Laser positioning method, device, equipment and storage medium

By screening and registering the intensity change characteristic points in the environment in lidar, the problem of degradation of positioning accuracy of lidar when the environmental scene is not obvious or there are obstacles, achieving higher positioning accuracy.

CN116819544BActive Publication Date: 2024-11-15GUANGZHOU SAITE INTELLIGENCE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310802537.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-03
Publication Date
2024-11-15
Estimated Expiration
2043-07-03

AI Technical Summary

Technical Problem

When the environmental scene is not obvious or there are obstacles, the accuracy of the lidar positioning method decreases, especially during long-distance scanning, the laser point clouds formed by the reflective patch are relatively sparse, resulting in a reduced positioning accuracy.

Method used

By driving the original points in the lidar scan environment, screen the feature points that characterize the intensity changes, and mark them onto the electronic map, register with the feature points in the map, and generate dense positioning features, thereby improving positioning accuracy.

Benefits of technology

The intensity change characteristics in the environment assist in positioning, and the stable and reliable positioning characteristics are generated, which improves the accuracy of lidar positioning and overcomes the problems of point cloud sparseness and obstacle occlusion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116819544B_ABST
    Figure CN116819544B_ABST
Patent Text Reader

Abstract

The present invention discloses a laser positioning method, device, equipment and storage medium, the method comprising: driving a laser radar to scan a first original point in an environment; screening a feature characterizing intensity change in the first original point as a first feature point; marking the first original point in an electronic map corresponding to the environment, the electronic map having a second original point, and the second original point having a second feature point characterizing intensity change; aligning the first original point with the second original point to obtain a first target point; aligning the first feature point with the second feature point to obtain a second target point; generating a positioning point for the environment according to the first target point and the second target point. This embodiment supplements the reflective sticker, and generally the environment has more intensity change features to assist positioning, which can make full use of the original information in the environment to generate dense positioning features, and the positioning features are stable and reliable, thereby improving the accuracy of positioning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] Robots are often deployed in factory environments. The robots are equipped with lidars, which use lidars to scan point clouds, align and locate the point clouds, and are responsible for business operations such as material transportation and fixed-point patrols.

[0003] In similar environments or environments where structural features are not obvious, the positioning method that relies on laser point cloud registration fails. For this reason, reflective stickers are deployed in the environment to increase the reflectivity of the laser as positioning points.

[0004] However, the laser point cloud formed by the reflective tape is relatively sparse, which is particularly obvious when scanning at a long distance. In addition, the reflective tape is easily blocked by obstacles such as trees, resulting in a small number of point clouds and a decrease in positioning accuracy. Summary of the invention

[0005] The present invention provides a laser positioning method, device, equipment and storage medium to solve the problem of how to improve the accuracy of laser radar positioning.

[0006] According to one aspect of the present invention, there is provided a laser positioning method, comprising:

[0007] Drive the laser radar to scan the first original point in the environment;

[0008] Selecting a feature representing the intensity change from the first original point as a first feature point;

[0009] Marking the first original point in an electronic map corresponding to the environment, wherein the electronic map has a second original point, and the second original point has a second characteristic point representing intensity change;

[0010] Registering the first original point with the second original point to obtain a first target point;

[0011] Aligning the first feature point with the second feature point to obtain a second target point;

[0012] A positioning point is generated for the environment according to the first target point and the second target point.

[0013] According to another aspect of the present invention, there is provided a laser positioning device, comprising:

[0014] A laser scanning module, used to drive the laser radar to scan a first original point in the environment;

[0015] An intensity change feature screening module, used to screen features representing intensity changes from the first original points as first feature points;

[0016] A point cloud marking module, used for marking the first original point in an electronic map corresponding to the environment, wherein the electronic map has a second original point, and the second original point has a second characteristic point representing an intensity change;

[0017] An original point registration module, used for registering the first original point with the second original point to obtain a first target point;

[0018] A feature point registration module, used for registering the first feature point with the second feature point to obtain a second target point;

[0019] A positioning point generating module is used to generate a positioning point for the environment according to the first target point and the second target point.

[0020] According to another aspect of the present invention, there is provided a robot, the robot comprising:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the laser positioning method described in any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the laser positioning method described in any embodiment of the present invention when executed.

[0025] In this embodiment, the laser radar is driven to scan the first original point in the environment; the feature characterizing the intensity change is selected in the first original point as the first feature point; the first original point is marked in the electronic map corresponding to the environment, the electronic map has a second original point, and the second original point has a second feature point characterizing the intensity change; the first original point is aligned with the second original point to obtain the first target point; the first feature point is aligned with the second feature point to obtain the second target point; and the positioning point is generated for the environment according to the first target point and the second target point. This embodiment supplements the reflective sticker, and usually there are more intensity change features in the environment to assist in positioning, which can make full use of the original information in the environment to generate dense positioning features, and the positioning features are stable and reliable, thereby improving the accuracy of positioning.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 is a flow chart of a laser positioning method provided according to Embodiment 1 of the present invention;

[0029] Figure 2 is a schematic structural diagram of a laser positioning device provided according to Embodiment 2 of the present invention;

[0030] Figure 3 It is a schematic diagram of the structure of a robot provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1This is a flow chart of a laser positioning method provided in the first embodiment of the present invention. This embodiment is applicable to the situation where positioning is performed based on the intensity variation characteristics of the laser point cloud. The method can be performed by a laser positioning device, which can be implemented in the form of hardware and / or software, and can be configured in a robot. Figure 1 As shown, the method includes:

[0035] Step 101: drive the laser radar to scan a first original point in the environment.

[0036] In this embodiment, a laser radar is installed in the robot. The laser radar is composed of multiple transmitters and receivers. Through the rotation of the motor, multiple line beams are obtained. The more lines there are, the more perfect the surface contour of the object is. Therefore, the larger the amount of data processed, the higher the hardware requirements.

[0037] The type of laser radar in the robot can be a single-line laser radar or a multi-line laser radar. Generally, the multi-line laser radar is designed to be an exponential level of 2, such as 4-line, 8-line, 16-line, 32-line, 64-line and 128-line. Different beams collect different information. The robot operates in a specific environment (such as a factory, production line, dock, etc.), and the type of laser radar can be selected according to the requirements of the business operations performed in the specific environment.

[0038] If the intensity variation feature is not obvious in a specific environment, multiple reflective stickers (also known as reflective sheets, reflective plates, etc.) can be set up through simple construction distribution, that is, materials with higher reflectivity to laser signals, to facilitate the creation of intensity variation features.

[0039] When the robot performs business operations in a specific environment, it drives the laser radar in real time to emit laser signals to the environment, thereby scanning point cloud data of the specific environment and recording the points in the point cloud data as the first original points.

[0040] Step 102: Select a feature representing the intensity change from the first original point as the first feature point.

[0041] In the environment where the robot operates, different things may have similar situations on a macro scale, but there are still many subtle changes. These subtle changes are more sensitive to the laser signal emitted by the lidar and show more obvious changes in the intensity of the reflection. Therefore, the first original points can be traversed, and the features that characterize the intensity changes (part of the first original points) can be screened out from all the first original points, and these first original points that characterize the intensity changes are recorded as the first feature points.

[0042] In one embodiment of the present invention, step 102 may include the following steps:

[0043] Step 1021, traverse the first reference point and the second reference point in the first original point.

[0044] In this embodiment, starting from the second first original point and traversing each first original point, two first original points that meet specific conditions are screened out from all the first original points and recorded as the first reference point and the second reference point, wherein the first reference point and the second reference point are adjacent in the timing of the scan, and the first reference point and the second reference point are close in geographical location.

[0045] In a specific implementation, each first original point has coordinates (x, y, z) in terms of geographical location. In terms of scanning sequence, the current first original point is adjacent to the previous first original point. Then, the coordinates can be used to calculate the first distance value (such as Euclidean distance) in terms of geographical location between the current first original point and the previous first original point.

[0046] Query the angular resolution of the laser radar in the horizontal direction, add the product of the first distance value and the angular resolution to the preset distance coefficient to obtain the nearest neighbor threshold. Then, the nearest neighbor threshold can be expressed as:

[0047] d = α + range * resolution

[0048] Among them, d is the nearest neighbor threshold, α is the distance coefficient, the distance coefficient is a positive number, such as 0.1, range is the first distance value, and resolution is the angular resolution of the laser radar in the horizontal direction.

[0049] If the distance between the robot (i.e., the laser radar) and the target object is farther, the first original point is sparser. At this time, the neighbor threshold is adaptively increased to expand the range of the neighbors, thereby ensuring that the first original point of the neighbors can be screened out in terms of geographical location.

[0050] For a given first distance value, the first distance value may be compared with a corresponding neighbor threshold.

[0051] If the first distance value is less than the neighbor threshold, the current first original point and the previous first original point are geographically neighboring, the current first original point is the first reference point, and the previous first original point is the second reference point.

[0052] Step 1022: Calculate the difference between the intensity value of the first reference point and the intensity value of the second reference point as the intensity change value.

[0053] In practical applications, each first original point has a reflected intensity value. For the convenience of budgeting, the intensity value of each first original point can be normalized to a specified range, such as [0, 100]. The intensity value of the first reference point is subtracted from the intensity value of the second reference point, and the difference between the two is set as the intensity change value delta_i.

[0054] Step 1023: If the intensity change value is greater than a preset change threshold, determine the first reference point as a first feature point representing the intensity change, and set the intensity change value as a coding value of the first feature point.

[0055] The intensity change value delta_i is compared with a preset change threshold (such as 30). If the intensity change value delta_i is greater than the preset change threshold, it means that there is a large change in the reflected intensity value between the first reference point and the second reference point. The first reference point can be determined as the first feature point characterizing the intensity change, and the intensity change value delta_i is set as the encoding value of the first feature point. The first feature point is represented as result1(x, y, z, delta_i).

[0056] Step 103: Mark the first original point in the electronic map corresponding to the environment.

[0057] In one case, the robot can drive the laser radar to scan multiple frames of point cloud data of the environment in real time, superimpose the multiple frames of point cloud data in real time, and create an electronic map of the environment. In the process of creating the electronic map, the first original point (including the first feature point) is marked in the electronic map to realize the recording and storage of the first original point (including the first feature point).

[0058] In another case, different robots can pre-drive the laser radar to scan multiple frames of point cloud data of the environment, superimpose the multiple frames of point cloud data and create an electronic map of the environment. The electronic map is stored in each robot, and the current robot marks the first original point (including the first feature point) in the electronic map to record and store the first original point (including the first feature point).

[0059] In this embodiment, the electronic map has point cloud data, which is recorded as second original points, and the second original points have second characteristic points representing intensity changes.

[0060] Generally, the semantics of the first feature point is consistent with the semantics of the second feature point, that is, the method of selecting the first feature point from the first original point is consistent with the method of selecting the second feature point from the first original point.

[0061] Specifically, a third reference point and a fourth reference point are traversed in the second original point, the third reference point and the fourth reference point are adjacent in the scanning time sequence, and the third reference point and the fourth reference point are close in geographical location; the difference between the intensity value of the third reference point and the intensity value of the fourth reference point is calculated as the intensity change value; if the intensity change value is greater than a preset change threshold, the third reference point is determined to be a second feature point characterizing the intensity change, and the intensity change value is set as the encoding value of the second feature point.

[0062] Furthermore, in the scanning sequence, a fourth distance value between the current second original point and the previous second original point in terms of geographical location is calculated; the angular resolution of the laser radar in the horizontal direction is queried; the product of the fourth distance value and the angular resolution is added to a preset distance coefficient to obtain a neighbor threshold; if the fourth distance value is less than the neighbor threshold, the current second original point and the previous second original point are geographically neighbors, the current second original point is the third reference point, and the previous second original point is the fourth reference point.

[0063] Step 104: align the first original point with the second original point to obtain a first target point.

[0064] In this embodiment, a point cloud registration algorithm such as ICP (Iterative Closest Point) and NDT (Normal Distribution Transform) can be used to align the first original point with the second original point to obtain a first target point. The first target point includes three-dimensional coordinates and a three-dimensional posture (yaw, roll, pitch). Then, the first target point is expressed as (x, y, z, roll, pitch, yaw).

[0065] Among them, the point cloud registration algorithm refers to inputting two point clouds Ps (source, such as the first original point) and Pt (target, such as the second original point), and outputting a transformation T (i.e., rotation R and translation t) so that the degree of overlap between T (Ps) and Pt is as high as possible.

[0066] Point cloud registration requires knowing the matching relationship between two sets of point clouds. For visual three-dimensional points, it can be obtained through visual feature matching, and for radar point clouds, it can be obtained through nearest neighbor matching.

[0067] After knowing the matching relationship of the point clouds, the transformation matrix is ​​calculated through two steps: coarse registration and fine registration. Coarse registration refers to a relatively rough registration when the transformation between the two point clouds is completely unknown. The main purpose is to provide a better initial value for the fine registration. The fine registration criterion is to give an initial transformation and further optimize it to obtain a more accurate transformation. Among them, coarse registration has an analytical solution, and fine registration further optimizes the result through nonlinear optimization.

[0068] Step 105: align the first feature point with the second feature point to obtain a second target point.

[0069] In this embodiment, the first feature point and the second feature point can be registered using a point cloud registration algorithm such as ICP and NDT to obtain a second target point. The second target point includes three-dimensional coordinates and a three-dimensional posture (yaw, roll, pitch). Then, the second target point is expressed as result2 (x, y, z, roll, pitch, yaw).

[0070] Furthermore, in most point cloud registration algorithms, the existence of abnormal related points cannot be removed, which affects the accuracy of pose solution. Therefore, this embodiment can remove abnormal related points based on intensity changes.

[0071] Specifically, the coding value of the first feature point includes an intensity change value, and the coding value of the second feature point includes an intensity change value. Then, the difference between the coding value of the first feature point (i.e., the intensity change value) and the coding value of the second feature point (i.e., the intensity change value) can be calculated as the change difference value, and the change difference value is compared with a preset difference threshold (such as 30).

[0072] If the change difference value is greater than the preset difference threshold, it means that the intensity change is quite different and the second target point is an abnormal related point. In this case, the second target point is removed to improve the positioning accuracy.

[0073] Step 106: Generate a positioning point for the environment according to the first target point and the second target point.

[0074] In practical applications, the first target point represents the alignment of the point cloud data in terms of position and posture (coordinates and attitude), and the second target point represents the alignment of the point cloud data in terms of changes in laser emission intensity. With the assistance of the second target point, a positioning point can be generated for the environment, that is, a point that can be used for positioning, to provide a reference for decision-making for subsequent navigation and other business operations.

[0075] In one embodiment of the present invention, step 106 may include the following steps:

[0076] Step 1061: Calculate a first matching value between the first original point and the second original point during registration.

[0077] In this embodiment, during the process of registering the first original point with the second original point, a first matching value between the first original point and the second original point may be calculated to represent the matching degree between the first original point and the second original point.

[0078] Exemplarily, for each first original point, the minimum second distance value between the first original point and any second original point is calculated; the negative of the ratio between the square of the second distance value and the preset first alignment coefficient is taken as the first reference value; and the first sub-score is generated with a natural number as the base and the first reference value as the exponent.

[0079] Then, the first sub-fraction is expressed as:

[0080]

[0081] Wherein, score is the first sub-score, d is the minimum second distance value between the first original point and any second original point, δ is the first registration coefficient, and the first registration coefficient is a positive number, such as 0.1.

[0082] An average value of the first sub-scores (ie, the sum of the first sub-scores of all first target points divided by the total number of first target points) is calculated as a first matching value between the first original point and the second original point during registration.

[0083] Step 1062: Calculate a second matching value between the first feature point and the second feature point during registration.

[0084] In this embodiment, during the process of registering the first feature point with the second feature point, a second matching value between the first feature point and the second feature point may be calculated to represent the matching degree between the first feature point and the second feature point.

[0085] Exemplarily, for each first feature point, the minimum third distance value between the first feature point and any second feature point is calculated; the negative of the ratio between the square of the third distance value and the preset second alignment coefficient is taken as the second reference value; and the second sub-score is generated with a natural number as the base and the second reference value as the exponent.

[0086] Then, the second sub-fraction is expressed as:

[0087]

[0088] Wherein, score is the second sub-score, d is the minimum second distance value between the first feature point and any second feature point, δ is the second registration coefficient, and the second registration coefficient is a positive number, such as 0.1.

[0089] An average value of the second sub-scores (ie, the sum of the first sub-scores of all the first feature points divided by the total number of the first feature points) is calculated as a second matching value between the first feature points and the second feature points during registration.

[0090] Step 1063: Use the first matching value and the second matching value to perform adaptive complementary filtering on the first target point and the second target point to obtain a positioning point of the environment.

[0091] In this embodiment, the laser point cloud in the environment and its changes in reflection intensity are used as the background, which is used as a dynamic constraint item to alleviate the problem of sparse laser point cloud in the background, so that the first target point and the second target point are adaptively complementary filtered using the first matching value and the second matching value to obtain high-precision positioning points in the environment, which can improve the robustness and smoothness of positioning, and slow down or avoid abnormalities such as positioning posture jitter and jump.

[0092] Exemplarily, the product between the first matching value and the first target point is calculated to obtain the first weighted adjustment point; the product between the second matching value and the second target point is calculated to obtain the second weighted adjustment point; the first weighted adjustment point is added to the second weighted adjustment point to obtain the third weighted adjustment point; the first matching value is added to the second matching value to obtain the filter coefficient; the ratio between the third weighted adjustment point and the filter coefficient is calculated to obtain the positioning point of the environment.

[0093] In this example, the anchor points are represented as follows:

[0094]

[0095] Among them, result is the positioning point, result1 is the first target point, result2 is the second target point, points_score is the first matching value, and feature_score is the second matching value.

[0096] In this embodiment, the laser radar is driven to scan the first original point in the environment; the feature characterizing the intensity change is selected in the first original point as the first feature point; the first original point is marked in the electronic map corresponding to the environment, the electronic map has a second original point, and the second original point has a second feature point characterizing the intensity change; the first original point is aligned with the second original point to obtain the first target point; the first feature point is aligned with the second feature point to obtain the second target point; and the positioning point is generated for the environment according to the first target point and the second target point. This embodiment supplements the reflective sticker, and usually there are more intensity change features in the environment to assist in positioning, which can make full use of the original information in the environment to generate dense positioning features, and the positioning features are stable and reliable, thereby improving the accuracy of positioning.

[0097] Embodiment 2

[0098] Figure 2 This is a schematic diagram of the structure of a laser positioning device provided in Embodiment 2 of the present invention. Figure 2 As shown, the device comprises:

[0099] The laser scanning module 201 is used to drive the laser radar to scan a first original point in the environment;

[0100] An intensity change feature screening module 202 is used to screen features representing intensity changes from the first original points as first feature points;

[0101] A point cloud marking module 203, used for marking the first original point in an electronic map corresponding to the environment, wherein the electronic map has a second original point, and the second original point has a second characteristic point representing an intensity change;

[0102] An original point registration module 204, configured to register the first original point with the second original point to obtain a first target point;

[0103] A feature point registration module 205, configured to register the first feature point with the second feature point to obtain a second target point;

[0104] The positioning point generating module 206 is configured to generate a positioning point for the environment according to the first target point and the second target point.

[0105] In one embodiment of the present invention, the intensity change feature screening module 202 includes:

[0106] A reference point traversal module, configured to traverse a first reference point and a second reference point from the first original point, wherein the first reference point and the second reference point are adjacent in scanning time sequence, and the first reference point and the second reference point are close in geographical location;

[0107] an intensity change value calculation module, used to calculate a difference between an intensity value of the first reference point and an intensity value of the second reference point as an intensity change value;

[0108] The feature point determination module is used to determine that the first reference point is a first feature point representing the intensity change if the intensity change value is greater than a preset change threshold, and set the intensity change value as a coding value of the first feature point.

[0109] In one embodiment of the present invention, the reference point traversal module includes:

[0110] A scanning distance calculation module, used for calculating a first distance value between the current first original point and the previous first original point in terms of geographical location in a scanning sequence;

[0111] An angular resolution query module, used to query the angular resolution of the laser radar in the horizontal direction;

[0112] A neighbor threshold calculation module, configured to add a preset distance coefficient to the product of the first distance value and the angular resolution to obtain a neighbor threshold;

[0113] A reference point determination module is used to determine that if the first distance value is less than the neighbor threshold, the current first original point and the previous first original point are geographically neighboring, the current first original point is the first reference point, and the previous first original point is the second reference point.

[0114] In one embodiment of the present invention, it also includes:

[0115] a change difference value calculation module, used to calculate the difference between the encoding value of the first feature point and the encoding value of the second feature point as the change difference value;

[0116] The target point elimination module is used to eliminate the second target point if the change difference value is greater than a preset difference threshold.

[0117] In one embodiment of the present invention, the positioning point generation module 206 includes:

[0118] A first matching value calculation module, used for calculating a first matching value between the first original point and the second original point during registration;

[0119] A second matching value calculation module, used for calculating a second matching value between the first feature point and the second feature point during registration;

[0120] The adaptive complementary filtering module is used to perform adaptive complementary filtering processing on the first target point and the second target point using the first matching value and the second matching value to obtain a positioning point of the environment.

[0121] In one embodiment of the present invention, the first matching value calculation module is further used for:

[0122] For each of the first original points, calculating the minimum second distance value between the first original point and any of the second original points;

[0123] Taking a negative value of a ratio between the square of the second distance value and a preset first registration coefficient as a first reference value;

[0124] Generate a first sub-fraction by taking a natural number as the base and the first reference value as the exponent;

[0125] An average value of the first sub-scores is calculated as a first matching value between the first original point and the second original point during registration.

[0126] In one embodiment of the present invention, the second matching value calculation module is further used for:

[0127] For each of the first feature points, calculating a minimum third distance value between the first feature point and any of the second feature points;

[0128] Taking a negative value of a ratio between the square of the third distance value and a preset second registration coefficient as a second reference value;

[0129] Generate a second sub-fraction by taking a natural number as the base and the second reference value as the exponent;

[0130] An average value of the second sub-scores is calculated as a second matching value between the first feature point and the second feature point during registration.

[0131] In one embodiment of the present invention, the adaptive complementary filtering module is further used for:

[0132] Calculating the product of the first matching value and the first target point to obtain a first weight adjustment point;

[0133] Calculating the product of the second matching value and the second target point to obtain a second weight adjustment point;

[0134] Adding the first weighting point to the second weighting point to obtain a third weighting point;

[0135] Adding the first matching value to the second matching value to obtain a filter coefficient;

[0136] The ratio between the third weight adjustment point and the filter coefficient is calculated to obtain the positioning point of the environment.

[0137] The laser positioning device provided in the embodiment of the present invention can execute the laser positioning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the laser positioning method.

[0138] Embodiment 3

[0139] Figure 3 A schematic diagram of a robot 10 that can be used to implement an embodiment of the present invention is shown. The robot is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The robot can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0140] like Figure 3As shown, the robot 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the robot 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0141] A number of components in the robot 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the robot 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0142] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the laser positioning method.

[0143] In some embodiments, the laser positioning method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the robot 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the laser positioning method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the laser positioning method in any other suitable manner (e.g., by means of firmware).

[0144] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0146] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on a robot having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the robot. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0148] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0149] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0150] Embodiment 4

[0151] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the laser positioning method provided by any embodiment of the present invention.

[0152] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0153] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A laser positioning method, It is characterized in that include: Drive the laser radar to scan the first original point in the environment; Selecting a feature representing the intensity change from the first original point as a first feature point; Marking the first original point in an electronic map corresponding to the environment, wherein the electronic map has a second original point, and the second original point has a second characteristic point representing intensity change; Registering the first original point with the second original point to obtain a first target point; Aligning the first feature point with the second feature point to obtain a second target point; Generating a positioning point for the environment according to the first target point and the second target point; Wherein, generating a positioning point for the environment according to the first target point and the second target point includes: Calculating a first matching value between the first original point and the second original point during registration; Calculating a second matching value between the first feature point and the second feature point during registration; The first matching value and the second matching value are used to perform adaptive complementary filtering on the first target point and the second target point to obtain a positioning point of the environment.

2. The method according to claim 1, It is characterized in that The step of selecting a feature representing intensity change from the first original point as a first feature point includes: Traversing a first reference point and a second reference point from the first original point, the first reference point and the second reference point are adjacent in scanning time sequence, and the first reference point and the second reference point are close in geographical location; Calculating a difference between the intensity value of the first reference point and the intensity value of the second reference point as an intensity change value; If the intensity change value is greater than a preset change threshold, the first reference point is determined to be a first feature point representing the intensity change, and the intensity change value is set as the encoding value of the first feature point.

3. The method according to claim 2, It is characterized in that The traversing the first reference point and the second reference point from the first original point includes: In the scanning sequence, calculating a first distance value between the current first original point and the previous first original point in terms of geographical location; Query the angular resolution of the laser radar in the horizontal direction; Add a preset distance coefficient to the product of the first distance value and the angle resolution to obtain a neighbor threshold; If the first distance value is less than the neighbor threshold, the current first original point and the previous first original point are geographically adjacent, the current first original point is the first reference point, and the previous first original point is the second reference point.

4. The method according to claim 2, It is characterized in that After registering the first feature point with the second feature point to obtain a second target point, the method further includes: Calculate the difference between the encoding value of the first feature point and the encoding value of the second feature point as a change difference value; If the change difference value is greater than a preset difference threshold, the second target point is eliminated.

5. The method according to claim 1, It is characterized in that The calculating a first matching value between the first original point and the second original point during registration includes: For each of the first original points, calculating the minimum second distance value between the first original point and any of the second original points; Taking a negative value of a ratio between the square of the second distance value and a preset first registration coefficient as a first reference value; Generate a first sub-fraction by taking a natural number as the base and the first reference value as the exponent; Calculating an average value of the first sub-scores as a first matching value between the first original point and the second original point during registration; The calculating a second matching value between the first feature point and the second feature point during registration includes: For each of the first feature points, calculating a minimum third distance value between the first feature point and any of the second feature points; Taking a negative value of a ratio between the square of the third distance value and a preset second registration coefficient as a second reference value; Generate a second sub-fraction by taking a natural number as the base and the second reference value as the exponent; An average value of the second sub-scores is calculated as a second matching value between the first feature point and the second feature point during registration.

6. The method according to claim 1, It is characterized in that The using the first matching value and the second matching value to perform adaptive complementary filtering on the first target point and the second target point to obtain the positioning point of the environment includes: Calculating the product of the first matching value and the first target point to obtain a first weight adjustment point; Calculating the product of the second matching value and the second target point to obtain a second weight adjustment point; Adding the first weighting point to the second weighting point to obtain a third weighting point; Adding the first matching value to the second matching value to obtain a filter coefficient; The ratio between the third weight adjustment point and the filter coefficient is calculated to obtain the positioning point of the environment.

7. A laser positioning device, It is characterized in that include: A laser scanning module, used to drive the laser radar to scan a first original point in the environment; An intensity change feature screening module, used to screen features representing intensity changes from the first original points as first feature points; A point cloud marking module, used for marking the first original point in an electronic map corresponding to the environment, wherein the electronic map has a second original point, and the second original point has a second characteristic point representing an intensity change; An original point registration module, used for registering the first original point with the second original point to obtain a first target point; A feature point registration module, used for registering the first feature point with the second feature point to obtain a second target point; A positioning point generating module, configured to generate a positioning point for the environment according to the first target point and the second target point; Wherein, the positioning point generation module includes: A first matching value calculation module, used for calculating a first matching value between the first original point and the second original point during registration; A second matching value calculation module, used for calculating a second matching value between the first feature point and the second feature point during registration; The adaptive complementary filtering module is used to perform adaptive complementary filtering processing on the first target point and the second target point using the first matching value and the second matching value to obtain a positioning point of the environment.

8. A robot, It is characterized in that The robot comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the laser positioning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the laser positioning method according to any one of claims 1 to 6 when executed.