processor 401 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0226] Memory 402 may include mass storage for data or instructions. For example, and not limitingly, memory 402 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 402 is non-volatile solid-state memory.

[0227] In some embodiments, memory 402 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0228] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any of the anti-collision detection methods for the boom in the above embodiments.

[0229] In one example, the electronic device may also include a communication interface 403 and a bus 410. As shown in Figure 4, the processor 401, memory 402, and communication interface 403 are connected via the bus 410 and communicate with each other.

[0230] The communication interface 403 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0231] Bus 410 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 410 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0232] The electronic device can execute the anti-collision detection method for the boom in the embodiments of this application, thereby realizing the anti-collision detection method and apparatus for the boom described in conjunction with Figures 1 to 3.

[0233] Furthermore, in conjunction with the boom collision detection method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the boom collision detection method in the above embodiments.

[0234] In conjunction with the anti-collision detection method for the boom in the above embodiments, this application embodiment can provide a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device implements the anti-collision detection method for the boom in the above embodiments.

[0235] In conjunction with the electronic devices in the above embodiments, this application embodiment can provide a working machine, which includes a boom, a point cloud acquisition device, and the electronic devices in the above embodiments.

[0236] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0237] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0238] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0239] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, 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, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0240] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for collision avoidance detection of a boom, comprising: Obtain the first point cloud data of the boom; Curve fitting is performed on the first point cloud data to obtain the boom curve of the boom; Based on the boom curve, determine the target curvature of the boom; Based on the target curvature, target modeling parameter values ​​are determined, which are parameter values ​​of modeling parameters used for spatial modeling; Spatial modeling is performed on the first point cloud data based on the target modeling parameter values ​​to obtain the boom spatial model of the boom; Collision avoidance detection is performed based on the boom space model to generate collision avoidance detection results for the boom. These results are used to indicate obstacles that pose a collision risk to the boom.

2. The method according to claim 1, wherein, Determining the target curvature of the boom based on the boom curve includes: The boom curve is divided to obtain multiple sub-boom curves; Based on each of the sub-boom curves, the curvature of the sub-boom curves is determined, and the target curvature includes the curvature of the plurality of sub-boom curves; The process of determining the parameter values ​​of the target modeling parameters based on the target curvature includes: Based on the curvature of each sub-boom curve, determine the sub-modeling parameter values ​​corresponding to the sub-boom curve; The boom space model includes space models of multiple sub-booms, the multiple sub-booms correspond to the curves of the multiple sub-booms, and the space model of each sub-boom is constructed based on the sub-modeling parameters corresponding to the sub-boom.

3. The method according to claim 2, wherein, The process of dividing the boom curve to obtain the plurality of sub-boom curves includes: Based on the length of the boom and the preset maximum error, a first quantity is determined, wherein the preset maximum error is the maximum allowable error for boom anti-collision calculation; The boom curve is divided into equal intervals to obtain the first number of sub-boom curves.

4. The method according to claim 2, wherein, Before determining the sub-modeling parameter value corresponding to each sub-boom curve based on the curvature of each sub-boom curve, the method further includes: Multiple sampling points were determined in the boom curve; Determine the curvature of at least one of the plurality of sampling points; The step of determining the sub-modeling parameter values ​​corresponding to the sub-boom curves based on the curvature of each sub-boom curve includes: Based on the curvature of each of the sub-boom curves and the curvature of the at least one sampling point, the sub-modeling parameter values ​​corresponding to the sub-boom curves are determined.

5. The method according to claim 4, wherein, Multiple sampling points were determined in the boom curve, including: Based on the length of the boom and the preset minimum error, a second quantity is determined, wherein the preset minimum error is the minimum allowable error for boom anti-collision calculation. A second number of sampling points are selected at equal intervals along the boom curve.

6. The method according to claim 4, wherein, The determination of sub-modeling parameter values ​​corresponding to the sub-boom curves based on the curvature of each sub-boom curve and the curvature of at least one sampling point includes: Among the curvatures of each of the plurality of sampling points, determine the maximum curvature and the minimum curvature; Based on the curvature of each sub-boom curve, as well as the maximum curvature and the minimum curvature, the sub-modeling parameter values ​​corresponding to the sub-boom curves are determined.

7. The method according to claim 6, wherein, The number of sub-arm curves is a first number, and the number of sampling points is a second number. The determination of sub-modeling parameter values ​​corresponding to each sub-boom curve based on the curvature of each sub-boom curve, as well as the maximum curvature and the minimum curvature, includes: Based on the curvature of each sub-boom curve, as well as the maximum curvature, the minimum curvature, the preset minimum error, and the preset maximum error, the sub-modeling parameter values ​​corresponding to the sub-boom curve are calculated.

8. The method according to claim 1, wherein, Before performing collision avoidance detection based on the boom space model and generating the collision avoidance detection result for the boom, the method further includes: Acquire second point cloud data of obstacles around the boom; An obstacle space model of the obstacle is generated based on the second point cloud data; The step of performing collision avoidance detection based on the boom space model and generating collision avoidance detection results for the boom includes: Collision avoidance detection is performed on the boom space model and the obstacle space model to generate the collision avoidance detection results for the boom.

9. The method according to claim 1, wherein, The modeling parameters include the model mesh resolution, which is negatively correlated with the target curvature.

10. A collision avoidance detection device for a boom, comprising: The point cloud data acquisition module is used to acquire the first point cloud data of the boom; The curve fitting module is used to perform curve fitting on the first point cloud data to obtain the boom curve of the boom. A curvature determination module is used to determine the target curvature of the boom based on the boom curve; The modeling parameter value determination module is used to determine target modeling parameter values ​​based on the target curvature, wherein the target modeling parameter values ​​are parameter values ​​for modeling parameters used in spatial modeling; The modeling module is used to perform spatial modeling on the first point cloud data based on the target modeling parameter values ​​to obtain the boom spatial model of the boom; The collision avoidance detection module is used to perform collision avoidance detection based on the boom space model and generate collision avoidance detection results for the boom. The collision avoidance detection results are used to indicate obstacles that pose a collision risk with the boom.

11. An electronic device, the electronic device comprising: Processor and memory storing computer program instructions; When the processor executes the computer program instructions, it implements the anti-collision detection method for the boom as described in any one of claims 1-9.

12. A computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the anti-collision detection method for a boom as described in any one of claims 1-9.

13. A computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the anti-collision detection method for a boom as described in any one of claims 1-9.

14. A working machine, comprising a boom, a point cloud acquisition device, and the electronic equipment as described in claim 11.

Images