Collision judgment method, device, computer equipment and storage medium

Abstract

This application relates to a collision determination method, apparatus, computer device, and storage medium. The method comprises: obtaining to-be-processed motion data and basic data of a target object within a test area; calculating the target center of gravity of the target object based on the to-be-processed motion data and basic data; calculating a to-be-processed area based on the to-be-processed motion data; classifying the target objects based on the target center of gravity and the to-be-processed area; and performing collision testing on target objects belonging to the target classification. This method can reduce the number of walking training sessions for a simulated robot, thereby reducing resource usage.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a collision judgment method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the development of technology in the field of robotics, robots have gradually evolved from simply moving on flat roads to being able to move in uneven and unstructured environments, adapting to complex road conditions and achieving more diverse actions.

[0003] In order to maintain the stability of the robot when walking on complex roads and performing complex movements, before the robot is put into use, it needs to undergo multi-scenario walking training to simulate situations that may occur in life. In this way, the robot can learn which actions will cause the robot to fall in certain scenarios, thereby avoiding unstable walking of the robot.

[0004] However, the current walking training of simulated robots requires many experiments, resulting in a large amount of computation. Summary of the Invention

[0005] Based on this, it is necessary to provide a collision judgment method, device, computer equipment and storage medium that can reduce the number of walking training times of the simulated robot and thus reduce resource usage in order to address the above technical problems.

[0006] A collision judgment method, the method comprising:

[0007] Acquire the motion data to be processed and the basic data of the target object in the test area;

[0008] Calculating the target center of gravity of the target object according to the motion data to be processed and the basic data;

[0009] Calculating a region to be processed according to the motion data to be processed;

[0010] Classifying the target object according to the target center of gravity and the area to be processed;

[0011] A collision test is performed on the target object belonging to the target category.

[0012] In one embodiment, the calculating the target center of gravity of the target object according to the motion data to be processed and the basic data includes:

[0013] Calculate the minimum bounding box surrounding the target object based on the basic data;

[0014] Calculating the center of gravity of the minimum bounding box and adjusting the center of gravity of the bounding box based on the motion data to be processed;

[0015] The adjusted center of gravity of the bounding box is vertically mapped to the test area to obtain the target center of gravity of the target object.

[0016] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed includes:

[0017] Calculate a minimum area according to the motion data to be processed, and use the minimum area as the area to be processed;

[0018] The classifying the target object according to the target center of gravity and the area to be processed includes:

[0019] According to the center of gravity of the target object and the minimum area, the target object is classified to obtain a target object classification with the target center of gravity outside the minimum area and a target object classification with the target center of gravity within the minimum area, and the target object classification with the target center of gravity within the minimum area is grouped as a target classification.

[0020] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed includes:

[0021] Calculating a maximum area according to the motion data to be processed, and using the maximum area as an area to be processed;

[0022] The classifying the target object according to the target center of gravity and the area to be processed includes:

[0023] According to the target center of gravity and the maximum area, the target object is classified into a target object classification whose target center of gravity is outside the maximum area and a target object classification whose target center of gravity is within the maximum area, and the target object classification whose target center of gravity is not within the maximum area is classified as a non-target classification.

[0024] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed includes:

[0025] determining target motion data from the motion data to be processed according to the target center of gravity;

[0026] Calculating a non-target stable region according to the target motion data, and using the non-target stable region as a region to be processed;

[0027] The classifying the target object according to the center of gravity of the target object and the area to be processed includes:

[0028] According to the target center of gravity and the non-target stable area, the target object is classified to obtain a target object classification with the target center of gravity outside the non-target stable area and a target object classification with the target center of gravity within the non-target stable area, and the target object classification with the target center of gravity within the non-target stable area is used as a non-target classification.

[0029] In one embodiment, the target object includes at least four supporting components, and the maximum area, the minimum area, and the non-target stable area are calculated based on the to-be-processed motion data of the four supporting components; the minimum area corresponding to the target object is calculated based on the to-be-processed motion data, including:

[0030] determining projection points of the four supporting components onto the test area according to the to-be-processed motion data of the four supporting components respectively;

[0031] Obtaining a rectangle whose at least two sides are parallel to the target direction based on the coordinates of the projection point, and obtaining an overlapping area of ​​the rectangles as a minimum area;

[0032] The maximum area is calculated as follows:

[0033] The maximum value and minimum value of the horizontal coordinate and the maximum value and minimum value of the vertical coordinate in the coordinates of the projection point are obtained, and the maximum area obtained based on the maximum value and minimum value of the horizontal coordinate and the maximum value and minimum value of the vertical coordinate is used as the maximum area corresponding to the target object.

[0034] In one embodiment, before obtaining the to-be-processed motion data of the target object in the test area, the method includes:

[0035] Splitting and / or recombining the target object to obtain multiple parts to be processed;

[0036] The step of obtaining the to-be-processed motion data of the target object in the test area includes:

[0037] Obtaining motion data to be processed of a plurality of to-be-processed parts of a target object in a test area.

[0038] In one embodiment, before obtaining the to-be-processed motion data of the target object in the test area, the method includes:

[0039] Measuring the motor drive torque range and simulating the force deformation of the limbs of the target object;

[0040] Configuring map data of the test area;

[0041] Performing a call test on the target object and the map data;

[0042] When the calling test passes, the to-be-processed motion data of the target object in the test area is continuously acquired.

[0043] A collision judgment device, comprising:

[0044] An acquisition module, configured to acquire the to-be-processed motion data of the target object in the test area and the basic data of the target object;

[0045] a target gravity center calculation module, configured to calculate the target gravity center of the target object based on the motion data to be processed and the basic data;

[0046] A to-be-processed area calculation module, configured to calculate the to-be-processed area based on the to-be-processed motion data;

[0047] A classification module, configured to classify the target object according to the target center of gravity and the area to be processed;

[0048] The testing module is used to perform a collision test on the target object belonging to the target classification.

[0049] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0050] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0051] The above-mentioned collision judgment method, device, computer equipment and storage medium calculate the target center of gravity of the target object based on the motion data to be processed and the basic data, calculate the area to be processed based on the motion data to be processed, classify the target object according to the target center of gravity of the target object and the area to be processed, and perform collision tests on target objects belonging to the target classification, thereby reducing the collision tests on target objects that do not belong to the target classification, thereby reducing the number of experiments for simulated robot walking training, and thus reducing the amount of resources occupied. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 1 is a flow chart of a collision determination method according to an embodiment;

[0053] Figure 2 FIG1 is a schematic diagram of a robot having four supporting components in one embodiment;

[0054] Figure 3 is a schematic diagram of an area to be processed in one embodiment;

[0055] Figure 4is a flow chart of a collision determination method in another embodiment;

[0056] Figure 5 is a structural block diagram of a collision judgment device in one embodiment;

[0057] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] In one embodiment, Figure 1 As shown, a collision judgment method is provided. This embodiment uses the method applied to a terminal as an example for explanation. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The target object in this embodiment is a robot, preferably a robot with four supporting parts. Specifically, the form of the robot with four supporting parts includes but is not limited to a quadruped robot dog and a quadruped robot cat. For ease of understanding, the form of the robot with four supporting parts in this embodiment is as follows Figure 2 As shown, it can be understood that the form of the robot with four supporting parts is not limited to Figure 2 In this embodiment, the collision determination method includes the following steps:

[0060] Step S102 : obtaining the to-be-processed motion data of the target object in the test area and the basic data of the target object.

[0061] The test area is a training ground pre-set by the terminal, i.e., the environment where the robot operates. Basic information settings for the training ground are also set, such as gravity acceleration settings and terrain settings. This embodiment does not limit the basic information settings for the training ground. The training ground can be a regular image training ground or an irregular image training ground, depending on the actual needs of robot training. This is not specifically limited in this embodiment.

[0062] The target object is the robot currently being trained, preferably a quadruped robot. There can be one or more quadruped robots in training, meaning there is no limit to the number of robots in the test area. If there are multiple robots in the test area, the terminal processes the motion data of each robot separately through multithreading or other methods. The specific number of target objects depends on the CPU capacity of the terminal or the specific circumstances faced by the experimental operator.

[0063] The motion data to be processed is the plane coordinates of the support component on the training ground corresponding to the robot's current motion posture. For a quadruped robot, for example, there are four plane coordinates: These four plane coordinates are acquired as follows: the terminal first obtains the robot's current motion posture. Then, based on this motion posture, the terminal obtains the projection of the robot's support component on the training ground perpendicular to the horizontal plane. Based on this projection, the terminal obtains the plane coordinates of the support component on the training ground.

[0064] The basic data of the target object is the size of each part of the robot and the gravity of each part, which is used to calculate the center of gravity of the robot.

[0065] Specifically, the terminal sets up and configures a test area. The terminal obtains the plane coordinates of each support component corresponding to the motion posture of at least one robot in the test area, i.e., the training ground, as well as basic data such as the size of each part of the robot and the gravity of each part used to calculate the target center of gravity of the robot.

[0066] Preferably, the interval at which the terminal obtains the motion data to be processed may be in frames.

[0067] Step S104 : Calculate the target center of gravity of the target object based on the motion data to be processed and the basic data.

[0068] The target center of gravity is the projection point obtained by projecting the center of gravity of the quadruped robot along a direction perpendicular to the horizontal plane.

[0069] Specifically, the terminal first determines the initial center of gravity of the robot in its initial state based on the basic data of the robot. Preferably, the terminal calculates the position of the center of gravity of the robot's bounding box and then projects it to a point on the horizontal plane. Secondly, when the robot moves, the terminal obtains the robot's motion data, which includes position data and posture data. The initial center of gravity is translated according to the position data and the position of the robot in its initial state, and the initial center of gravity is rotated according to the posture data to obtain the target center of gravity corresponding to the motion data. In other embodiments, the terminal can generate a spatial transformation matrix based on the position data and posture data, and then calculate the target center of gravity corresponding to the initial center of gravity by means of the spatial transformation matrix.

[0070] Specifically, the terminal calculates the robot's center of gravity based on its basic data and the motion data to be processed. The basic data includes the dimensions of the robot's various components and the corresponding gravity, while the motion data to be processed is the plane coordinates of each support component on the training ground corresponding to the robot's current posture. The terminal then projects the center of gravity perpendicular to the horizontal plane, and the coordinates of the projected point are the target center of gravity.

[0071] Preferably, after obtaining the center of gravity of the robot, the vertical coordinate of the center of gravity of the robot on the training ground perpendicular to the horizontal plane is recorded, and the above vertical coordinate is compared with the height of the horizontal plane of the training ground. If the height of the vertical coordinate is lower than the height of the horizontal plane, it is determined that the robot has fallen.

[0072] Step S106: Calculate and obtain the area to be processed based on the motion data to be processed.

[0073] The area to be processed is the area calculated based on the motion data to be processed, i.e., the horizontal coordinates of each support component on the training ground. The area to be processed can be set as needed. Preferably, the area to be processed includes at least one of a maximum area, a minimum area, and a non-target stable area. The maximum area is the largest regular shape calculated based on the horizontal coordinates of the support components, the minimum area is the minimum overlapping area calculated based on the horizontal coordinates of the support components, and the non-target stable area is the area determined based on the horizontal coordinates of at least two support components.

[0074] Specifically, the terminal calculates three areas to be processed based on the motion data to be processed, that is, the horizontal coordinates of each supporting component on the training ground.

[0075] Step S108 : classifying the target object according to the target center of gravity and the area to be processed.

[0076] Specifically, the terminal classifies the robots according to the target center of gravity of the robots and the positions of the areas to be processed, into robots belonging to the target classification and robots not belonging to the target classification.

[0077] Step S110 : performing a collision test on the target objects belonging to the target category.

[0078] The collision test involves performing collision processing on two rigid bodies. The contact points and rigid body properties during the collision are used to calculate the new state of the rigid bodies, such as the new velocity, according to physical equations. The two rigid bodies in the collision test are the training ground and the robot.

[0079] Specifically, the terminal performs a collision test on the robot belonging to the target category, and records the basic data and motion data of the target robot at the current moment.

[0080] The above-mentioned collision judgment method calculates the target center of gravity of the target object based on the motion data to be processed and the basic data, calculates the area to be processed based on the motion data to be processed, classifies the target object according to the target center of gravity of the target object and the area to be processed, and performs collision tests on target objects that belong to the target classification, thereby reducing the collision tests on target objects that do not belong to the target classification, thereby reducing the number of experiments for the simulated robot's walking training, and thus reducing the amount of resources occupied.

[0081] In one embodiment, calculating a target center of gravity of a target object based on the motion data to be processed and the basic data includes: calculating a minimum bounding box that encloses the target object based on the basic data; calculating a center of gravity of the minimum bounding box; and adjusting the center of gravity of the bounding box based on the motion data to be processed. The adjusted center of gravity of the bounding box is vertically projected onto a test area to obtain the target center of gravity of the target object.

[0082] A bounding box is a simple geometric object, such as a cuboid or a sphere, that completely encloses each part of the rigid body (i.e., the robot in this embodiment). This embodiment does not limit the shape of the bounding box; it can be any simple, computationally convenient shape.

[0083] Specifically, the terminal calculates the minimum bounding box of the robot according to the size of each part in the basic data of the robot.

[0084] Specifically, the terminal calculates the center of gravity of the bounding box surrounding the robot according to the sizes of the bounding boxes corresponding to various parts of the robot and the corresponding gravity, and performs spatial translation and rotation changes on the center of gravity of the bounding box based on the motion data to be processed.

[0085] Specifically, the terminal vertically maps the bounding box's center of gravity onto the training ground to obtain the coordinates of the bounding box on the horizontal plane, and uses these coordinates as the robot's target center of gravity.

[0086] In this embodiment, the terminal calculates the minimum bounding box surrounding the target object based on the basic data, calculates the center of gravity of the minimum bounding box, and projects the center of gravity of the bounding box vertically onto the test area to obtain the target center of gravity of the target object. Using bounding box technology, the robot's basic data is processed to simplify the complex shape of the rigid body, i.e., the robot, facilitating simulation calculations, thereby reducing resource usage and improving computational efficiency.

[0087] In one embodiment, the method of calculating the area to be processed based on the motion data to be processed includes: calculating a minimum area based on the motion data to be processed, and using the minimum area as the area to be processed; classifying the target objects based on the target center of gravity and the minimum area to obtain a classification of target objects with the target center of gravity outside the minimum area and a classification of target objects with the target center of gravity within the minimum area, and grouping the target objects with the target center of gravity within the minimum area as the target classification.

[0088] The minimum area is the reference area of ​​the center of gravity calculated based on the robot's support components. When the target center is within this minimum area, the robot is considered to be stable. Therefore, this minimum area can also be considered the stable center of gravity area.

[0089] Specifically, the terminal calculates the minimum area according to the plane coordinates of each supporting component of the robot in the training field, and uses the minimum area as the area to be processed.

[0090] Specifically, the terminal classifies the robots based on the coordinates corresponding to the target center of gravity of the robots and the plane coordinates contained in the minimum area. One category is for robots whose target center of gravity coordinates are outside the plane coordinates contained in the minimum area, and the other category is for robots whose target center of gravity coordinates are within the plane coordinates contained in the minimum area. The terminal labels the robots whose target center of gravity coordinates are within the plane coordinates contained in the minimum area as target classification robots. After the classification is completed, the terminal performs a collision test on the robots corresponding to the target classification and records the basic data and motion data of the target robots at the current moment. The group of robots whose target center of gravity coordinates are outside the plane coordinates contained in the minimum area are classified again.

[0091] In one embodiment, calculating the minimum area corresponding to the target object based on the processed motion data includes: determining projection points of the four support components onto the test area based on the processed motion data of the four support components, generating a rectangle with at least two sides parallel to the target direction based on the coordinates of the projection points, and determining the overlapping area of ​​the rectangles as the minimum area.

[0092] Specifically, taking a quadruped robot as an example, the terminal determines the projection of the four supporting components in a direction perpendicular to the horizontal plane based on the motion posture of the four supporting components of the quadruped robot at the current moment. The intersection of this projection and the test area, i.e., the training ground, is the projection point.

[0093] Specifically, the terminal processes the four projection points so that the four projection points are on the same horizontal plane, and obtains the corresponding coordinates generated based on the projection points being on the same plane. Figure 3 For example, if the coordinates of the four projection points are (X1, Y1), (X2, Y2), (X3, Y3) and (X4, Y4), the terminal generates four horizontal lines parallel to the horizontal axis based on the horizontal coordinates X1, X2, X3 and X4, and selects the first area enclosed by the two middle horizontal lines of the four horizontal lines; generates four vertical lines parallel to the vertical axis based on the vertical coordinates Y1, Y2, Y3 and Y4, and selects the second area enclosed by the two middle vertical lines of the four vertical lines; the double-shaded area where the first and second areas overlap is the minimum area.

[0094] In this embodiment, the terminal calculates a minimum area based on the motion data to be processed and uses this minimum area as the area to be processed. The terminal then classifies the robot under the current motion data based on the target center of gravity and the minimum area. Robots whose target center of gravity coordinates fall within the plane coordinates of the minimum area are labeled as target-classified robots and then perform collision testing on these robots. This classification allows collision testing of target objects that fall within the target classification, reducing collision testing of target objects that do not fall within the target classification. This reduces the number of simulated robot walking training experiments and, in turn, reduces resource usage.

[0095] In one embodiment, the area to be processed is calculated based on the motion data to be processed, including:

[0096] The maximum area is calculated based on the motion data to be processed, and the maximum area is used as a processing area. According to the target center of gravity and the maximum area, the target object is classified into a target object classification with the target center of gravity outside the maximum area and a target object classification with the target center of gravity within the maximum area. The target object classification with the target center of gravity not within the maximum area is non-targeted.

[0097] The maximum area is the reference area of ​​the center of gravity calculated based on the robot's support components. If the target center is not within this maximum area, it can be considered that the robot will definitely fall. Therefore, this maximum area can also be regarded as the stable center of gravity area.

[0098] Specifically, the terminal calculates the maximum area according to the plane coordinates of each supporting component of the robot in the training field, and uses the maximum area as the area to be processed.

[0099] Specifically, the terminal classifies the robots according to the coordinates corresponding to the target center of gravity of the robots and the plane coordinates contained in the maximum area. One category is the robots whose target center of gravity coordinates are outside the plane coordinates contained in the maximum area, and the other category is the robots whose target center of gravity coordinates are within the plane coordinates contained in the maximum area. The terminal marks the robots whose target center of gravity coordinates are within the plane coordinates contained in the maximum area as target classification robots. After the classification is completed, the terminal performs a collision test on the robots corresponding to the target classification and records the basic data and motion data of the target robots at the current moment. The group of robots whose target center of gravity coordinates are outside the plane coordinates contained in the maximum area are reset and the next simulated walking experiment is carried out.

[0100] In one embodiment, a method for calculating the maximum area corresponding to the target object based on the motion data to be processed includes: obtaining the maximum and minimum values ​​of the horizontal coordinate, the maximum and minimum values ​​of the vertical coordinate in the coordinates of the projection point, and the maximum area obtained based on the maximum and minimum values ​​of the horizontal coordinate, the maximum and minimum values ​​of the vertical coordinate as the maximum area corresponding to the target object.

[0101] Specifically, taking a quadruped robot as an example, the terminal processes the four projection points so that the four projection points are on the same horizontal plane, and obtains the corresponding coordinates generated based on the projection points on the same plane. Figure 3 For example, if the coordinates of the four projection points are (X1, Y1), (X2, Y2), (X3, Y3) and (X4, Y4) respectively, the terminal selects the maximum and minimum values ​​of the horizontal coordinates as X1 and X3 based on the horizontal coordinates X1, X2, X3 and X4, and selects the maximum and minimum values ​​of the vertical coordinates as Y4 and Y2 based on the vertical coordinates Y1, Y2, Y3 and Y4. A horizontal line parallel to the horizontal axis is generated based on X1 and X3, and a vertical line parallel to the horizontal axis is generated based on Y4 and Y2. The rectangle enclosed by these four lines is selected as the maximum area.

[0102] In this embodiment, the terminal calculates the maximum area based on the motion data to be processed and uses the maximum area as the area to be processed. The terminal then classifies the robot under the current motion data based on the target center of gravity and the maximum area. Robots whose target center of gravity coordinates fall within the plane coordinates of the maximum area are labeled as target-classified robots and then perform collision testing on these robots. This classification allows collision testing of target objects that fall within the target classification, reducing collision testing of target objects that do not fall within the target classification. This reduces the number of simulated robot walking training experiments and, in turn, reduces resource usage.

[0103] In one embodiment, the area to be processed is calculated based on the motion data to be processed, including:

[0104] Target motion data is determined from the motion data to be processed based on the target center of gravity. A non-target stable region is calculated based on the target motion data, and the non-target stable region is used as a region to be processed. Target objects are classified based on the target center of gravity and the non-target stable region to obtain a classification of target objects with a target center of gravity outside the non-target stable region and a classification of target objects with a target center of gravity within the non-target stable region, and the target object with a target center of gravity within the non-target stable region is classified as a non-target classification.

[0105] Taking a quadruped robot as an example, the process of acquiring the target motion data is as follows: according to the target center of gravity coordinates, the closest coordinate interval is approximately selected from the four coordinates corresponding to the four support parts of the quadruped robot, and the target motion data is determined based on the closest coordinate interval.

[0106] Specifically, Figure 3 For example, if the four plane coordinates of the four supporting components of the quadruped robot on the training ground are (X1, Y1), (X2, Y2), (X3, Y3), and (X4, Y4), the terminal will approximately select the closest coordinate interval based on the target center of gravity coordinates (X, Y) and determine the target motion data based on this closest coordinate interval. If the target center of gravity coordinates (X, Y) are between (X1, Y1) and (X4, Y4), the terminal will determine the plane coordinates corresponding to the target motion data as (X1, Y1) and (X4, Y4).

[0107] Specifically, Figure 3 For example, based on the target motion data corresponding to the plane coordinates (X1, Y1) and (X4, Y4), the terminal draws parallel lines along the horizontal and vertical coordinates X1 and X4, and the vertical coordinates Y1 and Y4. The terminal then selects the portion of the image outside the line connecting (X1, Y1), (X2, Y2), (X3, Y3), and (X4, Y4), resulting in the lower left corner shaded image. This lower left corner shaded image is the non-target determination area, which the terminal considers as a pending area. It should be understood that the non-target determination area is not necessarily the lower left corner shaded image. If the target's center of gravity is approximated by the coordinate interval closest to (X2, Y2) and (X3, Y3), the non-target determination area is the upper right corner shaded image. Therefore, the specific location of the non-target determination area can be anywhere, above, below, or left. The specific location is determined based on the motion data to be processed and the target's center of gravity, and again, there is no limitation.

[0108] Specifically, the terminal classifies the robots according to the coordinates corresponding to the target center of gravity of the robots and the plane coordinates contained in the non-target determination area. One category is that the target center of gravity coordinates of the robots are outside the plane coordinates contained in the non-target determination area, and the other category is that the target center of gravity coordinates of the robots are within the plane coordinates contained in the non-target determination area. The terminal marks the robots whose target center of gravity coordinates are outside the plane coordinates contained in the non-target determination area as target classification robots. After the classification is completed, the terminal performs a collision test on the robots corresponding to the target classification, and records the basic data and motion data of the target robots at the current moment. The group of robots whose target center of gravity coordinates are outside the plane coordinates contained in the non-target determination area are reset and the next simulated walking experiment is carried out.

[0109] In this embodiment, the terminal determines target motion data from the motion data to be processed using the target center of gravity, calculates a non-target stable region based on the target motion data, and classifies the robot under the current motion data based on the target center of gravity and the non-target determination region. The terminal labels robots whose target center of gravity coordinates fall within the plane coordinates of the non-target determination region as target-classified robots and performs collision testing on the target-classified robots. Through classification, collision testing is performed on target objects that fall within the target classification, reducing collision testing on target objects that do not fall within the target classification. This reduces the number of simulated robot walking training experiments and, in turn, reduces resource usage.

[0110] In one embodiment, the target object includes at least four supporting components, and the maximum area, the minimum area, and the non-target stable area are calculated based on the to-be-processed motion data of the four supporting components.

[0111] In this embodiment, the terminal calculates the maximum area and the minimum area through the motion data to be processed and the target center of gravity. The logic is simple and easy to implement and maintain.

[0112] In one embodiment, before obtaining the motion data to be processed of the target object in the test area, the terminal includes: splitting and / or reassembling the target object to obtain multiple parts to be processed. The terminal obtains the motion data to be processed of the multiple parts to be processed of the target object in the test area. Specifically, the terminal splits the robot into multiple parts and reassembles some of the parts to form multiple parts to be processed. For example, in a specific implementation, the terminal splits the robot into parts such as feet, legs, torso, and head, combines the feet and legs into support components, and uses each support component as a part to be processed.

[0113] Specifically, the terminal obtains the posture of each supporting component of the robot in the training field to obtain corresponding data to be processed.

[0114] In this embodiment, the terminal can separate and / or reassemble the robot to obtain multiple parts to be processed. The terminal can then perform corresponding calculations on each of the parts and integrate the calculation results as the calculation result for the entire robot, thereby improving computational efficiency. For example, the multiple parts can be calculated in parallel to reduce computation time, and the calculation results can be integrated as the calculation result for the entire robot.

[0115] In one embodiment, before obtaining the to-be-processed motion data of the target object in the test area, the method includes:

[0116] Measure the motor drive torque range and simulate the force and deformation of the limbs of the target object. Configure the map data of the test area. Perform a call test on the target object and the map data. When the call test passes, continue to obtain the pending motion data of the target object in the test area. Specifically, the user inputs the measured motor drive torque range, enters the basic torso data, support component data, and joint strength. The terminal user inputs the measured motor drive torque range, torso data, support component data, and joint strength, and simulates the force and deformation of the limbs based on the above data. Among them, data such as the torque output range of the motor determines the force of the robot during movement, and is used to calculate the force when the robot takes a step. If the torque output is too small, the support component will not be able to support the robot under certain circumstances. Therefore, it is necessary to simulate the force and deformation of the robot's limbs.

[0117] Specifically, the terminal receives map data for configuring the test area input by the user to configure the test area. This embodiment does not limit the map data. Optionally, the map can be a flat map similar to a floor or a rugged off-road map. The specific map form can be set according to actual needs and is not specifically limited in this embodiment.

[0118] After obtaining the robot and map data, the terminal needs to test the robot and map data to detect or verify whether the above data meets the basic test requirements.

[0119] When the terminal confirms that the above data passes the call test, it continues to obtain the robot's motion data to be processed.

[0120] In this embodiment, the terminal measures the motor drive torque range and simulates the force and deformation of the limbs of the target object, configures the map data of the test area, and calls the test on the target object and map data to meet the basic conditions and operating basis required for the collision test and avoid invalid collision tests.

[0121] In one embodiment, Figure 4 As shown, the target object's motion data to be processed and the basic data of the target object in the test area are obtained. The target center of gravity of the target object is calculated based on the motion data to be processed and the basic data. The maximum area or the minimum area in the area to be processed is calculated based on the motion data to be processed.

[0122] The target object is roughly classified based on its center of gravity and the minimum or maximum area in the area to be processed. If the target center of gravity is outside the maximum area, the process is reset. If the target center of gravity is inside the minimum area, the collision detection step is performed. If the target center of gravity is inside the maximum area but outside the minimum area, the refined classification step is performed.

[0123] The precise classification step is to calculate the non-target stable area in the area to be processed based on the target center of gravity and the motion data to be processed, and classify it according to the target center of gravity and the non-target stable area. If the target center of gravity is not in the non-target stable area, the collision detection step is entered.

[0124] Preferably, if the target center of gravity is within the maximum area but outside the minimum area, another rough classification can be performed to reduce the number of times entering the precise classification and reduce the amount of calculation.

[0125] It is understandable that the order of the two rough classifications is not prioritized, and the order rules can be set arbitrarily.

[0126] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0127] In one embodiment, Figure 5 As shown, a collision judgment device is provided, comprising: an acquisition module 100, a target center of gravity calculation module 200, a to-be-processed area calculation module 300, a classification module 400 and a testing module 500, wherein:

[0128] The acquisition module 100 is used to acquire the to-be-processed motion data of the target object in the test area and the basic data of the target object.

[0129] The target center of gravity calculation module 200 is used to calculate the target center of gravity of the target object according to the motion data to be processed and the basic data.

[0130] The to-be-processed area calculation module 300 is configured to calculate the to-be-processed area based on the to-be-processed motion data.

[0131] The classification module 400 is used to classify the target object according to the target center of gravity and the area to be processed.

[0132] The testing module 500 is used to perform a collision test on target objects belonging to the target category.

[0133] In one embodiment, the target center of gravity calculation module includes:

[0134] The bounding box obtaining unit is used to calculate the minimum bounding box surrounding the target object based on the basic data.

[0135] The bounding box center of gravity calculation unit is used to calculate the bounding box center of gravity of the minimum bounding box and adjust the bounding box center of gravity based on the motion data to be processed.

[0136] The mapping unit is used to vertically map the adjusted bounding box center of gravity on the test area to obtain the target center of gravity of the target object.

[0137] In one embodiment, the module for calculating the area to be processed includes:

[0138] The first calculation unit is configured to calculate a minimum area according to the motion data to be processed, and use the minimum area as the area to be processed.

[0139] Classification modules, including:

[0140] The first classification unit is used to classify the target object according to the center of gravity and the minimum area of ​​the target object to obtain a target object classification with the target center of gravity outside the minimum area and a target object classification with the target center of gravity within the minimum area, and group the target object classification with the target center of gravity within the minimum area as the target classification.

[0141] In one embodiment, the module for calculating the area to be processed includes:

[0142] The second calculation unit is configured to calculate a maximum area according to the motion data to be processed, and use the maximum area as an area to be processed.

[0143] Classification modules, including:

[0144] The second classification unit is used to classify the target object according to the target center of gravity and the maximum area to obtain a target object classification with the target center of gravity outside the maximum area and a target object classification with the target center of gravity within the maximum area, and classify the target object that the target center of gravity is not within the maximum area as a non-target classification.

[0145] In one embodiment, the module for calculating the area to be processed includes:

[0146] The target data determination unit is used to determine target motion data from the motion data to be processed according to the target center of gravity.

[0147] The third calculation unit is configured to calculate a non-target stable region according to the target motion data, and use the non-target stable region as a region to be processed.

[0148] Classification modules, including:

[0149] The third classification unit is used to classify the target object according to the target center of gravity and the non-target stable area to obtain a target object classification with the target center of gravity outside the non-target stable area and a target object classification with the target center of gravity within the non-target stable area, and classify the target object classification with the target center of gravity within the non-target stable area as a non-target classification.

[0150] In one embodiment, the target object includes at least four supporting components, and the maximum area, minimum area, and non-target stable area are calculated based on the motion data to be processed of the four supporting components. The first calculation unit includes:

[0151] The projection point determination subunit is used to determine the projection points of the four supporting components projected onto the test area according to the to-be-processed motion data of the four supporting components.

[0152] The first minimum area calculation subunit is configured to generate a rectangle with at least two sides parallel to the target direction according to the coordinates of the projection point, and obtain an overlapping area of ​​the rectangles as the minimum area.

[0153] The second computing unit includes:

[0154] The second maximum area calculation subunit is used to obtain the maximum and minimum values ​​of the horizontal coordinate, the maximum and minimum values ​​of the vertical coordinate in the coordinates of the projection point, and the maximum area obtained based on the maximum and minimum values ​​of the horizontal coordinate, the maximum and minimum values ​​of the vertical coordinate as the maximum area corresponding to the target object.

[0155] In one embodiment, the method includes:

[0156] The preprocessing module is used to split and / or reassemble the target object to obtain multiple parts to be processed.

[0157] The acquisition module is used to acquire the to-be-processed motion data of multiple to-be-processed parts of the target object in the test area.

[0158] In one embodiment, the method includes:

[0159] The measurement simulation module is used to measure the motor drive torque range and simulate the force deformation of the target object.

[0160] Configuration module, used to configure the map data of the test area.

[0161] The test module is used to call and test the target object and map data.

[0162] The second acquisition module is used to continue acquiring the to-be-processed motion data of the target object in the test area after the call test passes.

[0163] The specific limitations of the collision determination device can be found in the limitations of the collision determination method described above and will not be elaborated upon here. Each module in the aforementioned collision determination device may be implemented in whole or in part through software, hardware, or a combination thereof. Each of the aforementioned modules may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a memory in a computer device in software form, so that the processor can call and execute the operations corresponding to each of the aforementioned modules.

[0164] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the motion data of the robot and the corresponding collision judgment data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a collision judgment method is implemented.

[0165] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0166] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0167] Obtain the target object's motion data to be processed and the basic data of the target object in the test area; calculate the target center of gravity of the target object based on the motion data to be processed and the basic data; calculate the area to be processed based on the motion data to be processed; classify the target object according to the target center of gravity and the area to be processed; and perform collision testing on the target objects belonging to the target classification.

[0168] In one embodiment, the calculation of the target center of gravity of the target object based on the motion data to be processed and the basic data implemented by the processor when executing the computer program includes:

[0169] The minimum bounding box surrounding the target object is calculated based on the basic data; the center of gravity of the minimum bounding box is calculated and adjusted based on the motion data to be processed; the adjusted center of gravity of the bounding box is vertically mapped on the test area to obtain the target center of gravity of the target object.

[0170] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed, implemented by the processor when executing the computer program, includes:

[0171] The minimum area is calculated based on the motion data to be processed, and the minimum area is used as the area to be processed; the target object is classified according to the target center of gravity and the area to be processed, including: according to the center of gravity of the target object and the minimum area, the target object is classified to obtain a target object classification with the target center of gravity outside the minimum area and a target object classification with the target center of gravity within the minimum area, and the target object classification grouping with the target center of gravity within the minimum area is used as the target classification.

[0172] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed, implemented by the processor when executing the computer program, includes:

[0173] The maximum area is calculated based on the motion data to be processed, and the maximum area is used as an area to be processed; the target object is classified according to the target center of gravity and the area to be processed, including: according to the target center of gravity and the maximum area, the target object is classified to obtain a target object classification whose target center of gravity is outside the maximum area and a target object classification whose target center of gravity is within the maximum area, and the target object classification whose target center of gravity is not within the maximum area is non-target classification.

[0174] In one embodiment, the step of calculating the area to be processed based on the motion data to be processed, implemented by the processor when executing the computer program, includes:

[0175] The method comprises the following steps: determining target motion data from the motion data to be processed according to the target center of gravity; calculating a non-target stable area according to the target motion data, and using the non-target stable area as an area to be processed; and classifying the target object according to the center of gravity of the target object and the area to be processed, including: classifying the target object according to the target center of gravity and the non-target stable area to obtain a target object classification whose target center of gravity is outside the non-target stable area and a target object classification whose target center of gravity is within the non-target stable area, and classifying the target object whose target center of gravity is within the non-target stable area as a non-target classification.

[0176] In one embodiment, the target object realized when the processor executes the computer program includes at least four supporting components, and the maximum area, minimum area and non-target stable area are calculated based on the motion data to be processed of the four supporting components; the minimum area corresponding to the target object is calculated based on the motion data to be processed, including: determining the projection points of the four supporting components projected onto the test area based on the motion data to be processed of the four supporting components respectively; obtaining a rectangle with at least two sides parallel to the target direction based on the coordinates of the projection points, and obtaining the overlapping area of ​​the rectangle as the minimum area; the calculation method of the maximum area includes: obtaining the maximum and minimum values ​​of the horizontal coordinate and the maximum and minimum values ​​of the vertical coordinate in the coordinates of the projection points, and obtaining the maximum area based on the maximum and minimum values ​​of the horizontal coordinate and the maximum and minimum values ​​of the vertical coordinate as the maximum area corresponding to the target object.

[0177] In one embodiment, before obtaining the to-be-processed motion data of the target object in the test area, the steps implemented by the processor when executing the computer program include:

[0178] The target object is split and / or reassembled to obtain multiple parts to be processed; and the motion data to be processed of the target object in the test area is obtained, including: obtaining the motion data to be processed of the multiple parts to be processed of the target object in the test area.

[0179] In one embodiment, before obtaining the to-be-processed motion data of the target object in the test area, the steps implemented by the processor when executing the computer program include:

[0180] Measure the motor drive torque range and simulate the force deformation of the target object; configure the map data of the test area; perform a call test on the target object and the map data; when the call test passes, continue to obtain the target object's motion data to be processed in the test area.

[0181] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0182] Obtain the target object's motion data to be processed and the basic data of the target object in the test area; calculate the target center of gravity of the target object based on the motion data to be processed and the basic data; calculate the area to be processed based on the motion data to be processed; classify the target object according to the target center of gravity and the area to be processed; and perform collision testing on the target objects belonging to the target classification.

[0183] In one embodiment, the computer program, when executed by a processor, calculates the target center of gravity of the target object based on the motion data to be processed and the basic data, including:

[0184] The minimum bounding box surrounding the target object is calculated based on the basic data; the center of gravity of the minimum bounding box is calculated and adjusted based on the motion data to be processed; the adjusted center of gravity of the bounding box is vertically mapped on the test area to obtain the target center of gravity of the target object.

[0185] In one embodiment, the steps of calculating the area to be processed based on the motion data to be processed implemented by the computer program when executed by the processor include:

[0186] The minimum area is calculated based on the motion data to be processed, and the minimum area is used as the area to be processed; the target object is classified according to the target center of gravity and the area to be processed, including: according to the center of gravity of the target object and the minimum area, the target object is classified to obtain a target object classification with the target center of gravity outside the minimum area and a target object classification with the target center of gravity within the minimum area, and the target object classification grouping with the target center of gravity within the minimum area is used as the target classification.

[0187] In one embodiment, the steps of calculating the area to be processed based on the motion data to be processed implemented by the computer program when executed by the processor include:

[0188] The maximum area is calculated based on the motion data to be processed, and the maximum area is used as an area to be processed; the target object is classified according to the target center of gravity and the area to be processed, including: according to the target center of gravity and the maximum area, the target object is classified to obtain a target object classification whose target center of gravity is outside the maximum area and a target object classification whose target center of gravity is within the maximum area, and the target object classification whose target center of gravity is not within the maximum area is non-target classification.

[0189] In one embodiment, the steps of calculating the area to be processed based on the motion data to be processed implemented by the computer program when executed by the processor include:

[0190] The method comprises the following steps: determining target motion data from the motion data to be processed according to the target center of gravity; calculating a non-target stable area according to the target motion data, and using the non-target stable area as an area to be processed; and classifying the target object according to the center of gravity of the target object and the area to be processed, including: classifying the target object according to the target center of gravity and the non-target stable area to obtain a target object classification whose target center of gravity is outside the non-target stable area and a target object classification whose target center of gravity is within the non-target stable area, and classifying the target object whose target center of gravity is within the non-target stable area as a non-target classification.

[0191] In one embodiment, when the computer program is executed by a processor, the target object includes at least four supporting components, and the maximum area, minimum area and non-target stable area are calculated based on the motion data to be processed of the four supporting components; the minimum area corresponding to the target object is calculated based on the motion data to be processed, including: determining the projection points of the four supporting components projected onto the test area based on the motion data to be processed of the four supporting components respectively; obtaining a rectangle with at least two sides parallel to the target direction based on the coordinates of the projection points, and obtaining the overlapping area of ​​the rectangle as the minimum area; the calculation method of the maximum area includes: obtaining the maximum and minimum values ​​of the horizontal coordinate and the maximum and minimum values ​​of the vertical coordinate in the coordinates of the projection points, and obtaining the maximum area based on the maximum and minimum values ​​of the horizontal coordinate and the maximum and minimum values ​​of the vertical coordinate as the maximum area corresponding to the target object.

[0192] In one embodiment, the computer program, when executed by a processor, includes:

[0193] The target object is split and / or reassembled to obtain multiple parts to be processed; and the motion data to be processed of the target object in the test area is obtained, including: obtaining the motion data to be processed of the multiple parts to be processed of the target object in the test area.

[0194] In one embodiment, the computer program, when executed by a processor, includes:

[0195] Measure the motor drive torque range and simulate the force deformation of the target object; configure the map data of the test area; perform a call test on the target object and the map data; when the call test passes, continue to obtain the target object's motion data to be processed in the test area.

[0196] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0197] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0198] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A collision judgment method, characterized in that: The method comprises: Acquire the motion data to be processed and the basic data of the target object in the test area; The target center of gravity of the target object is calculated based on the motion data to be processed and the basic data; the target center of gravity is used to represent the projection point obtained by projecting the center of gravity of the target object along a direction perpendicular to the horizontal plane; Calculating a region to be processed according to the motion data to be processed; Classifying the target object according to the target center of gravity and the area to be processed; Performing a collision test on the target object belonging to a target classification; the target classification is used to characterize the target object classification in which the target center of gravity is in a stable center of gravity area; The step of calculating the area to be processed according to the motion data to be processed includes: determining target motion data from the motion data to be processed according to the target center of gravity; Calculating a non-target stable region according to the target motion data, and using the non-target stable region as a region to be processed; The determining target motion data from the motion data to be processed according to the target center of gravity includes: According to the coordinates of the target center of gravity, a closest coordinate area is selected from the motion data to be processed, and the target motion data is determined according to the closest coordinate interval.

2. The method according to claim 1, characterized in that The calculating the target center of gravity of the target object according to the motion data to be processed and the basic data includes: Calculate the minimum bounding box surrounding the target object based on the basic data; Calculating the center of gravity of the minimum bounding box and adjusting the center of gravity of the bounding box based on the motion data to be processed; The adjusted center of gravity of the bounding box is vertically mapped to the test area to obtain the target center of gravity of the target object.

3. The method according to claim 1, characterized in that The step of calculating the area to be processed according to the motion data to be processed includes: Calculate a minimum area according to the motion data to be processed, and use the minimum area as the area to be processed; The classifying the target object according to the target center of gravity and the area to be processed includes: According to the center of gravity of the target object and the minimum area, the target object is classified to obtain a target object classification with the target center of gravity outside the minimum area and a target object classification with the target center of gravity within the minimum area, and the target object classification with the target center of gravity within the minimum area is grouped as a target classification.

4. The method according to claim 3, characterized in that The step of calculating the area to be processed according to the motion data to be processed includes: Calculating a maximum area according to the motion data to be processed, and using the maximum area as an area to be processed; The classifying the target object according to the target center of gravity and the area to be processed includes: According to the target center of gravity and the maximum area, the target object is classified into a target object classification whose target center of gravity is outside the maximum area and a target object classification whose target center of gravity is within the maximum area, and the target object classification whose target center of gravity is not within the maximum area is classified as a non-target classification.

5. The method according to claim 4, characterized in that The classifying the target object according to the center of gravity of the target object and the area to be processed includes: According to the target center of gravity and the non-target stable area, the target object is classified to obtain a target object classification with the target center of gravity outside the non-target stable area and a target object classification with the target center of gravity within the non-target stable area, and the target object classification with the target center of gravity within the non-target stable area is used as a non-target classification.

6. The method according to claim 5, characterized in that The target object includes at least four supporting components, and the maximum area, the minimum area and the non-target stable area are calculated based on the motion data to be processed of the four supporting components; The calculating the minimum area corresponding to the target object according to the motion data to be processed includes: determining projection points of the four supporting components onto the test area according to the to-be-processed motion data of the four supporting components respectively; Obtaining a rectangle whose at least two sides are parallel to a target direction based on the coordinates of the projection point, and obtaining an overlapping area of ​​the rectangle as a minimum area; the target direction is a horizontal coordinate axis or a vertical coordinate axis; The maximum area is calculated as follows: The maximum value and minimum value of the horizontal coordinate and the maximum value and minimum value of the vertical coordinate in the coordinates of the projection point are obtained, and the maximum area obtained based on the maximum value and minimum value of the horizontal coordinate and the maximum value and minimum value of the vertical coordinate is used as the maximum area corresponding to the target object.

7. The method according to claim 1, characterized in that Before obtaining the to-be-processed motion data of the target object in the test area, the method includes: Splitting and / or recombining the target object to obtain multiple parts to be processed; The step of obtaining the to-be-processed motion data of the target object in the test area includes: Obtaining motion data to be processed of a plurality of to-be-processed parts of a target object in a test area.

8. The method according to claim 1, characterized in that Before obtaining the to-be-processed motion data of the target object in the test area, the method includes: Measuring the motor drive torque range and simulating the force deformation of the limbs of the target object; Configuring map data of the test area; Performing a call test on the target object and the map data; When the calling test passes, the to-be-processed motion data of the target object in the test area is continuously acquired.

9. A collision judgment device, characterized in that: The device comprises: An acquisition module, configured to acquire the to-be-processed motion data of the target object in the test area and the basic data of the target object; a target center of gravity calculation module, configured to calculate the target center of gravity of the target object based on the motion data to be processed and the basic data; the target center of gravity is used to represent a projection point obtained by projecting the center of gravity of the target object along a direction perpendicular to the horizontal plane; a to-be-processed region calculation module, configured to select the closest coordinate region from the to-be-processed motion data based on the coordinates of the target's center of gravity, and determine the target motion data based on the closest coordinate interval; calculate a non-target stable region based on the target motion data, and use the non-target stable region as a to-be-processed region; A classification module, configured to classify the target object according to the target center of gravity and the area to be processed; The test module is used to perform a collision test on the target object belonging to the target classification; the target classification is used to characterize the target object classification whose center of gravity is in a stable center of gravity area.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images