Navigation control method, device, paving robot and storage medium

Abstract

The present application discloses a navigation control method, device, paving robot and storage medium, which are applied to the paving robot, and the method comprises: acquiring an image including a paving route; acquiring the position information of the paving robot based on the image; and controlling the paving robot to walk based on the position information. The present application acquires an image including a paving route through a visual system, and controls the paving robot to walk based on the image, so that the paving robot can be automatically controlled to walk along the paving route, thereby improving walking accuracy, reducing manual intervention, and reducing labor costs.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and more specifically, to a navigation control method, device, paving robot and storage medium. Background Art

[0002] As a leak-free connection between the engineering foundation and the building, waterproofing membrane is the first barrier to waterproofing the entire project and plays a vital role in the entire project. Currently, the commonly used methods for laying waterproofing membranes include hot melt method, cold adhesive method, self-adhesive method, hot air welding method and mechanical fixing method, but the current laying method requires a team of construction workers to complete the work, which consumes a lot of manpower and material resources. Summary of the invention

[0003] In view of the above problems, the present application proposes a navigation control method, device, paving robot and storage medium to solve the above problems.

[0004] In a first aspect, an embodiment of the present application provides a navigation control method applied to a paving robot, the method comprising: acquiring an image including a paving route; acquiring position information of the paving robot based on the image; and controlling the paving robot to walk based on the position information.

[0005] In a second aspect, an embodiment of the present application provides a navigation control device, which is applied to a paving robot. The device includes: an image acquisition module, which is used to acquire an image including a paving route; an information acquisition module, which is used to acquire the posture information of the paving robot based on the image; and a robot control module, which is used to control the walking of the paving robot based on the posture information.

[0006] In a third aspect, an embodiment of the present application provides a paving robot, comprising a memory and a processor, wherein the memory is coupled to the processor, the memory stores instructions, and when the instructions are executed by the processor, the processor executes the above method.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored, and the program code can be called by a processor to execute the above method.

[0008] The embodiment of the present application provides a navigation control method, device, paving robot and storage medium, which are applied to the paving robot, and the method includes: acquiring an image including a paving route; acquiring the position information of the paving robot based on the image; and controlling the paving robot to walk based on the position information. Thus, by acquiring an image including a paving route through a visual system and controlling the paving robot to walk based on the image, the paving robot can be automatically controlled to walk along the paving route, thereby improving walking accuracy, reducing manual intervention, and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A flowchart of a navigation control method provided by an embodiment of the present application is shown;

[0011] Figure 2 An example diagram of a paving route provided by an embodiment of the present application is shown;

[0012] Figure 3 A flowchart of another navigation control method provided by an embodiment of the present application is shown;

[0013] Figure 4 This application shows Figure 3 The flowchart of step S230 of the navigation control method shown in FIG.

[0014] Figure 5 A schematic diagram showing a flow chart of another navigation control method provided in an embodiment of the present application is shown;

[0015] Figure 6 A flowchart of another navigation control method provided in an embodiment of the present application is shown;

[0016] Figure 7 A flowchart of another navigation control method provided in an embodiment of the present application is shown;

[0017] Figure 8 An example diagram of a marker provided in an embodiment of the present application is shown;

[0018] Fig. 9 A flowchart of yet another navigation control method provided in an embodiment of the present application is shown;

[0019] Fig.10 A module block diagram of a navigation control device provided in an embodiment of the present application is shown;

[0020] Fig.11 A block diagram of a paving robot for executing a navigation control method according to an embodiment of the present application is shown;

[0021] Fig.12 A structural block diagram of a computer-readable storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0023] Waterproofing membrane is mainly used for building walls, roofs, tunnels, roads, landfills, etc. It is a kind of flexible building material product that can be rolled into a roll to resist the leakage of rainwater and groundwater from the outside. As a leak-free connection between the engineering foundation and the building, it is the first barrier to waterproofing the entire project and plays a vital role in the entire project. At present, the commonly used methods for laying waterproofing membranes are hot melt method, cold adhesive method, self-adhesive method, hot air welding method and mechanical fixing method. The specific operation is generally completed by a team of construction workers who work together to carry the membrane, lay the material, paste the material and other required materials, as well as the necessary tools. Such a laying mode is less effective and consumes a lot of manpower and material resources. The current automatic walking robot chassis often uses the laser positioning method, which has strong adaptability and diverse algorithms. However, it is difficult to filter temporary obstacles in the complex and changeable scenes of the construction site and the positioning is poor.

[0024] In response to the above problems, the inventors proposed the navigation control method, device, paving robot and storage medium provided in the embodiments of the present application, which acquires an image including a paving route through a visual system, controls the paving robot to walk based on the image, and can automatically control the paving robot to walk along the paving route, thereby improving walking accuracy, reducing manual intervention, and reducing labor costs. The specific navigation control method is described in detail in the subsequent embodiments.

[0025] See also Figure 1 , Figure 1 A flowchart of a navigation control method provided by an embodiment of the present application is shown below. Figure 1 The process shown is described in detail, and the navigation control method may specifically include the following steps:

[0026] Step S110: Acquire an image including a paving route.

[0027] In this embodiment, the movement of the paving robot can be controlled by image recognition. The paving robot usually walks along the paving route when walking. Therefore, an image including the paving route can be obtained first, wherein the paving route can be manually paved or can be the white line of the overlapped edge of the coiled material. As an implementation mode, a machine vision device such as a camera can be provided on the paving robot, and the paving robot can collect images including the paving route through the machine vision device. Furthermore, a machine vision device can also be provided externally to collect images of the paving route, and the paving robot can communicate with the machine vision device, so as to obtain images including the paving route collected by the external machine vision device. Among them, the paving robot can obtain images including the paving route in real time, or can obtain images including the paving route at preset time intervals, which are not limited here.

[0028] In some embodiments, the image of the paving route obtained by the paving robot may contain "noise", such as impurities, a messy background of the image, unclear paving routes, etc., which will affect subsequent processing. Therefore, when the image including the paving route is obtained, the image may be preprocessed first. The preprocessing method may include converting the image into a grayscale image, image enhancement, noise removal, etc., which are not limited here.

[0029] Step S120: Acquire the position and posture information of the paving robot based on the image.

[0030] In this embodiment, the position of the paving robot can be determined by the offset of the paving route in the image. Therefore, the pose information of the paving robot can be obtained based on the image, wherein the pose information is used to represent the position information and angle information of the paving robot. As an implementation method, the pose information of the paving robot can be obtained based on the deviation between the paving route and the standard paving route. Specifically, the position of the paving route in the image can be determined, and a standard paving route image can be obtained, wherein the standard paving route image can be an image of the paving route obtained by the paving robot at the start stage, or a pre-stored standard paving route image. The acquired image is compared with the standard paving route image to determine whether the paving route in the image acquired by the paving robot is completely consistent with the paving route in the standard paving route image. If not, the offset between the paving route acquired by the paving robot and the paving route in the standard paving route map can be used as the pose information of the paving robot, such as Figure 2 As shown, S1 is the paving route obtained by the paving robot, and S2 is the standard paving route. The offset distance y between S1 and S2, and the angle α between S1 and S2 can be obtained, and the offset distance y and the angle α are used as the position information of the paving robot.

[0031] In some embodiments, a coordinate system can be established to obtain the position information of the paving robot based on the difference between the paving route obtained by the paving robot and the coordinate axis. Specifically, after obtaining an image including the paving route, a coordinate system can be established, wherein the X-axis can be established with the direction of travel of the paving robot as the X direction, and the Y-axis can be established with the direction perpendicular to the travel direction of the paving robot as the Y direction. By placing the coordinate system at a position corresponding to the paving route, the angle between the paving route and the Y-axis and the distance between the paving route and the X-axis can be obtained, and then the angle between the paving route and the Y-axis can be used as the angle offset, and the distance between the paving route and the X-axis can be used as the position offset, and the position information of the paving robot can be obtained.

[0032] Step S130: Controlling the paving robot to move based on the posture information.

[0033] In this embodiment, the walking of the paving robot can be controlled based on the posture information. Specifically, the speed and direction of the paving robot can be controlled according to the position offset and angle offset of the paving robot, so that the paving robot can always walk along the paving route without deviating from the route.

[0034] In some embodiments, in order to accurately control the walking of the paving robot, the posture information of the paving robot can be first filtered to obtain the posture information after filtering, and then the walking of the paving robot can be controlled according to the posture information after filtering. The filtering method can be a sliding window filtering algorithm, a median filtering algorithm, a low-pass digital filtering algorithm, etc., which is not limited here.

[0035] In some embodiments, while controlling the paving robot to walk, the paving robot can be controlled to pave, so that the paving robot can pave while walking. The paving robot can be a waterproof coil paving robot, or other types of paving robots that walk in a straight line, such as wallpaper paving robots, floor tile paving robots, etc. The chassis of the paving robot of this embodiment can use differential wheels to reduce costs while achieving higher walking accuracy.

[0036] Furthermore, when the paving robot is paving coils, when it detects that one row of coils has been laid, it can first control the paving robot to stop moving, and then control the paving robot to continue moving after obtaining the next row of coils, thereby realizing fully automatic paving of multiple rows by the robot, that is, a new row of coils can continue to move forward along the traces of the previous row of coils.

[0037] The navigation control method provided in the above embodiment acquires an image including a paving route; acquires the position information of the paving robot based on the image; and controls the paving robot to walk based on the position information. Thus, by acquiring an image including a paving route through a visual system and controlling the paving robot to walk based on the image, the paving robot can be automatically controlled to walk along the paving route, thereby improving walking accuracy, reducing manual intervention, and reducing labor costs.

[0038] See also Figure 3 , Figure 3 A flowchart of another navigation control method provided in an embodiment of the present application is shown. Figure 3 The process shown is described in detail, and the method may specifically include the following steps S210-S240.

[0039] Step S210: Acquire an image including a paving route.

[0040] Step S220: Acquire the position and posture information of the paving robot based on the image.

[0041] For the detailed description of step S210 to step S220, please refer to step S110 to step S120, which will not be repeated here.

[0042] Step S230: taking the posture information as the input of the fuzzy PID controller to obtain the control instruction output by the fuzzy PID controller, wherein the control instruction is used to control the left wheel speed and the right wheel speed of the paving robot.

[0043] In this embodiment, the speed and direction of the paving robot can be controlled by a fuzzy PID controller. Specifically, the posture information can be used as the input of the fuzzy PID controller to obtain the control instructions output by the fuzzy PID controller, wherein the fuzzy PID controller combines the fuzzy algorithm with the PID control parameters, wherein the PID control parameters can include proportional control parameters, integral control parameters and differential control parameters.

[0044] In some embodiments, referring to calculation formula (1),

[0045]

[0046] Among them, formula (1) is the principle formula of PID control, K p is the proportional control parameter, K i is the integral control parameter, K d is the differential control parameter. Taking the posture information of the paving robot as input, that is, e(t), the control instruction of the paving robot, that is, u(t), can be obtained.

[0047] In some embodiments, different operation scenarios correspond to different speeds. In order to enable the paving robot to achieve the same control effect at different speeds, multiple sets of PID control parameters can be set according to different speeds. Combining the fuzzy algorithm with the PID control parameters, the following calculation formulas (2) to (5) can be obtained:

[0048]

[0049]

[0050]

[0051]

[0052] Where max represents the boundary value of the system control quantity, k is the number of corresponding PID control parameter groups, for example, there are three groups of control parameters, k is 3; p, q is the number of singular function points generated by u(t).

[0053] According to the above formula, the control instructions of the paving robot can be obtained according to the position information of the paving robot to control the speed and direction of the paving robot. Furthermore, the chassis of the paving robot of this embodiment can adopt differential wheels, and the structure of the differential wheels is that the differential wheels are installed on the left and right sides of the vehicle body as driving wheels, and the other is a follower wheel. The differential wheels realize steering through the speed difference between the left and right driving wheels. Therefore, the control instructions obtained above can be used to control the left and right wheel speeds of the paving robot.

[0054] See also Figure 4 , Figure 4 This application shows Figure 3 The flowchart of step S230 of the navigation control method shown may specifically include steps S231 to S233.

[0055] Step S231: Obtain the travel speed of the paving robot, and determine the PID control parameters based on the travel speed.

[0056] In this embodiment, the paving robot may have different operation scenes when working, and different operation scenes correspond to different speeds. In order to enable the paving robot to achieve the same control effect at different speeds, the travel speed of the paving robot can be obtained, and the PID control parameters can be determined based on the travel speed. In some embodiments, a correspondence between the travel speed and the PID control parameters can be preset. After the travel speed of the paving robot is obtained, the PID control parameters corresponding to the currently obtained travel speed can be found according to the correspondence between the travel speed and the PID control parameters.

[0057] Step S232: Obtain the fuzzy control table corresponding to the fuzzy PID controller.

[0058] In this embodiment, the fuzzy control table corresponding to the fuzzy PID controller can be obtained. Please refer to Table 1:

[0059] Table 1

[0060]

[0061]

[0062] Table 1 shows the fuzzy rules corresponding to the fuzzy PID controller, where e1 and e2 represent the position offset and angle offset in the posture information of the paving robot, respectively, and n can be set according to the requirements of establishing the table. p , we can get the fuzzy control table of proportional control parameters according to Table 1. When n is K i , we can get the fuzzy control table of integral control parameters according to Table 1. When n is K d , the fuzzy control table of differential control parameters can be obtained according to Table 1. NB (negative large), NM (negative medium), NS (negative small), ZO (zero), PS (positive small), PM (positive medium) and PB (positive large) are 7 language variables, and the precise value is replaced by the language variable value. For example, the position offset e1 of the paving robot is 30, among which the position offset that the paving robot can obtain has a range, and the feasible interval of the position offset can be set to [-40, 40]. The feasible interval is divided into 8 parts, namely -40~-30, -30~-20, -20~-10, -10~0, 0~10, 10~20, 20~30, 30~40, and then -30, -20, -10, 0, 10, 20, 30, 40 are represented by NB, NM, NS, ZO, PS, PM, PB respectively. The position offset e1 is 30, so the membership of e1 is 1, and the membership value is PB. Similarly, the membership of e2 can be deduced. According to the fuzzy rules in Table 1 above, the output value, that is, the membership corresponding to n, can be deduced. The solution of the output value can be calculated by multiplying the membership by the corresponding membership value. Furthermore, the above fuzzy rules can be adjusted according to the relationship between e1, e2 and n. For example, when n is the integral control parameter, the integral control is mainly used to eliminate the steady-state deviation of the system. Due to saturation nonlinearity and other reasons, the integral process may produce integral saturation in the early stage of the regulation process. Therefore, in the early stage of the regulation process, in order to prevent integral saturation, its integral effect should be weaker. For example, when e1 is NB and e2 is NB, the membership value of n can be set to NB.

[0063] Step S233: Based on the posture information, PID control parameters and fuzzy control table, obtain the control instructions output by the fuzzy PID controller.

[0064] In this embodiment, the control instruction output by the fuzzy PID controller can be obtained based on the posture information, PID control parameters and fuzzy control table. Specifically, the PID control parameters can be corrected according to the fuzzy control table, and then the corrected PID control parameters and posture information can be substituted into formula (1) to obtain the control instruction output by the fuzzy PID controller.

[0065] Step S240: In response to the control instruction, control the left wheel speed and the right wheel speed of the paving robot.

[0066] In this embodiment, based on the posture information of the paving robot and combined with the fuzzy PID controller, the control instructions of the paving robot can be obtained, wherein the control instructions can be used to control the left wheel speed and the right wheel speed of the paving robot. Therefore, the paving robot can control the left wheel speed and the right wheel speed in response to the control instructions.

[0067] In some embodiments, the output of the fuzzy PID controller may be the speed difference between the left and right wheels of the paving robot. Based on the inverse solution of the differential wheel kinematic model, the left and right wheel speeds of the paving robot can be calculated according to the speed difference between the left and right wheels of the paving robot. The inverse solution of the differential wheel kinematic model is as follows: assuming that the speed difference between the two wheels is Δv, and the speed in the x direction, i.e., the direction of travel of the robot, is v x , then the left wheel speed v x -Δv, right wheel speed v x +Δv. Therefore, the traveling speed of the paving robot can be obtained through the paving robot system, and then the left wheel speed and the right wheel speed of the paving robot can be calculated.

[0068] Compared with the navigation control method provided in the above embodiment, Figure 1 The navigation control method shown in the figure, this embodiment also obtains the control instructions of the paving robot through the fuzzy PID controller to control the walking of the paving robot, thereby realizing precise control of the paving robot.

[0069] See also Figure 5 , Figure 5 FIG. 1 is a flow chart showing another navigation control method provided by an embodiment of the present application. Figure 5 The process shown is described in detail, and the method may specifically include the following steps S310-S350.

[0070] Step S310: Acquire an image including a paving route.

[0071] Step S320: Acquire the position and posture information of the paving robot based on the image.

[0072] For the detailed description of step S310 to step S320, please refer to step S110 to step S120, which will not be repeated here.

[0073] Step S330: acquiring historical posture information of the paving robot, where the acquisition time of the historical posture information is earlier than the acquisition time of the posture information.

[0074] Before controlling the paving robot to walk based on its posture information, it is also possible to first determine whether the acquired image is an erroneous recognition by the machine vision device, wherein it is possible to determine whether the deviation between the acquired posture information and the historical posture information is too large. When the deviation between the acquired posture information and the historical posture information is too large, it can be considered that the currently acquired image is an erroneous recognition by the machine vision device, and the currently acquired posture information can be discarded, and the image including the paving route can continue to be acquired. Specifically, in this embodiment, the historical posture information of the paving robot can be acquired, and the acquisition time of the historical posture information is earlier than the acquisition time of the posture information.

[0075] In some embodiments, the earliest historical posture information can be obtained, wherein the earliest historical posture information can be the posture information obtained when the paving robot is in the starting state; or it can be the posture information obtained earliest within a preset time period. For example, the preset time period is 7:00-8:00, and the posture information obtained at 7:00 can be used as the earliest historical posture information obtained within the preset time period. As another embodiment, the most recent historical posture information can also be obtained, that is, the historical posture information with the acquisition time closest to the acquisition time of this posture information. For example, the acquisition time of this posture information can be first obtained as 8:01, and the acquisition time of the posture information closest to the acquisition time of this posture information is 8:00, then the posture information obtained at 8:00 can be used as the most recent historical posture information. As another embodiment, all historical posture information earlier than the posture information can also be obtained, which is not limited here. Among them, the posture information can be stored after each acquisition of the posture information, which can be stored locally in the paving robot or in the cloud, which is not limited here. After the posture information is stored, it can be iteratively updated for subsequent use. As an implementation method, the posture information can be stored and updated based on quantity, that is, the amount of posture information stored is limited. When new posture information is obtained and the amount of currently stored posture information is saturated, the first stored posture information can be deleted, and then the new posture information can be stored. As an implementation method, the posture information can be stored and updated based on a preset time period, that is, the posture information is updated every preset time period. For example, the posture information can be updated every hour. The currently stored posture information is the posture information obtained from 7:00-8:00. If the time changes to 8:01, the posture information obtained from 7:00-8:00 can be deleted, and the posture information obtained from 8:00-9:00 can be stored.

[0076] Step S340: Calculate the difference between the historical posture information and the posture information.

[0077] In this embodiment, the deviation between the historical posture information and the posture information obtained above is obtained, and the difference between the historical posture information and the posture information can be calculated. The posture information may include a position offset and an angle offset, so the difference between the historical position offset and the position offset obtained this time can be calculated, and the difference between the historical angle offset and the angle offset obtained this time can be calculated.

[0078] In some embodiments, it is also possible to first obtain all historical posture information that is earlier than the posture information, calculate the sum of all historical posture information, and when new posture information is obtained (i.e., the posture information obtained in step S320), delete the historical posture information with the earliest acquisition time, calculate the sum of the remaining multiple historical posture information and the new posture information, and finally calculate the error between the two sums.

[0079] Step S350: When the difference is less than the difference threshold, the paving robot is controlled to walk based on the posture information.

[0080] In this embodiment, when the difference between the historical posture information and the posture information is less than the difference threshold, it proves that the acquired posture information is correctly identified by the machine vision device, and the posture information can be used to control the walking of the paving robot. The specific control method can refer to the above embodiment and will not be repeated here. If the difference between the historical posture information and the posture information is greater than the difference threshold, it can be considered that the acquired posture information is an erroneous identification of the machine vision device, and the posture information acquired this time can be discarded, and the image including the paving route can continue to be acquired.

[0081] Compared with the navigation control method provided in the above embodiment, Figure 1 The navigation control method shown in this embodiment also determines whether the posture information obtained this time is an erroneous recognition of the machine vision device based on the difference between the historical posture information and the posture information obtained this time, thereby achieving more precise control of the paving robot.

[0082] See also Figure 6 , Figure 6 FIG. 1 is a flow chart showing another navigation control method provided by an embodiment of the present application. Figure 6 The process shown is described in detail, and the method may specifically include steps S410-S490.

[0083] Step S410: Acquire an image including a paving route.

[0084] Step S420: Acquire the position and posture information of the paving robot based on the image.

[0085] Step S430: Controlling the paving robot to move based on the posture information.

[0086] For the detailed description of step S410 to step S430 , please refer to step S110 to step S130 , which will not be repeated here.

[0087] Step S440: Obtain the left wheel speed and the right wheel speed of the paving robot at the current moment.

[0088] In actual operation, the speed of motor feedback may not be immediate and accurate, and the speed of the motor itself may also have errors. For the differential gear system, these tiny errors may cause the paving robot to produce an additional motion trajectory approaching the Y direction when it stops. At the same time, according to the correct solution of the differential wheel kinematic model, that is, the speed of the paving robot in the direction of travel is the average of the two wheel speeds. The lateral speed of the paving robot is 0, and the angular speed of the paving robot is the difference between the two wheel speeds. Wherein, l is the wheelbase. Therefore, the above error will also produce an unnecessary steering angular velocity, and this steering angular velocity will further expand the error, thereby producing a butterfly effect causing the chassis angle to deviate more and more until the speed in the X direction is reduced to 0. Therefore, it is necessary to reduce the offset caused by the error. In this embodiment, the Y direction speed information can be controlled based on the X direction speed information, thereby reducing the offset caused by the error. Specifically, the left wheel speed and the right wheel speed of the paving robot at the current moment can be obtained first, and the actual travel speed of the paving robot can be determined based on the left wheel speed and the right wheel speed of the paving robot at the current moment.

[0089] In some embodiments, the left wheel speed and the right wheel speed of the paving robot at the current moment can be obtained through the motors of the left and right wheels of the paving robot. Specifically, the rotation speed of the motor can be obtained, and the left wheel speed and the right wheel speed can be obtained according to the rotation speed of the motor. As another embodiment, the paving robot can also be provided with a sensor, and the left wheel speed and the right wheel speed of the paving robot at the current moment can be obtained through the sensor.

[0090] Step S450: Determine the actual travel speed of the paving robot at the current moment based on the left wheel speed and the right wheel speed at the current moment.

[0091] In this embodiment, the actual travel speed of the paving robot at the current moment can be determined based on the left wheel speed and the right wheel speed at the current moment. The speed difference between the left wheel speed and the right wheel speed can be used as the actual travel speed at the current moment, or the sum of the left wheel speed and the right wheel speed can be used as the actual travel speed at the current moment, or the left wheel speed can be used as the actual travel speed at the current moment, or the right wheel speed can be used as the actual travel speed at the current moment, without limitation here.

[0092] Step S460: Obtain the ideal travel speed of the paving robot.

[0093] In this embodiment, the ideal travel speed of the paving robot can be obtained. Among them, the ideal travel speed of the paving robot can be pre-stored, and the ideal travel speed of the paving robot can be directly obtained. Further, the ideal left wheel speed and the ideal right wheel speed of the paving robot can also be obtained, and the speed difference between the ideal left wheel speed and the ideal right wheel speed can be used as the actual travel speed at the current moment, or the speed sum of the ideal left wheel speed and the ideal right wheel speed can be used as the actual travel speed at the current moment, and the ideal left wheel speed can also be used as the actual travel speed at the current moment, or the ideal right wheel speed can be used as the actual travel speed at the current moment, without limitation here.

[0094] Step S470: Calculate the speed difference between the actual traveling speed and the ideal traveling speed.

[0095] In this embodiment, the speed difference between the actual travel speed and the ideal travel speed can be calculated, and the error between the current left wheel speed and the right wheel speed and the ideal left wheel speed and the ideal right wheel speed can be determined based on the speed difference.

[0096] Step S480: When the speed difference is greater than the speed difference threshold and the current motion state of the paving robot does not meet the preset motion state, the Y direction speed information of the paving robot is controlled based on the X direction speed information of the paving robot, wherein the X direction is the moving direction of the paving robot, and the X direction speed information is calculated based on the left wheel speed and the right wheel speed at the current moment; the Y direction intersects with the X direction.

[0097] In this embodiment, when the speed difference between the actual travel speed and the ideal travel speed is greater than the speed difference threshold, it indicates that the left wheel speed and the right wheel speed of the paving robot at the current moment have a large error with the ideal left wheel speed and the ideal right wheel speed. At the same time, the current motion state of the paving robot is obtained. If the current motion state of the paving robot does not meet the preset motion state, in order to ensure the stability of the X-direction speed information, the Y-direction speed information can be changed based on the X-direction speed information, where the motion state can include stop, walk, turn left, turn right, retreat, etc.

[0098] In some embodiments, the preset motion state may be pre-set or determined according to the current instruction. For example, if the current instruction is to stop, the preset motion state of the paving robot may be a stop state. If the current motion state of the paving robot obtained indicates that the motor is rotating slightly, it can be concluded that the current motion state of the paving robot does not meet the preset motion state. When the speed difference is greater than the speed difference threshold and the current motion state of the paving robot does not meet the preset motion state, the speed information of the paving robot may be adjusted.

[0099] In some embodiments, the X-direction speed information can be calculated based on the current left wheel speed and the current right wheel speed. Specifically, the speed of the paving robot in the travel direction is the average of the two wheel speeds. The speed information in the X direction is the average of the left wheel speed and the right wheel speed at the current moment. As an implementation method, the speed information in the X direction can also be directly obtained through the main control of the paving robot.

[0100] In some embodiments, the Y direction speed information of the paving robot can be controlled based on the X direction speed information of the paving robot, wherein the X direction is the traveling direction of the paving robot and the Y direction intersects the X direction. As an embodiment, the Y direction speed information can be reduced proportionally according to the X direction speed information, thereby reducing the deviation of the paving robot.

[0101] Step S490: Determine the left wheel speed and the right wheel speed of the paving robot at the next moment based on the X-direction speed information and the Y-direction speed information.

[0102] In this embodiment, the inverse solution of the differential wheel kinematic model can be used, that is, the speed difference between the two wheels is Δv, and the speed in the x direction, that is, the speed in the direction of travel of the paving robot, is v. x , then the left wheel speed v x -Δv, right wheel speed v x +Δv, where Among them, v y is the speed in the Y direction; L is the wheelbase; W is the angular velocity; k is the rotation parameter, the size of k determines v y Therefore, based on the X-direction speed information and Y-direction speed information obtained above, combined with the inverse solution of the differential wheel kinematics model, the left wheel speed and the right wheel speed of the paving robot at the next moment can be calculated.

[0103] Compared with the navigation control method provided in the above embodiment, Figure 1 In the navigation control method shown in FIG. 1 , when there is a large error between the actual travel speed and the ideal travel speed of the paving robot, the Y direction speed information is adjusted according to the X direction speed information, thereby reducing the offset caused by the error.

[0104] See also Figure 7 , Figure 7 FIG. 1 is a flow chart showing another navigation control method provided by an embodiment of the present application. Figure 7 The process shown in the figure is described in detail. The method may specifically include the following steps S510-S530

[0105] Step S510: Acquire an image including a paving route.

[0106] For the detailed description of step S510, please refer to step S110, which will not be repeated here.

[0107] Step S520: Recognize the image to obtain a recognition result of the image.

[0108] In this embodiment, markers may be arranged around the paving route. The markers may be used to represent control instructions, that is, the control instructions of the paving robot may be executed after the marker is identified. For example, when the marker represents a control instruction to stop, the control instruction to stop walking may be executed after the marker is identified, and the paving robot may stop walking; when the marker represents a control instruction to walk, the control instruction to walk may be executed after the marker is identified, and the paving robot may continue walking. Thus, the paving robot may achieve a stop-and-go effect by identifying the marker. The marker may be a pre-set object that is different from the paving route, and it may be any sign with obvious and easily recognizable grayscale information. For example, the marker may include a carrier background and an identification point arranged on the carrier background, and the identification point and the carrier background have different visual parameters, so that the machine vision device may easily identify the marker. For example, the color of the identification point is different from that of the carrier background, so as to facilitate the recognition by a visible light camera, or the reflectivity of the identification point and the carrier background to infrared light is different, so as to facilitate the recognition by an infrared light camera. Specifically, Figure 8 The marker A shown can be a 5cm*5cm square white paper (carrier background) with 4 black dots (identification points) with a radius of 1cm. The shape of the marker can also be circular, triangular, etc. The surface of the marker can also be marked with words "marker", and the color of the marker can also be black, yellow, red, etc. The shape, color, and content of the marker can be designed according to the actual scene and are not limited here.

[0109] In some embodiments, when an image including a paving route is acquired, the image may be identified to obtain an image recognition result, and whether the image contains a marker is determined based on the image recognition result. As an embodiment, feature recognition may be performed on the image, and the identified image features may be compared with pre-stored features of the marker to determine whether the image contains a marker. As another embodiment, an image recognition model may be pre-established, and by inputting an image including a paving route into the image recognition model, the image recognition model may be used to determine whether the image contains a marker.

[0110] Step S530: When the recognition result indicates that the image contains a preset marker, the paving robot is controlled to stop moving.

[0111] In this embodiment, the preset marker can be used to control the paving robot to stop walking. When the recognition result represents that the image contains the preset marker, the paving robot can be controlled to stop walking. Specifically, when the preset marker is recognized, a stop walking instruction can be sent to the main control of the paving robot, and the main control of the paving robot stops the motor by controlling the rotation, so that the paving robot stops walking. Furthermore, when the preset marker is removed or the main control sends a continuous walking route, the paving robot can continue to walk.

[0112] In some embodiments, different markers can be set around the paving route, wherein different markers represent different control instructions. For example, marker A is used to control the paving robot to stop walking, marker B is used to control the paving robot to continue walking, and marker C is used to control the paving robot to turn left. When the image recognition result shows that the marker contained in the image is marker A, the paving robot can be controlled to stop walking. When the image recognition result shows that the marker contained in the image is marker B, the paving robot can be controlled to continue walking. When the image recognition result shows that the marker contained in the image is marker C, the paving robot can be controlled to turn left.

[0113] In some embodiments, since the machine vision device may collect the same marker multiple times during the walking process of the paving robot, the paving robot may receive the same instruction multiple times, which affects the normal operation of the paving robot. For example, when marker A represents a stop instruction, the paving robot is controlled to stop walking after identifying marker A. When the worker sends an instruction to the paving robot to continue walking, the paving robot starts to walk, but at this time the paving robot will obtain marker A again, and then the robot will be controlled to stop walking again. This will be repeated, which will affect the normal operation of the paving robot. Therefore, an anti-recognition mechanism can also be set to solve the above problem, wherein the anti-recognition mechanism can be to detect whether the paving robot detects a marker within a preset distance. When the paving robot detects a marker within the preset distance, it can not identify the marker and continue to walk; when the paving robot does not detect a marker within the preset distance, the recognition function of the marker can be turned on. Specifically, when the paving robot travels continuously for a certain distance and does not detect a marker, the current state of the paving robot can be set to detectable, that is, if the paving robot continues to detect and detects a marker, the paving robot can be controlled according to the control instructions represented by the marker; when the paving robot detects a marker within this distance, it can be considered that the paving robot has never left the marker paper in its field of vision, and the paving robot can be controlled not according to the marker.

[0114] Compared with the navigation control method provided in the above embodiment, Figure 1The navigation control method shown in the figure, this embodiment also adds a way to control the paving robot without signal transmission, that is, using the special recognition of certain landmarks by the machine vision device to achieve the effect of the robot moving and stopping, thereby improving the flexibility of the paving robot and the variability of the operation, making the paving of waterproof membranes de-manualized, intelligent, and futuristic.

[0115] See also Fig. 9 , Fig. 9 FIG. 1 is a flow chart showing yet another navigation control method provided by an embodiment of the present application. Fig. 9 The process shown is described in detail, and the method may specifically include the following steps S610-S640.

[0116] Step S610: Acquire an image including a paving route.

[0117] Step S620: Acquire the position and posture information of the paving robot based on the image.

[0118] For the detailed description of step S610 to step S620, please refer to step S110 to step S120, which will not be repeated here.

[0119] Step S630: When it is determined that the paving robot is in the starting state and the posture information is greater than the posture information threshold, the paving robot is controlled to walk, and the latest posture information of the paving robot is obtained in real time.

[0120] Since the current waterproofing coil laying robots on the market require the manually operated robots to stop at a nearly perfect set position before starting laying, in this embodiment, a self-adjustment mode of the laying robot is provided, so that the operator does not need to park the robot perfectly at the starting position. Specifically, after obtaining the posture information of the laying robot, it can be determined whether the laying robot is in the starting state. When the laying robot is in the starting state, it can be determined whether the obtained posture information has a large deviation. When the deviation is too large, if the laying robot is directly controlled to walk, the walking route of the laying robot may deviate from the laying route. Therefore, when the deviation is too large, the laying robot can be self-adjusted to reduce the deviation of the posture information; when the deviation is not large, the laying robot can be directly controlled to walk.

[0121] Specifically, when it is determined that the paving robot is in a starting state and the posture information is greater than the posture information threshold, the paving robot can be controlled to walk based on the posture information, and the latest posture information of the paving robot can be obtained in real time. Among them, the posture information threshold can be pre-set by the system or set by the construction worker, which is not limited here. When it is determined that the paving robot is in a starting state and the posture information is greater than the posture information threshold, the self-adjustment mode of the paving robot can be turned on. Among them, the self-adjustment mode can first adjust the posture information of the paving robot to a suitable range, wherein the suitable range refers to the adjusted posture information not greater than the posture information threshold, wherein the speed and direction of the paving robot can be controlled to make the paving robot walk, and the latest posture information of the paving robot can be obtained in real time during the walking process of the paving robot.

[0122] Step S640: When it is detected that the latest posture information is not greater than the posture information threshold, the paving robot is controlled to retreat based on the latest posture information until the paving robot retreats to the starting position.

[0123] In this embodiment, when the paving robot is controlled to walk along the direction of travel, the latest posture information of the paving robot can be obtained in real time during the walking process of the paving robot, and it can be determined whether the latest posture information meets the requirements. When it is detected that the latest posture information is not greater than the posture information threshold, it can be indicated that the current paving robot has a small offset from the paving route, and then the paving robot can be controlled to retreat based on the latest posture information until the paving robot retreats to the starting position. That is, when the paving robot walks until the posture information is not greater than the posture information threshold, the paving robot can be controlled to retreat and maintain the latest posture information until the paving robot retreats to the starting position. At this time, the paving robot is at the starting position and the offset from the paving route is small, indicating that the self-adjustment of the paving robot is completed.

[0124] In some embodiments, the paving robot is controlled to move backward based on the latest posture information until it moves backward to the starting position, and then the paving robot is controlled to move forward for a short distance to eliminate the steering errors of the left and right wheels, and then the paving robot is controlled to stop moving. Thus, through three-stage forward and backward walking adjustment, not only the offset can be reduced, but also the direction of the universal wheel can be adjusted correctly.

[0125] Compared with the navigation control method provided in the above embodiment, Figure 1 The navigation control method shown in this embodiment can also self-adjust the paving robot when the paving robot is in the starting state, thereby eliminating the need to require the operator to park the paving robot perfectly at the starting position, thereby improving the flexibility of the paving robot.

[0126] See also Fig.10 , Fig.10The module block diagram of the navigation control device 100 provided in the embodiment of the present application is shown in FIG. Fig.10 As described in the block diagram, the navigation control device 100 includes: an image acquisition module 110, an information acquisition module 120 and a robot control module 130, wherein:

[0127] The image acquisition module 110 is used to acquire an image including a paving route.

[0128] The information acquisition module 120 is used to acquire the position information of the paving robot based on the image.

[0129] The robot control module 130 is used to control the walking of the paving robot based on the posture information.

[0130] Furthermore, the robot control module 130 includes: a command output submodule and a wheel speed control submodule, wherein:

[0131] The instruction output submodule is used to use the posture information as the input of the fuzzy PID controller to obtain the control instruction output by the fuzzy PID controller, and the control instruction is used to control the left wheel speed and the right wheel speed of the paving robot.

[0132] Furthermore, the instruction output submodule includes: a control parameter determination unit, a control table acquisition unit and a control instruction output unit, wherein:

[0133] The control parameter determination unit is used to obtain the travel speed of the paving robot and determine the PID control parameters based on the travel speed.

[0134] The control table acquisition unit is used to acquire the fuzzy control table corresponding to the fuzzy PID controller.

[0135] The control instruction output unit is used to obtain the control instruction output by the fuzzy PID controller based on the posture information, PID control parameters and fuzzy control table.

[0136] The wheel speed control submodule is used to respond to control instructions and control the left and right wheel speeds of the paving robot.

[0137] Furthermore, the robot control module 130 further includes: a history information acquisition submodule, a difference calculation submodule and a first robot control submodule, wherein:

[0138] The historical information acquisition submodule is used to acquire the historical posture information of the paving robot, and the acquisition time of the historical posture information is earlier than the acquisition time of the posture information.

[0139] The difference calculation submodule is used to calculate the difference between the historical posture information and the posture information.

[0140] The first robot control submodule is used to control the paving robot to walk based on the posture information when the difference is less than the difference threshold.

[0141] Furthermore, the robot control module 130 further includes: a latest information acquisition submodule and a second robot control submodule, wherein:

[0142] The latest information acquisition submodule is used to control the paving robot to walk along the moving direction and obtain the latest posture information of the paving robot when it is determined that the paving robot is in the starting state and the posture information is greater than the posture information threshold.

[0143] The second robot control submodule is used to control the paving robot to walk in a direction opposite to the moving direction based on the latest posture information when it is detected that the latest posture information is not greater than the posture information threshold, until the paving robot walks to the starting position.

[0144] Furthermore, the navigation control device 100 further includes: a wheel speed acquisition module, an actual speed determination module, an ideal speed acquisition module, a speed difference calculation module, a speed control module and a wheel speed determination module, wherein:

[0145] The wheel speed acquisition module is used to obtain the left wheel speed and the right wheel speed of the paving robot at the current moment.

[0146] The actual speed determination module is used to determine the actual travel speed of the paving robot at the current moment based on the left wheel speed and the right wheel speed at the current moment.

[0147] The ideal speed acquisition module is used to obtain the ideal travel speed of the paving robot.

[0148] The speed difference calculation module is used to calculate the speed difference between the actual travel speed and the ideal travel speed.

[0149] The speed control module is used to control the Y direction speed information of the paving robot based on the X direction speed information of the paving robot when the speed difference is greater than the speed difference threshold and the current motion state of the paving robot does not meet the preset motion state, wherein the X direction is the moving direction of the paving robot, the X direction speed information is calculated based on the left wheel speed and the right wheel speed at the current moment, and the Y direction intersects with the X direction.

[0150] The wheel speed determination module is used to determine the left wheel speed and the right wheel speed of the paving robot at the next moment based on the X-direction speed information and the Y-direction speed information.

[0151] Furthermore, the navigation control device 100 further includes: an image recognition module and a second robot control module, wherein:

[0152] The image recognition module is used to recognize the image and obtain the recognition result of the image.

[0153] The second robot control module is used to control the paving robot to stop moving when the recognition result represents that the image contains a preset marker.

[0154] Furthermore, the navigation control device 100 further includes: a paving control module, wherein:

[0155] The paving control module is used to control the paving robot to perform paving.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0157] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0158] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0159] See also Fig.11 , which shows a structural block diagram of a paving robot 200 provided in an embodiment of the present application. The paving robot 200 in the present application may include one or more of the following components: a processor 210, a memory 220, and one or more application programs, wherein the one or more application programs may be stored in the memory 220 and configured to be executed by one or more processors 210, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0160] Among them, the processor 210 may include one or more processing cores. The processor 210 uses various interfaces and lines to connect the various parts of the entire paving robot 200, and executes various functions and processes data of the paving robot 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 210 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 210 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 210, but implemented separately through a communication chip.

[0161] The memory 220 may include a random access memory (RAM) or a read-only memory (ROM). The memory 220 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 220 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also be paved with data created by the robot 200 during use (such as a phone book, audio and video data, chat record data), etc.

[0162] See also Fig.12 , which shows a structural block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable storage medium 300 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.

[0163] The computer readable storage medium 300 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 300 includes a non-transitory computer-readable storage medium. The computer readable storage medium 300 has storage space for program code 310 that performs any method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code 310 can be compressed, for example, in an appropriate form.

[0164] In summary, the navigation control method, device, paving robot and storage medium provided in the embodiments of the present application acquire an image including a paving route; acquire the position information of the paving robot based on the image; and control the paving robot to walk based on the position information. The present application acquires an image including a paving route through a visual system, and controls the paving robot to walk based on the image, so that the paving robot can be automatically controlled to walk along the paving route, thereby improving walking accuracy, reducing manual intervention, and reducing labor costs.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A navigation control method, characterized in that: Applied to a paving robot, the method comprises: Acquiring an image including a paving route; Acquiring position information of the paving robot based on the image; and Controlling the paving robot to walk based on the posture information; After controlling the paving robot to walk based on the posture information, the method further includes: Obtaining the left wheel speed and the right wheel speed of the paving robot at the current moment; Determining the actual travel speed of the paving robot at the current moment based on the left wheel speed and the right wheel speed at the current moment; Obtaining an ideal travel speed of the paving robot; Calculating a speed difference between the actual traveling speed and the ideal traveling speed; When the speed difference is greater than the speed difference threshold and the current motion state of the paving robot does not meet the preset motion state, the Y direction speed information of the paving robot is controlled based on the X direction speed information of the paving robot, wherein the X direction is the moving direction of the paving robot, and the X direction speed information is calculated based on the left wheel speed and the right wheel speed at the current moment; the Y direction intersects the X direction; the Y direction speed information is reduced in proportion to the X direction speed information to reduce the deviation of the paving robot; and Based on the X-direction speed information and the Y-direction speed information, determine the left wheel speed and the right wheel speed of the paving robot at the next moment: Assume that the speed difference between the left wheel and the right wheel is Δv, and the X-direction speed is v x , then the left wheel speed is v x -Δv, the right wheel speed is v x +Δv, where Among them, v y is the speed in the Y direction; L is the wheelbase; W is the angular velocity; k is the rotation parameter; based on the speed information in the X direction and the speed information in the Y direction, combined with the inverse solution of the differential wheel kinematic model, the left wheel speed and the right wheel speed of the paving robot at the next moment are calculated.

2. The method according to claim 1, characterized in that The step of controlling the paving robot to walk based on the posture information includes: Using the posture information as an input of a fuzzy PID controller to obtain a control instruction output by the fuzzy PID controller, wherein the control instruction is used to control the left wheel speed and the right wheel speed of the paving robot; and In response to the control instruction, the left wheel speed and the right wheel speed of the paving robot are controlled.

3. The method according to claim 2, characterized in that The step of using the posture information as an input of a fuzzy PID controller to obtain a control instruction output by the fuzzy PID controller includes: Acquiring a traveling speed of the paving robot, and determining a PID control parameter based on the traveling speed; Obtaining a fuzzy control table corresponding to the fuzzy PID controller; and Based on the posture information, the PID control parameters and the fuzzy control table, a control instruction output by a fuzzy PID controller is obtained.

4. The method according to claim 1, characterized in that: Before controlling the paving robot to walk based on the posture information, the method further includes: Acquire historical position and posture information of the paving robot, where the acquisition time of the historical position and posture information is earlier than the acquisition time of the position and posture information; Calculating the difference between the historical posture information and the posture information; and When the difference is less than a difference threshold, the paving robot is controlled to walk based on the posture information.

5. The method according to any one of claims 1 to 4, characterized in that: After acquiring the image including the paving route, the method further includes: Recognize the image to obtain a recognition result of the image; and When the recognition result indicates that the image contains a preset marker, the paving robot is controlled to stop moving.

6. The method according to any one of claims 1 to 4, characterized in that: The step of controlling the paving robot to walk based on the posture information includes: When it is determined that the paving robot is in a starting state and the position information is greater than a position information threshold, the paving robot is controlled to walk, and the latest position information of the paving robot is acquired in real time; When it is detected that the latest posture information is not greater than the posture information threshold, the paving robot is controlled to retreat based on the latest posture information until the paving robot retreats to a starting position.

7. The method according to any one of claims 1 to 4, characterized in that: After controlling the paving robot to walk based on the posture information, the method further includes: Control the paving robot to perform paving.

8. A navigation control device, characterized in that: Applied to a paving robot, the device comprises: An image acquisition module, used to acquire an image including a paving route; An information acquisition module, used to acquire the position information of the paving robot based on the image; A robot control module, used for controlling the paving robot to walk based on the posture information; The wheel speed acquisition module is used to obtain the left wheel speed and the right wheel speed of the paving robot at the current moment; An actual speed determination module, used to determine the actual travel speed of the paving robot at the current moment based on the left wheel speed and the right wheel speed at the current moment; An ideal speed acquisition module is used to obtain the ideal travel speed of the paving robot; A speed difference calculation module is used to calculate the speed difference between the actual travel speed and the ideal travel speed; The speed control module is used to control the Y direction speed information of the paving robot based on the X direction speed information of the paving robot when the speed difference is greater than the speed difference threshold and the current motion state of the paving robot does not meet the preset motion state, wherein the X direction is the moving direction of the paving robot, the X direction speed information is calculated based on the left wheel speed and the right wheel speed at the current moment, and the Y direction intersects with the X direction; the Y direction speed information is proportionally reduced according to the X direction speed information to reduce the deviation of the paving robot; The wheel speed determination module is used to determine the left and right wheel speeds of the paving robot at the next moment based on the X-direction speed information and the Y-direction speed information: Assume that the speed difference between the left and right wheels is Δv, and the X-direction speed is v x , then the left wheel speed is v x -Δv, the right wheel speed is v x +Δv, where Among them, v y is the speed in the Y direction; L is the wheelbase; W is the angular velocity; k is the rotation parameter; based on the speed information in the X direction and the speed information in the Y direction, combined with the inverse solution of the differential wheel kinematic model, the left wheel speed and the right wheel speed of the paving robot at the next moment are calculated.

9. A paving robot, characterized in that: The method comprises a memory and a processor, wherein the memory is coupled to the processor, and the memory stores instructions. When the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images