Robot positioning method, apparatus, device, and storage medium

Abstract

The application relates to the technical field of robots and discloses a robot positioning method, a robot positioning device, a robot positioning equipment and a storage medium, the method comprising the following steps: generating an information matrix according to first point cloud information at a first moment and a first normal distribution matrix corresponding to the first point cloud information; generating transformation information between the first moment and a second moment on the basis of sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment; predicting a predicted pose state of the robot equipment at the second moment on the basis of the information matrix, a covariance matrix corresponding to second point cloud information at the second moment and the transformation information; and updating the predicted pose state according to the second point cloud information and a second normal distribution matrix corresponding to the second point cloud information to obtain an updated pose state at the second moment. The application can improve the generation accuracy of the updated pose state.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a robot positioning method, device, equipment and storage medium. Background Art

[0002] In current laser positioning solutions, the positioning of mobile robots is achieved by measuring the distance between the laser device and obstacles. Conventional laser positioning performs feature-to-feature matching in three-dimensional / two-dimensional space, such as point-to-point or line-to-line matching. The distribution of matching features and features to be matched is the obstacle in space and the single-frame laser data. When the obstacles are relatively fixed and the shapes of the obstacles are relatively regular, this matching method can obtain accurate matching results. However, in actual applications, the position of some obstacles in space will change, and the regularity of the shapes of some obstacles cannot be effectively guaranteed. For example, in areas with large scene changes, such as temporary exhibition stands added to the hall, and obstacles with large area and low density, such as green plants, due to the strong penetrability of these types of obstacles, it is impossible to accurately measure the distance between the laser device and the obstacle, resulting in the inability to accurately locate and identify the robot. Summary of the Invention

[0003] In view of the above, it is necessary to provide a robot positioning method, device, equipment and storage medium that can solve the technical problem of being unable to accurately position and identify the robot.

[0004] In a first aspect, the present invention provides a robot positioning method, which is applied to a robot device. The robot positioning method includes:

[0005] Generate an information matrix according to the first point cloud information at the first moment and the first normal distribution matrix corresponding to the first point cloud information;

[0006] generating transformation information between a second moment and the first moment based on sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment;

[0007] Predicting a predicted posture state of the robot device at the second moment based on the information matrix, the covariance matrix corresponding to the predicted second point cloud information at the second moment, and the transformation information;

[0008] The predicted posture state is updated according to the second point cloud information and the second normal distribution matrix corresponding to the second point cloud information to obtain the updated posture state at the second moment.

[0009] According to a preferred embodiment of the present invention, generating an information matrix based on the first point cloud information at the first moment and a first normal distribution matrix corresponding to the first point cloud information includes:

[0010] Generate a covariance matrix and a mean corresponding to the first point cloud information according to the first point cloud information;

[0011] generating the first normal distribution matrix according to the covariance matrix corresponding to the first point cloud information and the mean;

[0012] The information matrix is ​​generated according to the first point cloud information and the first normal distribution matrix.

[0013] According to a preferred embodiment of the present invention, the sensors corresponding to the sensor information include: an encoder and an inertial measurement unit;

[0014] The sensor information includes: an initial encoder value of the encoder at the first moment and a target encoder value at the second moment, an initial heading angle of the inertial measurement unit at the first moment and a target heading angle at the second moment.

[0015] According to a preferred embodiment of the present invention, generating transformation information between the second moment and the first moment based on sensor information includes:

[0016] Obtaining the wheel radius of the mobile wheel of the robot device and the total number of pulses of the encoder when the mobile wheel rotates per unit;

[0017] The transformation information is generated based on the sensor information, the wheel radius, and the total number of pulses.

[0018] According to a preferred embodiment of the present invention, the transformation information includes displacement information and rotation information. The generation formula of the displacement information is:

[0019]

[0020] Wherein, Δx represents the displacement information, n t represents the target encoder value, n t-1 represents the initial encoder value, r represents the wheel radius, and f represents the total number of pulses;

[0021] The rotation information is generated as follows:

[0022] The rotation information is generated based on the target heading angle and the initial heading angle.

[0023] According to a preferred embodiment of the present invention, the predicted posture state of the robot device at the second moment is predicted based on the information matrix, the covariance matrix corresponding to the second point cloud information obtained at the second moment, and the transformation information, wherein the implementation formula of the predicted posture is:

[0024]

[0025] in, Represents the predicted pose state, A t represents the transformation information, Ω t-1 represents the information matrix, R t Represents the covariance matrix corresponding to the second point cloud information.

[0026] According to a preferred embodiment of the present invention, the generation formula for updating the posture state is:

[0027]

[0028] Among them, Ω t represents the updated pose state, Represents the predicted pose state, C t Represents the second point cloud information, Q t Represents the second normal distribution matrix corresponding to the second point cloud information.

[0029] In a second aspect, the present invention further provides a robot positioning device, comprising:

[0030] a generating unit, configured to generate an information matrix according to first point cloud information at a first moment and a first normal distribution matrix corresponding to the first point cloud information;

[0031] The generating unit is further configured to generate transformation information between a second moment and the first moment based on sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment;

[0032] A prediction unit, configured to predict a predicted posture state of the robot device at the second moment based on the information matrix, a covariance matrix corresponding to the predicted second point cloud information at the second moment, and the transformation information;

[0033] An updating unit is used to update the predicted posture state according to the second point cloud information and a second normal distribution matrix corresponding to the second point cloud information to obtain an updated posture state at the second moment.

[0034] In a third aspect, the present invention further provides a robotic device, comprising:

[0035] a memory storing computer-readable instructions or computer programs; and

[0036] The processor executes the computer-readable instructions or computer program stored in the memory to implement the robot positioning method.

[0037] In a fourth aspect, the present invention further proposes a computer-readable storage medium, in which computer-readable instructions or a computer program are stored. The computer-readable instructions or the computer program are executed by a processor in a robot device to implement the robot positioning method.

[0038] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program or instructions, which implement the steps of any embodiment of the robot positioning method when executed by a processor.

[0039] It can be seen from the above technical solution that the present application monitors the robot device through the encoder and the inertial measurement unit, and can predict the positioning of the robot device based on the sensor information, the first point cloud information observed by the lidar, and the second point cloud information, and then update the real-time positioning of the robot in combination with the second normal distribution matrix. It can avoid the appearance of obstacles with large area and low density in the scene, which may cause the robot device to be unable to accurately locate and identify, thereby improving the stable positioning of the robot device in dynamic scenes. At the same time, through real-time updating of obstacles, it can avoid the problem of robot positioning matching errors when the on-site environment changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a flow chart of an embodiment of the robot positioning method of the present invention.

[0042] Figure 2 It is a functional module diagram of an embodiment of the robot positioning device of the present invention.

[0043] Figure 3 It is a structural schematic diagram of a robot device according to a preferred embodiment of the robot positioning method provided by the present invention. DETAILED DESCRIPTION

[0044] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0045] like Figure 1 FIG. 1 is a flow chart of an embodiment of a robot positioning method according to the present invention. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

[0046] The robot positioning method can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0047] The robot positioning method is applied to one or more robot devices, which are devices that can automatically perform numerical calculations and / or information processing according to pre-set or stored computer-readable instructions or computer programs. Their hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0048] The robot device can be any electronic product that can interact with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, a mobile robot, etc. The following embodiments use a mobile robot as an example of a robot device.

[0049] The robot device may include a network device and / or a user device. The network device includes, but is not limited to, a single network robot device, a robot device group consisting of multiple network robot devices, or a cloud based on cloud computing consisting of a large number of hosts or network robot devices.

[0050] The network where the robot device is located includes, but is not limited to: the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0051] 101. Generate an information matrix according to first point cloud information at a first moment and a first normal distribution matrix corresponding to the first point cloud information.

[0052] In an embodiment of the present invention, the robotic device may be any robot corresponding to the device type that needs to be put into production in a preset scene, for example, the robotic device may be a navigation robot of model A, etc. The preset scene may be any building, hotel, supermarket, etc.

[0053] A laser sensor is installed in the robot device, which is used to detect the two-dimensional plane contour information of the surrounding environment and collect laser point cloud data of the robot device in the plane coordinate system. The laser sensor can be a 2D laser radar sensor or a 3D laser radar sensor. The embodiment of the present invention does not impose too many restrictions.

[0054] The first point cloud information refers to the laser point cloud data acquired by the laser sensor at the first moment. When the robot device moves within the preset scene, the laser sensor emits laser light toward the preset scene in real time to scan the current environment, and measures the distance between the robot device and obstacles in the preset scene as the first point cloud information.

[0055] In an embodiment of the present invention, the robot device generates an information matrix based on the first point cloud information at the first moment and the first normal distribution matrix corresponding to the first point cloud information, including:

[0056] Generate a covariance matrix and a mean corresponding to the first point cloud information according to the first point cloud information;

[0057] generating the first normal distribution matrix according to the covariance matrix corresponding to the first point cloud information and the mean;

[0058] The information matrix is ​​generated according to the first point cloud information and the first normal distribution matrix.

[0059] Specifically, the robot device generates a covariance matrix corresponding to the first point cloud information according to the first point cloud information, including:

[0060] Extracting the horizontal coordinate value and the vertical coordinate value from the initial point cloud information;

[0061] Calculate the covariance of each abscissa value and the corresponding ordinate value;

[0062] An initial covariance matrix corresponding to the first point cloud information is constructed according to the covariance.

[0063] Specifically, the generation method of the first normal distribution matrix is ​​similar to the generation method of the second normal distribution matrix. The generation method of the second normal distribution matrix has been explained below and will not be repeated in this application.

[0064] Specifically, when the first moment is the starting moment of the movement of the robot device, the generation formula of the information matrix is:

[0065]

[0066] Among them, Ω t-1 Denotes the information matrix, C t-1 represents the first point cloud information, Q t-1 represents the first normal distribution matrix.

[0067] 102 : Generate transformation information between a second moment and the first moment based on sensor information, where the sensor information is sensor information acquired between the first moment and the second moment.

[0068] In an embodiment of the present invention, the sensor information is data collected by sensors carried by the robot itself, and the sensors include: an encoder and an inertial measurement unit (IMU) installed on the robot device, wherein the encoder can be a rotary encoder, and the inertial measurement unit includes a gyroscope, etc.

[0069] In an embodiment of the present invention, the sensor information includes: the initial encoder value of the encoder at the first moment and the target encoder value obtained between the first moment and the second moment, the initial heading angle of the inertial measurement unit at the first moment and the target heading angle obtained between the first moment and the second moment.

[0070] The second moment refers to the next moment of the first moment, for example, the first moment is 12:00.30, and the second moment is 12:00.31 or 12:00.32. The sensor information used here is the sensor data between the first moment and the second moment. The robot obtains sensor information in real time during the movement, so the robot will continue to obtain sensor information between the first moment and the second moment, and use this sensor data to predict the transformation information of the robot at the second moment, so as to predict the position and posture of the robot at the second moment.

[0071] The transformation information includes the displacement information and rotation information from the first moment to the second moment. The transformation information between the second moment and the first moment in this step is the transformation information of the displacement information and rotation information obtained by the robot's sensor at the current moment relative to the first moment.

[0072] In an embodiment of the present invention, the robot device generates transformation information between the second moment and the first moment based on sensor information, including:

[0073] Obtaining the wheel radius of the mobile wheel of the robot device and the total number of pulses of the encoder when the mobile wheel rotates per unit;

[0074] The transformation information is generated based on the sensor information, the wheel radius, and the total number of pulses.

[0075] The moving wheels refer to wheels installed on the robot device that enable the robot device to move.

[0076] By combining the sensor information, the wheel radius, and the total number of pulses, the transformation information can be accurately generated.

[0077] Specifically, the generation formula of the displacement information is:

[0078]

[0079] Wherein, Δx represents the displacement information, n t represents the target encoder value, n t-1 represents the initial encoder value, r represents the wheel radius, and f represents the total number of pulses;

[0080] Specifically, the robot device generates the rotation information based on an angle difference between the target heading angle and the initial heading angle.

[0081] 103 , predicting a predicted posture state of the robot device at the second moment based on the information matrix, the covariance matrix corresponding to the second point cloud information obtained at the predicted second moment, and the transformation information.

[0082] In an embodiment of the present invention, the second point cloud information refers to the point cloud obtained by the robot device at the second moment. The point cloud information used here to predict the robot's posture at the second moment is the point cloud information of the predicted position obtained after the sensor information obtained in step 102 is observed by the filter. The robot obtains the sensor information in step 102 at the current moment, and obtains the corresponding covariance matrix based on this information. As an embodiment, the sensor information obtained by the current robot can be used as the point cloud information of the robot at the second moment.

[0083] The predicted posture state includes: the predicted position and predicted posture of the robot device. The predicted posture state refers to the posture state matrix corresponding to when the displacement information and the rotation information are optimized to convergence.

[0084] The optimization convergence conditions of the displacement information and the rotation information are as follows: based on the displacement information and the rotation information, the second point cloud information is spatially transformed, and the transformed point cloud is mapped to the laser point cloud corresponding to the first point cloud information, the normal distribution probability value corresponding to each transformed point cloud in the first point cloud information is determined, and the score of the displacement information and the rotation information is calculated. If the score cannot be increased or the increase does not exceed a preset threshold, it is determined that the displacement information and the rotation information meet the optimization convergence conditions.

[0085] The calculation formula of the normal distribution probability value is:

[0086]

[0087] Wherein, P(x) represents the normal distribution probability value, p represents the number of position information in the initial point cloud information, μ represents the mean of multiple position information, and ∑ represents the initial covariance matrix.

[0088] In an embodiment of the present invention, when the location information is larger, the corresponding probability value is larger, indicating that the probability of an obstacle existing in the location information is greater. The robotic device may also perform real-time mapping of the preset scene based on the normal distribution probability value and the prior map of the preset scene.

[0089] In an embodiment of the present invention, the robot device predicts a predicted posture state of the robot device at the second moment based on the information matrix, the covariance matrix corresponding to the second point cloud information obtained at the second moment, and the transformation information, wherein the implementation formula of the predicted posture state is:

[0090]

[0091] in, Represents the predicted pose state, A t represents the transformation information, Ω t-1 represents the information matrix, R t Represents the covariance matrix corresponding to the second point cloud information.

[0092] In other embodiments, the covariance matrix corresponding to the second point cloud information is generated in a similar manner to the covariance matrix corresponding to the first point cloud information, and this application will not elaborate on this.

[0093] 104. Update the predicted posture state according to the second point cloud information and the second normal distribution matrix corresponding to the second point cloud information to obtain an updated posture state at the second moment.

[0094] In an embodiment of the present invention, the updated posture state refers to a posture state matrix generated after updating the predicted posture state.

[0095] In an embodiment of the present invention, the generation formula for updating the posture state is:

[0096]

[0097] Among them, Ω t represents the updated pose state, Represents the predicted pose state, C t Represents the second point cloud information, Q t Represents the second normal distribution matrix corresponding to the second point cloud information.

[0098] Specifically, the calculation formula of the second normal distribution matrix is:

[0099]

[0100] Among them, Q t represents the second normal distribution matrix, det represents the determinant of the matrix, ∑ represents the covariance matrix corresponding to the second point cloud information, x represents the second point cloud information, and μ represents the mean of multiple position information in the second point cloud information.

[0101] It can be seen from the above technical solution that the present application monitors the robot device through the encoder and the inertial measurement unit, and can predict the positioning of the robot device based on the sensor information, the first point cloud information observed by the lidar, and the second point cloud information, and then update the real-time positioning of the robot in combination with the second normal distribution matrix. It can avoid the appearance of obstacles with large area and low density in the scene, which may cause the robot device to be unable to accurately locate and identify, thereby improving the stable positioning of the robot device in dynamic scenes. At the same time, through real-time updating of obstacles, it can avoid the problem of robot positioning matching errors when the on-site environment changes.

[0102] like Figure 2 FIG2 shows a functional block diagram of an embodiment of a robot positioning device according to the present invention. The robot positioning device 11 includes a generation unit 110, a prediction unit 111, and an update unit 112. A module / unit as referred to herein refers to a series of computer-readable instruction segments or computer programs that can be accessed by the processor 13 and perform a fixed function, and is stored in the memory 12. The functions of each module / unit in this embodiment will be described in detail in subsequent embodiments.

[0103] A generating unit 110 is configured to generate an information matrix based on first point cloud information at a first moment and a first normal distribution matrix corresponding to the first point cloud information;

[0104] The generating unit 110 is further configured to generate transformation information between a second moment and the first moment based on sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment;

[0105] A prediction unit 111 is configured to predict a predicted posture state of the robot device at the second moment based on the information matrix, a covariance matrix corresponding to the predicted second point cloud information at the second moment, and the transformation information;

[0106] The updating unit 112 is used to update the predicted posture state according to the second point cloud information and the second normal distribution matrix corresponding to the second point cloud information to obtain the updated posture state at the second moment.

[0107] When the robot positioning device 11 is specifically implemented, the robot positioning method described in any of the above embodiments can be used to achieve positioning of the robot device.

[0108] like Figure 3 As shown, this is a schematic structural diagram of a robot device according to a preferred embodiment of the robot positioning method provided by the present invention.

[0109] The robotic device 1 includes a memory 12 , a processor 13 , and computer-readable instructions or computer programs stored in the memory 12 and executable on the processor 13 , such as a robotic positioning program.

[0110] Those skilled in the art will understand that the schematic diagram is merely an example of the robot device 1 and does not constitute a limitation on the robot device 1. The robot device 1 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the robot device 1 may also include input and output devices, network access devices, buses, etc.

[0111] The processor 13 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 13 is the computing core and control center of the robot device 1, connecting various parts of the entire robot device 1 using various interfaces and lines, and executing the operating system of the robot device 1 as well as various installed applications, program codes, etc.

[0112] Exemplarily, the computer-readable instructions may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, and the computer-readable instruction segments are used to describe the execution process of the computer-readable instructions in the robotic device 1. For example, the computer-readable instructions may be divided into a generation unit 110, a prediction unit 111, and an update unit 112.

[0113] The memory 12 can be used to store the computer-readable instructions and / or modules. The processor 13 implements the various functions of the robotic device 1 by running or executing the computer-readable instructions and / or modules stored in the memory 12 and accessing the data stored in the memory 12. The memory 12 can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the robotic device. The memory 12 can include non-volatile and volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other storage devices.

[0114] The memory 12 may be an external memory and / or an internal memory of the robot device 1. Furthermore, the memory 12 may be a physical memory, such as a memory stick, a TF card (Trans-flash Card), and the like.

[0115] If the modules / units integrated into the robotic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-mentioned method embodiments by instructing the relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When executed by a processor, the computer-readable instructions can implement the steps of each of the above-mentioned method embodiments.

[0116] The computer-readable instructions include computer-readable instruction codes, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer-readable instruction codes, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), or a random access memory (RAM).

[0117] Combine Figure 1 The memory 12 in the robot device 1 stores computer-readable instructions to implement a robot positioning method. The processor 13 can execute the computer-readable instructions or computer program according to the robot positioning method in any of the above embodiments, which will not be repeated here.

[0118] In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementation may employ other division methods.

[0119] The present invention provides a computer-readable storage medium having computer-readable instructions or a computer program stored thereon, wherein the computer-readable instructions or the computer program, when executed by the processor 13, follow the steps of the robot positioning method in any of the above embodiments.

[0120] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0121] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0122] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0123] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices described may also be implemented by a single unit or device through software or hardware. Terms such as first and second are used to indicate names and do not imply any particular order.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A robot positioning method, applied to a robot device, characterized in that: The robot positioning method comprises: Generate a covariance matrix and a mean corresponding to the first point cloud information according to the first point cloud information at the first moment; generating a first normal distribution matrix according to the covariance matrix corresponding to the first point cloud information and the mean; generating an information matrix according to the first point cloud information and the first normal distribution matrix; generating transformation information between a second moment and the first moment based on sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment; Predicting a predicted posture state of the robot device at the second moment based on the information matrix, the covariance matrix corresponding to the predicted second point cloud information at the second moment, and the transformation information; Updating the predicted posture state according to the second point cloud information and a second normal distribution matrix corresponding to the second point cloud information to obtain an updated posture state at the second moment; Among them, the realization formula of the predicted posture state is: ； represents the predicted pose state, represents the transformation information, represents the information matrix, Represents the covariance matrix corresponding to the second point cloud information; The generation formula of the updated posture state is: ； represents the updated pose state, represents the second point cloud information, Represents the second normal distribution matrix corresponding to the second point cloud information.

2. The robot positioning method according to claim 1, wherein: The sensors corresponding to the sensor information include: an encoder and an inertial measurement unit; The sensor information includes: an initial encoder value of the encoder at the first moment and a target encoder value at the second moment, an initial heading angle of the inertial measurement unit at the first moment and a target heading angle at the second moment.

3. The robot positioning method according to claim 2, wherein: The generating, based on the sensor information, the transformation information between the second moment and the first moment includes: Obtaining the wheel radius of the mobile wheel of the robot device and the total number of pulses of the encoder when the mobile wheel rotates per unit; The transformation information is generated based on the sensor information, the wheel radius, and the total number of pulses.

4. The robot positioning method according to claim 3, wherein: The transformation information includes displacement information and rotation information. The generation formula of the displacement information is: ； in, represents the displacement information, represents the target encoder value, represents the initial encoder value, represents the wheel radius, represents the total number of pulses; The rotation information is generated as follows: The rotation information is generated based on the target heading angle and the initial heading angle.

5. A robot positioning device, running in a robot device, characterized in that: The robot positioning device comprises: a generating unit, configured to generate a covariance matrix and a mean corresponding to the first point cloud information based on the first point cloud information at the first moment; generate a first normal distribution matrix based on the covariance matrix and the mean corresponding to the first point cloud information; and generate an information matrix based on the first point cloud information and the first normal distribution matrix; The generating unit is further configured to generate transformation information between a second moment and the first moment based on sensor information, wherein the sensor information is sensor information acquired between the first moment and the second moment; A prediction unit, configured to predict a predicted posture state of the robot device at the second moment based on the information matrix, a covariance matrix corresponding to the predicted second point cloud information at the second moment, and the transformation information; an updating unit, configured to update the predicted posture state according to the second point cloud information and a second normal distribution matrix corresponding to the second point cloud information, to obtain an updated posture state at the second moment; Among them, the realization formula of the predicted posture state is: ； represents the predicted pose state, represents the transformation information, represents the information matrix, Represents the covariance matrix corresponding to the second point cloud information; The generation formula of the updated posture state is: ； represents the updated pose state, represents the second point cloud information, Represents the second normal distribution matrix corresponding to the second point cloud information.

6. A robotic device, characterized in that: The robotic device comprises: a memory storing computer-readable instructions; and A processor is configured to execute computer-readable instructions stored in the memory to implement the robot positioning method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by a processor in a robotic device to implement the robot positioning method according to any one of claims 1 to 4.

Images