Collision detection method, device, equipment and medium for preventing over-detection

Abstract

The present invention provides a collision detection method for preventing over-detection, characterized by comprising: obtaining first point cloud data of N first objects, wherein N is an integer greater than or equal to 1; determining second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects; calculating the degree of match between the shape contour of the target object and the second point cloud data; when the degree of match is less than or equal to a preset threshold, removing the point cloud data within the shape contour and the difference point cloud data from the first point cloud data to obtain third point cloud data; and performing collision detection based on the third point cloud data to obtain a collision detection result. The present invention also provides a collision detection device, electronic device, and storage medium for preventing over-detection.

Description

Technical Field

[0001] The present invention relates to the field of robotics or intelligent logistics, and more particularly to a collision detection method, device, electronic device and storage medium for preventing over-detection. Background Art

[0002] When performing collision detection on tools under inspection in a simulated real-world scenario, image data or point cloud data can be used for collision detection. This often leads to over-detection. Over-detection occurs when a collision is detected in a virtual environment simulating the real-world scenario, but no collision occurs when the tool is executed in the real-world scenario.

[0003] For example, when using point cloud data for collision detection, the model of the tool being tested can be controlled in a virtual environment to perform collision detection against the point cloud data. However, due to factors such as point cloud fluctuations, noise, and acquisition accuracy, the point cloud data may not match the actual pose information of the object, which may lead to over-detection and inaccurate collision detection results. If a feasible planned path is abandoned, planning resources will be wasted. Summary of the Invention

[0004] In view of the above problems, the present invention provides a collision detection method, device, electronic device and storage medium capable of preventing over-detection.

[0005] One aspect of an embodiment of the present invention provides a collision detection method for preventing over-detection, characterized in that it includes: acquiring first point cloud data of N first objects, wherein N is an integer greater than or equal to 1; determining second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects; calculating the degree of matching between the shape contour of the target object and the second point cloud data; when the degree of matching is less than or equal to a preset threshold, removing the point cloud data within the shape contour and the difference point cloud data from the first point cloud data to obtain third point cloud data; and performing collision detection based on the third point cloud data to obtain a collision detection result.

[0006] According to an embodiment of the present invention, calculating the degree of matching between the shape outline of the target object and the second point cloud data includes: determining at least one initial common point between the shape outline and the second point cloud data in the same spatial coordinate system; using the at least one initial common point as a matching reference, calculating the matching common points between the shape outline and the second point cloud data; and determining the degree of matching based on the proportion of the matching common points occupying the second point cloud data.

[0007] According to an embodiment of the present invention, when the degree of matching is less than or equal to a preset threshold, the method further includes obtaining the difference point cloud data, specifically including: determining data in the second point cloud data that does not belong to the matching common points and the at least one initial common point as the difference point cloud data.

[0008] According to an embodiment of the present invention, the shape contour includes the contour of a first surface, and the step of removing the point cloud data and the difference point cloud data within the shape contour from the first point cloud data includes: determining the first surface of the target object, wherein the first surface includes the surface of the target object in contact with the tool to be detected; and based on the first surface, removing the point cloud data and the difference point cloud data within the shape contour.

[0009] According to an embodiment of the present invention, based on the first surface, removing the point cloud data within the shape outline and the difference point cloud data includes: extending from the first surface along the first direction, removing all point cloud data within a specific space, wherein the specific space is the projection space of the shape outline in the first direction, and the first direction is the negative direction of the first coordinate axis of the coordinate system where the target object posture is located.

[0010] According to an embodiment of the present invention, based on the first surface, removing the point cloud data within the shape contour and the difference point cloud data includes: removing the difference point cloud data outside the specific space according to the difference between the shape contour of the target object and the point cloud data of the target object.

[0011] According to an embodiment of the present invention, based on the first surface, removing the point cloud data within the shape contour and the difference point cloud data includes: removing the difference point cloud data of the first surface along the second direction, wherein the second direction is the positive direction of the first coordinate axis of the coordinate system where the target object posture is located.

[0012] Another aspect of an embodiment of the present invention provides a collision detection device for preventing over-detection, characterized in that it includes: a point cloud acquisition module for acquiring first point cloud data of N first objects, wherein N is an integer greater than or equal to 1; a target determination module for determining second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects; a matching calculation module for calculating the degree of matching between the shape contour of the target object and the second point cloud data; a point cloud removal module for removing the point cloud data and difference point cloud data within the shape contour from the first point cloud data to obtain third point cloud data when the degree of matching is less than or equal to a preset threshold; a collision detection module for performing collision detection on the planned moving path of the tool to be detected based on the third point cloud data, wherein the planned moving path includes the path of the tool to be detected moving from the starting planned position until it contacts the target object.

[0013] Another aspect of an embodiment of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the method as described above.

[0014] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method described above.

[0015] The embodiments of the present invention determine the range to be removed from the first point cloud data by calculating the degree of match between the shape outline of the target object and the second point cloud data. If the degree of match is less than or equal to a preset threshold, the point cloud data within the shape outline and the difference point cloud data are removed, and collision detection is performed based on the third point cloud data to obtain a collision detection result. The shape outline of the target object can be compared with the second point cloud data to avoid the situation where the point cloud data of the target object and the object pose information of the target object do not match due to factors such as point cloud fluctuations, noise, and acquisition accuracy, thereby improving collision detection accuracy and saving planning resources.

[0016] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0018] Figure 1 A flowchart of a collision detection method for preventing over-detection according to an embodiment of the present invention is schematically shown;

[0019] Figure 2 Schematically shows a flow chart of calculating the degree of matching according to an embodiment of the present invention;

[0020] Figure 3 Schematically shows a flow chart for obtaining third point cloud data according to an embodiment of the present invention;

[0021] Figure 4 A schematic diagram schematically illustrates removing point cloud data within a shape outline according to an embodiment of the present invention;

[0022] Figure 5 A schematic diagram illustrating the removal of point cloud data within a shape outline and difference point cloud data according to an embodiment of the present invention is shown;

[0023] Figure 6 A schematic diagram schematically illustrates removing point cloud data within a shape outline and difference point cloud data according to another embodiment of the present invention;

[0024] Figure 7 Schematically shows a schematic diagram of removing point cloud data within a shape outline according to another embodiment of the present invention;

[0025] Figure 8 Schematically shows a schematic diagram of removing point cloud data within a shape outline and difference point cloud data according to another embodiment of the present invention;

[0026] Figure 9 Schematically shows a schematic diagram of removing point cloud data within a shape outline and difference point cloud data according to another embodiment of the present invention;

[0027] Figure 10 Schematically shows a structural block diagram of a collision detection device for preventing over-detection according to an embodiment of the present invention;

[0028] Figure 11 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0029] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0030] Figure 1The flowchart of the collision detection method for preventing over-detection according to an embodiment of the present invention is schematically shown.

[0031] like Figure 1 As shown, the collision detection method of this embodiment includes operations S110 to S150.

[0032] In operation S110 , first point cloud data of N first objects is acquired, where N is an integer greater than or equal to 1;

[0033] The N first objects may be N objects to be grasped. Point cloud data of all objects in the inspection area may be obtained, and then the first point cloud data may be further determined. The point cloud data may be obtained using a point cloud device using laser measurement principles or photogrammetry principles. The point cloud device may include a laser scanner, a depth camera, a binocular camera, or other devices.

[0034] In operation S120, second point cloud data of a target object is determined from the first point cloud data, wherein the target object is determined from the N first objects;

[0035] For example, image data of N first objects is obtained, and a preset target detection algorithm is invoked to perform target extraction processing on the image data to identify the target object. Based on the pixel coordinate values ​​of each pixel of the target object in the image data, second point cloud data of the target object is determined from the first point cloud data through coordinate conversion and other processing.

[0036] In operation S130 , a matching degree between the shape outline of the target object and the second point cloud data is calculated;

[0037] The shape outline can be obtained by edge detection of the target object image, and the coordinate information of the shape outline is obtained to adjust the position of the target object's CAD model in the spatial coordinate system. The degree of matching can be calculated by matching the target object's CAD model with the point cloud data in the same spatial coordinate system.

[0038] In operation S140, when the matching degree is less than or equal to a preset threshold, the point cloud data within the shape outline and the difference point cloud data are removed from the first point cloud data to obtain third point cloud data;

[0039] In operation S150 , collision detection is performed based on the third point cloud data to obtain a collision detection result.

[0040] For example, based on the third point cloud data, collision detection is performed on the planned movement path of the tool to be inspected. The planned movement path includes the path of the tool to be inspected from the planned starting position until it contacts the target object. The tool to be inspected can be a fixture, such as a suction cup or gripper. It should be noted that the tool to be inspected can also be connected to a component such as a robotic arm, and collision detection can be performed on the movement path of the robotic arm and the tool to be inspected.

[0041] The planned starting position of the tool to be inspected can be any location, which can be considered the origin of the planned movement path. The path from the origin to the point of contact with the target object is the planned movement path. For example, after determining the target object, the gripping point position of the target object can be obtained. When the tool to be inspected moves to the gripping point position, it can be considered to be in contact with the target object.

[0042] The collision detection process may include first planning a path for a model of the tool to be inspected in a virtual environment, which also includes third point cloud data. Then, the model of the tool to be inspected is controlled to move within the virtual environment along the planned path. Next, the model of the tool to be inspected is moved to a grasping point position of the target object and a grasping action is performed. In some embodiments, the model of the tool to be inspected may also be controlled to grasp the target object to a final position along the planned path.

[0043] During the collision detection process, the model of the tool to be detected is calculated to determine whether it collides with the third point cloud data in the virtual environment. The collision detection calculation can use a box algorithm to construct boxes for the model of the tool to be detected and the third point cloud data, and then determine whether the projections of the two boxes on the three coordinate axes intersect (for example only).

[0044] It should be noted that the collision detection method of the embodiment of the present invention is not limited to the grasping scenario, for example, it can also be applied to other scenarios where external force is applied to the target object by contact, such as pushing, pulling, and impacting the target object.

[0045] The embodiments of the present invention determine the range to be removed from the first point cloud data by calculating the degree of match between the shape outline of the target object and the second point cloud data. If the degree of match is less than or equal to a preset threshold, the point cloud data within the shape outline and the difference point cloud data are removed, and collision detection is performed based on the third point cloud data to obtain a collision detection result. The shape outline of the target object can be compared with the second point cloud data to avoid the situation where the point cloud data of the target object and the object pose information of the target object do not match due to factors such as point cloud fluctuations, noise, and acquisition accuracy, thereby improving collision detection accuracy and saving planning resources.

[0046] Figure 2The flowchart of calculating the matching degree in operation S130 according to an embodiment of the present invention is schematically shown.

[0047] like Figure 2 As shown, calculating the matching degree between the shape outline of the target object and the second point cloud data in operation S130 may include operations S210 to S230.

[0048] In operation S210 , at least one initial common point of the shape outline and the second point cloud data in the same spatial coordinate system is determined;

[0049] In operation S220 , the shape contour and the matching common points of the second point cloud data are calculated using the at least one initial common point as a matching reference;

[0050] Initial common points are points whose coordinates match those of the shape outline and the second point cloud data, which serve as the calculation basis. Other common points with the same coordinates between the two are then calculated as matching common points. To establish a comparison, the shape outline can be derived differently from the point cloud data, such as by edge detection on a 2D or 3D image. Point cloud data can be obtained using a laser scanner (for example).

[0051] In operation S230 , a matching degree is determined based on a ratio of the matching common points occupying the second point cloud data.

[0052] According to an embodiment of the present invention, when the degree of matching is less than or equal to a preset threshold, it also includes obtaining difference point cloud data, specifically including: determining data in the second point cloud data that does not belong to the matching common points and at least one initial common point as the difference point cloud data.

[0053] For example, in the spatial coordinate system, a point of the target object is determined as a common point in the CAD model and the second point cloud data for rough registration. The coarsely registered CAD model and point cloud data are then precisely registered using the iterative nearest neighbor (ICP) algorithm. Finally, the degree of match between the registered point cloud data and the CAD model is calculated. For example, if the proportion of matching common points and at least one initial common point in the point cloud data is 90%, the degree of match is considered to be 90%, and the difference is 10% (for example only). If the preset threshold is 95%, it is necessary to determine the difference point cloud data based on the difference to remove it.

[0054] In some embodiments, when the difference is 10%, after accurately registering which parts are common points, the remaining 10% can be considered as difference point cloud data.

[0055] Figure 3 The flowchart of obtaining the third point cloud data in operation S140 according to an embodiment of the present invention is schematically shown. Figure 4The figure schematically shows a schematic diagram of removing point cloud data within a shape outline according to an embodiment of the present invention.

[0056] like Figure 3 As shown, the step of removing the point cloud data within the shape outline and the difference point cloud data from the first point cloud data in operation S140 to obtain the third point cloud data includes operations S310 to S320.

[0057] In operation S310 , a first surface of a target object is determined, wherein the first surface includes a surface of the target object in contact with a tool to be inspected;

[0058] The first coordinate axis can be any one of the x-axis, y-axis and z-axis, such as Figure 4 As shown, the first coordinate axis is the z-axis. In the case where the tool to be detected is a suction cup, the suction cup can contact the first surface 410 of the target object 400 to perform a grasping operation. Figure 4 The directions of the x-axis, y-axis and z-axis of the coordinate system where the object posture of the target object 400 is located, and the projection range 420 of the shape outline of the target object 400 on a plane perpendicular to the first direction (direction A) are shown.

[0059] In operation S320 , based on the first surface, the point cloud data within the shape outline and the difference point cloud data are removed.

[0060] In some embodiments, based on the first surface, removing point cloud data and difference point cloud data within the shape outline includes: extending from the first surface along the first direction, removing all point cloud data within a specific space, wherein the specific space is the projection space of the shape outline in the first direction, and the first direction is the negative direction of the first coordinate axis of the coordinate system where the target object posture is located.

[0061] Reference Figure 4 For example, in a depalletizing application, the target object 400 may be a box on the top layer of a pallet, with the first surface 410 located at the top of the target object 400. It is assumed that the suction cup will not collide with objects below the target object 400 during the grasping process. Therefore, all point clouds, including noise points, extending from the first surface 410 in the first direction are removed.

[0062] Figure 4 The target object 400 shown in FIG is a cuboid, so the projection range of the shape outline in the first direction is the same as the area of ​​the first surface 410 , thereby extending in the negative direction along the first surface to remove all point cloud data within the shape outline.

[0063] Figure 5 The diagram schematically shows the removal of point cloud data within a shape outline and difference point cloud data according to an embodiment of the present invention.

[0064] In other embodiments, based on the first surface, removing the point cloud data and difference point cloud data within the shape contour includes: removing the difference point cloud data outside a specific space according to the difference between the shape contour of the target object and the point cloud data of the target object.

[0065] For example, facing the positive direction of the y-axis as the main viewing direction, Figure 5 FIG4 shows a top view of the target object 400. Due to the existence of point cloud fluctuations and other reasons, the point cloud data of the target object 400 may be larger than the shape outline of the target object 400. The range of the difference point cloud data is as follows: Figure 5 As shown in the oblique line portion 510.

[0066] If only the point cloud data within the shape outline is removed, and it is calculated that the tool to be detected is in contact with the point cloud data within the oblique line portion 510, the collision detection will be considered to have failed. In actual grasping scenarios, the point cloud data within the oblique line portion 510 also corresponds to the target object 400, and the tool to be detected is allowed to come into contact with it. Therefore, the purpose of removing the difference point cloud data outside of the specific space is to avoid over-detection (where there is no actual collision with other objects other than the target object, but a collision is detected).

[0067] Figure 6 The figure schematically shows a schematic diagram of removing point cloud data within a shape outline and difference point cloud data according to another embodiment of the present invention.

[0068] In other embodiments, based on the first surface, removing the point cloud data and difference point cloud data within the shape contour includes: removing the difference point cloud data of the first surface along the second direction, wherein the second direction is the positive direction of the first coordinate axis of the coordinate system where the target object posture is located.

[0069] like Figure 6 As shown, the CAD model and point cloud data can be bottom-aligned in the spatial coordinate system. The portion of the point cloud data that is above the first surface is the difference point cloud data. Therefore, when the point cloud data is above the object's pose, removing points in the negative z-axis direction (direction A) will not effectively remove the object's point cloud. However, additional point cloud removal along the positive z-axis direction (direction B) can be used.

[0070] Reference Figure 6 If only the point cloud data within the shape outline is removed, point cloud data will exist in the second direction of the first surface. In the process of simulating the movement of the fixture until it contacts the first surface, the fixture will inevitably come into contact with the difference point cloud data in the second direction of the first surface. In this case, the collision detection will be considered to have failed. In the actual grasping scenario, the fixture is allowed to come into contact with part of the point cloud data in the second direction of the first surface. Therefore, the purpose of removing the difference point cloud data along the second direction of the first surface is to avoid over-inspection.

[0071] It should be noted that the target object of the embodiment of the present invention is not limited to a rectangular parallelepiped, but can also be applied to regular-shaped solids such as prisms and cylinders, and can also be applied to irregular-shaped solids. It is sufficient that there is a surface on the target object that contacts the tool to be detected and can smoothly perform the preset action. For example, when the tool to be detected is a suction cup, there is a plane on the target object that can be sucked by the suction cup and can complete the grasping action. Figures 7 to 9 , describing a process of removing point cloud data within a shape outline and difference point cloud data from first point cloud data in another embodiment.

[0072] Figure 7 A schematic diagram of removing point cloud data within a shape outline according to yet another embodiment of the present invention is shown schematically. Figure 8 A schematic diagram of removing point cloud data within a shape outline and difference point cloud data according to yet another embodiment of the present invention is shown. Figure 9 A schematic diagram of removing point cloud data within a shape outline and difference point cloud data according to yet another embodiment of the present invention is shown.

[0073] like Figure 7 As shown, the target object 700 is a truncated cone, which gradually shrinks along the first direction (direction A, negative direction of the z-axis) from the first surface 710, and its shape outline is Figure 7 The black solid line of the truncated cone. Specific space 720 is the projection space of the shape outline of target object 700 along the first direction on the x-axis-y-axis plane. The area of ​​specific space 720 on the x-axis-y-axis plane is the same as the area of ​​first surface 710.

[0074] When using a suction cup to absorb the target object 700, all point cloud data within a specific space 720 can be removed by extending from the first surface 710 along direction A. Since the target object 700 is arranged with a larger object at the top and a smaller object at the bottom, removing all point cloud data within the specific space 720 also removes point cloud data within its shape outline.

[0075] like Figure 8 As shown, the top view of the target object 700 shows the first surface 710. If there is a difference between the contour of the first surface and the second point cloud data, the difference point cloud data outside the specific space is removed. It should be noted that the difference point cloud data outside the specific space is not infinitely removed. Figure 8 The point cloud within the difference point cloud data range 810 shown in FIG. Figure 9 When the second point cloud data is higher than the target object 700, the difference point cloud data of the first surface along the second direction (direction B, positive direction of the z-axis) is removed.

[0076] Based on the above-mentioned collision detection method for preventing over-detection, the present invention also provides a collision detection device for preventing over-detection. Figure 10 The device is described in detail.

[0077] Figure 10 The structure block diagram of the collision detection device 1000 for preventing over-detection according to an embodiment of the present invention is schematically shown.

[0078] like Figure 10 As shown, the collision detection device 1000 of this embodiment includes a point cloud acquisition module 1010 , a target determination module 1020 , a matching calculation module 1030 , a point cloud removal module 1040 , and a collision detection module 1050 .

[0079] The point cloud acquisition module 1010 may perform operation S110 for acquiring first point cloud data of N first objects, where N is an integer greater than or equal to 1;

[0080] The target determination module 1020 may perform operation S120 for determining second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects;

[0081] The matching calculation module 1030 may perform operation S130 for calculating a matching degree between the shape outline of the target object and the second point cloud data;

[0082] The matching calculation module 1030 can execute operations S210 to S230 to determine at least one initial common point between the shape outline and the second point cloud data in the same spatial coordinate system; use the at least one initial common point as a matching reference to calculate the matching common points between the shape outline and the second point cloud data; and determine the degree of matching based on the proportion of the matching common points in the second point cloud data.

[0083] The point cloud subtraction module 1040 may perform operation S140 for subtracting the point cloud data within the shape outline and the difference point cloud data from the first point cloud data to obtain third point cloud data when the matching degree is less than or equal to a preset threshold.

[0084] The point cloud removal module 1040 can perform operations S310 to S320 to determine the first surface of the target object, wherein the first surface includes the surface of the target object in contact with the tool to be detected; based on the first surface, remove the point cloud data within the shape contour and the difference point cloud data.

[0085] The collision detection module 1050 can perform operation S150 to perform collision detection on the planned moving path of the tool to be detected based on the third point cloud data, wherein the planned moving path includes the path of the tool to be detected moving from the starting planned position until it contacts the target object.

[0086] Figure 11 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0087] like Figure 11 As shown, the computing device may include: a processor (processor) 1102 , a communications interface (Communications Interface) 1104 , a memory (memory) 1106 , and a communication bus 1108 .

[0088] in:

[0089] The processor 1102 , the communication interface 1104 , and the memory 1106 communicate with each other via a communication bus 1108 .

[0090] The communication interface 1104 is used to communicate with other devices such as clients or other servers.

[0091] The processor 1102 is configured to execute the program 1110 , and specifically may execute the relevant steps in the above embodiments.

[0092] Specifically, the program 1110 may include program codes, which include computer operation instructions.

[0093] Processor 1102 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computing device may be of the same type, such as one or more CPUs, or may be of different types, such as one or more CPUs and one or more ASICs.

[0094] The memory 1106 is used to store the program 1110. The memory 1106 may include a high-speed RAM memory, and may also include a non-volatile memory (nonvolatile memory), such as at least one disk memory.

[0095] Program 1110 can be specifically configured to cause processor 1102 to execute any of the aforementioned method embodiments. The specific implementation of each step in program 1110 can be found in the corresponding descriptions of the corresponding steps and units in the aforementioned embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for ease and brevity of description, the specific working processes of the devices and modules described above can refer to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0096] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0097] The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus.

[0098] Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the embodiments of the present invention are not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0099] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0100] Similarly, it should be understood that in order to streamline the present invention and facilitate understanding of one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the inventive embodiments are sometimes grouped together into a single embodiment, figure, or description thereof. However, this inventive approach should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all of the features of a single embodiment of the preceding invention.

[0101] Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

[0102] Those skilled in the art will appreciate that the modules in the devices of the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into a plurality of submodules or subunits or subcomponents. All features of the invention in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so invented may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature of the invention in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0103] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination.

[0104] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0105] It should be noted that the above embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by a person skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments should not be understood as limiting the order of execution unless otherwise specified.

Claims

1. A collision detection method for preventing over-detection, characterized in that: include: Acquire first point cloud data of N first objects, where N is an integer greater than or equal to 1; Determining second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects; Calculating a matching degree between the shape outline of the target object and the second point cloud data; When the degree of matching is less than or equal to a preset threshold, removing the point cloud data within the shape outline and the difference point cloud data from the first point cloud data to obtain third point cloud data; Performing collision detection based on the third point cloud data to obtain a collision detection result; The shape contour includes a contour of a first surface, and removing the point cloud data and difference point cloud data within the shape contour from the first point cloud data includes: Determining a first surface of the target object, wherein the first surface includes a surface of the target object in contact with a tool to be detected; Based on the first surface, the point cloud data within the shape outline and the difference point cloud data are removed, specifically including: extending from the first surface along the first direction, and removing all point cloud data within a specific space, wherein the specific space is the projection space of the shape outline in the first direction, and the first direction is the negative direction of the first coordinate axis of the coordinate system where the target object posture is located.

2. The method according to claim 1, characterized in that Calculating the matching degree between the shape outline of the target object and the second point cloud data includes: Determining at least one initial common point between the shape outline and the second point cloud data in the same spatial coordinate system; Calculating matching common points between the shape outline and the second point cloud data using the at least one initial common point as a matching reference; The matching degree is determined based on a proportion of the second point cloud data occupied by the matching common points.

3. The method according to claim 2, characterized in that When the matching degree is less than or equal to a preset threshold, the method further includes obtaining the difference point cloud data, specifically including: Data in the second point cloud data that does not belong to the matching common points and the at least one initial common point is determined as the difference point cloud data.

4. The method according to claim 1, wherein Based on the first surface, removing the point cloud data within the shape outline and the difference point cloud data includes: According to the difference between the shape outline of the target object and the point cloud data of the target object, the difference point cloud data outside the specific space is removed.

5. The method according to claim 1, characterized in that Based on the first surface, removing the point cloud data within the shape outline and the difference point cloud data includes: The difference point cloud data of the first surface along the second direction is removed, wherein the second direction is the positive direction of the first coordinate axis of the coordinate system where the target object posture is located.

6. A collision detection device for preventing over-detection, characterized in that: include: a point cloud acquisition module, configured to acquire first point cloud data of N first objects, where N is an integer greater than or equal to 1; a target determination module, configured to determine second point cloud data of a target object from the first point cloud data, wherein the target object is determined from the N first objects; a matching calculation module, configured to calculate a matching degree between the shape outline of the target object and the second point cloud data; a point cloud subtraction module, configured to, when the degree of matching is less than or equal to a preset threshold, subtract the point cloud data within the shape outline and the difference point cloud data from the first point cloud data to obtain third point cloud data; a collision detection module, configured to perform collision detection on a planned movement path of the tool to be detected based on the third point cloud data, wherein the planned movement path includes a path of the tool to be detected moving from a planned starting position until it contacts the target object; The shape contour includes a contour of a first surface, and removing the point cloud data and difference point cloud data within the shape contour from the first point cloud data includes: Determining a first surface of the target object, wherein the first surface includes a surface of the target object in contact with a tool to be detected; Based on the first surface, the point cloud data within the shape outline and the difference point cloud data are removed, specifically including: extending from the first surface along the first direction, and removing all point cloud data within a specific space, wherein the specific space is the projection space of the shape outline in the first direction, and the first direction is the negative direction of the first coordinate axis of the coordinate system where the target object posture is located.

7. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 5.

Images