WO2019196478A1

WO2019196478A1 - Robot positioning

Info

Publication number: WO2019196478A1
Application number: PCT/CN2018/121180
Authority: WO
Inventors: 郝立良; 申浩; 程保山
Original assignee: 北京三快在线科技有限公司
Priority date: 2018-04-13
Filing date: 2018-12-14
Publication date: 2019-10-17
Also published as: CN110377015A; CN110377015B

Abstract

A robot positioning method and device. The robot positioning method comprises: acquiring an image by means of an image acquisition unit on a robot, and extracting a feature point from the image (S1); determining, in the pre-stored feature point library, a target sample feature point that matches the feature point (S2); and determining the coordinate of the image acquisition unit in a preset coordinate system according to the coordinate of the pre-stored target sample feature point in the preset coordinate system and the coordinate mapping relationship between the target sample feature point and the image acquisition unit in the preset coordinate system (S3).

Description

Robot positioning

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 2018103308, the entire disclosure of which is incorporated herein in in.

Technical field

The present application relates to the field of navigation technology, and in particular to robot positioning.

Background technique

At present, the method of robot navigation by laser can generate a two-dimensional map by the obstacle of the area where the laser scanning robot is located, and the robot can determine the driving route based on the position of the obstacle in the two-dimensional map, thereby realizing navigation.

However, while the current robot is capable of determining the surrounding obstacles by laser scanning at the time of starting, it is not possible to determine its position in the coordinate system. Therefore, it is necessary to manually indicate the position of the robot in the coordinate system when the robot is started, so that the robot can perform path planning in the two-dimensional map according to the position to realize navigation.

Summary of the invention

In view of this, embodiments of the present invention provide a robot positioning method, a robot positioning device, and a computer readable storage medium, and a robot.

According to a first aspect of the embodiments of the present invention, a robot positioning method includes: acquiring an image by an image collector on the robot, extracting feature points from the image; and determining and storing in a pre-stored feature point library. a target sample feature point matched by the feature point; a coordinate according to the pre-stored target sample feature point in a preset coordinate system, and the target sample feature point and the image collector at the preset coordinate The coordinate mapping relationship in the system determines the coordinates of the image collector in the preset coordinate system.

According to a second aspect of the embodiments of the present invention, a robot positioning apparatus includes: a feature point extraction module, configured to extract a feature point from an image collected by an image collector on the robot; and a feature point matching module, And determining, by using a pre-stored feature point library, a target sample feature point that matches the feature point; and a first coordinate determining module, configured to use, according to the pre-stored coordinate of the target sample feature point in a preset coordinate system And a coordinate mapping relationship between the target sample feature point and the image collector in the preset coordinate system, and determining coordinates of the image collector in the preset coordinate system.

According to a third aspect of the embodiments of the present invention, there is provided a computer readable storage medium having stored thereon a computer program that, when executed by a processor, performs the above-described robot positioning method.

According to a fourth aspect of the embodiments of the present invention, there is provided a robot comprising a laser sensor and an image collector, further comprising a processor, wherein the processor is configured to perform the robot positioning method described above.

It can be seen from the above embodiment that, since the image collector is disposed on the robot, after determining the coordinates of the image collector in the preset coordinate system, the coordinates of the robot in the preset coordinate system can be determined, and The coordinates are calibrated so that operations can be performed based on the coordinates so that the navigation path can be planned in the navigation map starting from the coordinates of the image collector in the preset coordinate system. Therefore, it is not necessary to manually instruct the coordinates of the robot to realize completely autonomous navigation of the robot.

The above general description and the following detailed description are intended to be illustrative and not restrictive.

DRAWINGS

The accompanying drawings, which are incorporated in the specification of FIG

1 is a schematic flow chart of a robot positioning method according to an embodiment of the present invention.

2 is a schematic flow chart of another robot positioning method according to an embodiment of the present invention.

3 is a schematic flow chart showing determining a positional relationship and a posture relationship of a laser sensor and an image collector, according to an embodiment of the present invention.

FIG. 4 is a diagram showing depth information, position information, and angle information of an image collector when acquiring a sample image according to an embodiment of the present invention, determining that a sample feature point and an image collector are preset. A schematic flow chart of the coordinate mapping relationship in the coordinate system.

FIG. 5 is a schematic flow chart of extracting feature points from an image by acquiring an image by an image collector, according to an embodiment of the invention.

FIG. 6 is a schematic flow chart of still another robot positioning method according to an embodiment of the present invention.

FIG. 7 is a schematic flow chart showing navigation path planning in a navigation map matching a preset coordinate system according to coordinates of the image collector in a preset coordinate system according to an embodiment of the present invention.

FIG. 8 is a schematic diagram showing a hardware configuration of a device in which a robot positioning device is located, according to an embodiment of the present invention.

9 is a schematic block diagram of a robotic positioning device, in accordance with an embodiment of the present invention.

Figure 10 is a schematic block diagram of another robotic positioning device shown in accordance with an embodiment of the present invention.

11 is a schematic block diagram of still another robotic positioning device shown in accordance with an embodiment of the present invention.

12 is a schematic block diagram of a path planning module, shown in accordance with an embodiment of the present invention.

detailed description

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. The following description refers to the same or similar elements in the different figures unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with aspects of the present application as detailed in the appended claims.

The terminology used in the present application is for the purpose of describing particular embodiments, and is not intended to be limiting. The singular forms "a", "the" and "the" It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used to describe various information in this application, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information may also be referred to as the second information without departing from the scope of the present application. Similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "when" or "in response to a determination."

1 is a schematic flow chart of a robot positioning method according to an embodiment of the present invention. The method shown in this embodiment can be applied to a robot, which can include a laser sensor and an image collector.

In one embodiment, the image capture device can be a monocular camera or a binocular camera. The image acquired by the image collector can be a depth image. Moreover, the image collector can be rotated, for example, by 360° in a preset plane to capture images in different directions.

In one embodiment, the laser sensor can emit and receive laser light. Also, the laser sensor can be rotated, for example, by rotating 360° in a predetermined plane to emit laser light in a direction in which it is directed.

In one embodiment, the laser sensor and image collector may be in the same plane or in different planes.

As shown in FIG. 1, the robot positioning method may include the following steps:

In step S1, an image is acquired by the image collector, and feature points are extracted from the image.

In one embodiment, the image acquired by the image collector may be an image or multiple images. In the case of collecting multiple images, the number of sheets specifically collected can be set as needed. Moreover, for different images, the number of feature points extracted from the image may be the same or different, and the number of specifically extracted feature points may be set as needed. For example, for one image, the number of extracted feature points may be greater than or equal to six.

Step S2: determining a target sample feature point that matches the feature point in a pre-stored feature point library.

In an embodiment, the sample feature points may be pre-stored, for example, a feature point library composed of sample feature points is generated in advance, and the feature point library stores coordinates of each sample feature point in a preset coordinate system.

The coordinate mapping relationship between the sample feature points and the image collector in the preset coordinate system may also be stored in the feature point library (for example, including a positional relationship and an attitude relationship, which may be represented by a matrix). Of course, the coordinate mapping relationship can also be stored in other storage spaces than the feature point library.

The description information of the sample feature points may also be stored in the feature point library. For example, if the granularity of the sample feature points is a pixel in the image, the description information may include gray values of several (eg, 8) pixels around the pixel as the sample feature point. The description information may also include information such as the category of the sample feature points, the position of the sample feature points in the image, and the like.

For the feature point, the description information of the feature point may be determined, and then the sample feature point whose description information matches the description information of the feature point may be queried in the pre-stored feature point library, that is, the target sample feature point.

Step S3: Determine coordinates of the image collector in a preset coordinate system according to a coordinate mapping relationship between the target sample feature point and the image collector in a preset coordinate system.

In an embodiment, since the coordinate mapping relationship between the target sample feature point and the image collector in the preset coordinate system and the coordinates of the target sample feature point in the preset coordinate system may be stored in the feature point library, The coordinates of the target sample feature points in the preset coordinate system are converted according to the coordinate mapping relationship, thereby deriving the coordinates of the image collector in the preset coordinate system.

Since the image collector is disposed on the robot, after determining the coordinates of the image collector in the preset coordinate system, the coordinates of the robot in the preset coordinate system can be determined. Therefore, it is not necessary to manually instruct the coordinates of the robot, and it is convenient to realize the completely autonomous navigation of the robot.

2 is a schematic flow chart of another robot positioning method according to an embodiment of the present invention. As shown in FIG. 2, the robot positioning method may include the following steps:

Step S4: Before acquiring the sample image by the image collector, determining a positional relationship and a posture relationship of the laser sensor with respect to the image collector.

In one embodiment, the positional relationship may refer to an offset of the image collector relative to the laser sensor along the x-axis in the predetermined coordinate system, an offset along the y-axis, and an offset along the z-axis. The attitude relationship may refer to a rotation angle and an elevation angle of a direction in which the image collector acquires an image with respect to a laser sensor emission direction.

Step S5, determining a first coordinate of the laser sensor in a preset coordinate system.

In one embodiment, the first coordinate of the laser sensor in a preset coordinate system can be determined by SLAM (Simultaneous Localization And Mapping).

In one embodiment, the coordinates determined by the SLAM may be two-dimensional coordinates, and if the preset coordinate system is three-dimensional coordinates, the two-dimensional coordinates may be converted into three-dimensional coordinates, wherein the z-axis coordinates are zero.

Step S6: Convert the first coordinate according to the position relationship and the attitude relationship to obtain a second coordinate of the image collector in a preset coordinate system.

Step S7, collecting a sample image by the image collector, and extracting a plurality of sample feature points from the sample image.

In one embodiment, multiple image images may be acquired by the image collector, and one or more sample feature points may be separately extracted for each sample image, and the number of sample feature points extracted for each sample image may be the same or different. The plurality of sample feature points thus acquired are stored in the feature point library.

Step S8: Determine the coordinate mapping relationship according to depth information, position information of the sample feature point in the sample image, and angle information when the image collector collects the sample image.

In one embodiment, the image acquired by the image collector may be a depth image. For example, the feature point has a granularity of pixels, and the depth image contains depth information for each pixel. Based on the depth information, the distance from the pixel to the image collector, that is, the distance from the feature point to the image collector, can be determined.

Further, according to the distance and the position information of the sample feature point in the sample image (for example, the pixel of the sample feature point corresponding to the first few rows in the sample image), and the angle information when the image collector collects the sample image, Determining the coordinate mapping relationship.

For example, the sample feature point is 100 pixels directly above the corresponding center point in the image collected by the image collector, wherein the length of each pixel may be preset, for example, L, then the length of 100 pixels is 100L. Since the sample feature point to the center of the image, the center of the image to the image collector, and the image collector to the sample feature point can form a right triangle, the distance D from the image collector to the sample feature point can be a hypotenuse, at 100L. At the corner, the length of the other right-angled edge is obtained according to the Pythagorean theorem, that is, the distance d from the center of the image to the image collector.

If the angle of rotation of the sample image when the image collector collects the sample image of the sample feature point is α, the coordinate mapping relationship may be: the sample feature point is located in the direction of the rotation angle α of the image collector, and to the image collector The distance is the plane of d, and is located 100L away from the center directly above the center of the plane. This content can be represented by a matrix.

Step S9: Determine, according to the second coordinate and the coordinate mapping relationship, a third coordinate of the sample feature point in a preset coordinate system.

In an embodiment, after the coordinate mapping relationship is obtained, the second coordinate may be further converted according to the coordinate mapping relationship to determine a third coordinate of the sample feature point. For example, the coordinate mapping relationship is represented by a matrix, and then the third coordinate can be obtained by multiplying the second coordinate with the matrix.

Step S10, storing the third coordinate and the coordinate mapping relationship.

In an embodiment, after obtaining the coordinates of the sample feature points in the preset coordinate system, a feature point library may be generated, and the feature point library may include coordinates of the sample feature points in the preset coordinate system for each sample feature point. And the coordinate mapping relationship between the sample feature points and the image collector in the preset coordinate system (for example, can be represented by a matrix).

It should be noted that the foregoing steps S4 to S10 may be pre-executed before the robot navigation, and the coordinate mapping relationship between the sample feature points and the image collector in the preset coordinate system is pre-stored through the feature point library, so as to facilitate subsequent determination of the image collector. The coordinates in the preset coordinate system, for example, when performing steps S1 to S3, the target sample feature points matching the feature points extracted from the image may be determined in the feature point library, and the pre-stored coordinate mapping relationship is used in advance. The stored target sample feature points are converted in the coordinates in the preset coordinate system, thereby obtaining the coordinates of the image collector in the preset coordinate system.

In addition, since the laser light emitted by the laser sensor is easily disturbed by the environment (for example, fog, helium), the coordinate accuracy of the feature point in the preset coordinate system is determined to be low only based on the result of the laser sensor scan. The image acquired by the image collector is relatively less susceptible to environmental interference, that is, the coordinate mapping relationship between the feature points in the image and the image collector in the preset coordinate system is relatively accurate, and the feature point library of the embodiment is Combined with the results of the laser sensor scan and the images acquired by the image collector, the coordinates of the feature points can be determined relatively accurately by matching in the feature point library.

3 is a schematic flow chart showing determining a positional relationship and a posture relationship of the laser sensor with respect to the image collector, according to an embodiment of the present invention. As shown in FIG. 3, determining the positional relationship and the attitude relationship of the laser sensor with respect to the image collector may include: step S401, determining a positional relationship of the laser sensor with respect to the image collector according to a nonlinear optimization algorithm. And attitude relationship.

In one embodiment, the positional relationship and attitude relationship of the laser sensor relative to the image collector can be determined by manual measurement or by a nonlinear optimization algorithm.

For example, the nonlinear optimization algorithm adopted is a least square method. Since the position of the laser sensor and the image collector on the robot is relatively fixed, the positional relationship and the attitude relationship of the laser sensor with respect to the image collector are relatively fixed.

For example, a plurality of known points may be set in the space, and for a known point, a laser sensor may be used to emit laser light to the known point and receive the reflected laser light, thereby determining the positional relationship of the known point with respect to the laser sensor and The attitude relationship is represented, for example, by matrix A, and the spatial coordinates of the laser sensor are represented as matrix P). Correspondingly, the image of the point can be acquired by the image collector, thereby determining the positional relationship and the attitude relationship of the known point with respect to the image collector (for example, represented by a matrix B, and the spatial coordinates of the image collector are represented as a matrix Q). . In this case, P·A=Q·B can be obtained, so that the positional relationship and the attitude relationship of the laser sensor with respect to the image collector can be represented by the transformation matrix C of the matrix A to the matrix B, for example, P=Q·C. .

Further, for a plurality of known points, a plurality of sets of matrices P, Q, and C can be separately measured, and a plurality of sets of matrices P, Q, and C can be calculated by using a least squares method to obtain a relatively accurate matrix C to represent the laser sensor relative to image acquisition. The positional relationship and attitude relationship of the device. Since the nonlinear optimization algorithm can be executed by software, the positional relationship and the attitude relationship of the laser sensor with respect to the image collector can be determined more accurately with respect to manual measurement.

4 is a diagram showing depth information, position information of sample feature points in a sample image, and angle information when the image collector acquires the sample image, and determining the coordinate mapping relationship according to an embodiment of the invention. Schematic flow chart. As shown in FIG. 4, determining the coordinate mapping relationship according to the depth information of the sample feature points in the sample image, the position information, and the angle information when the image collector acquires the sample image includes:

Step S801, determining the coordinate mapping relationship according to the depth information, the position information, the angle information, and the imaging model of the image collector of the sample feature point in the sample image.

In one embodiment, since the imaging model of the image collector is different, for example, the image collector is a pinhole camera, and the imaging model is a pinhole model, for example, the image collector is a fisheye camera, then the imaging model is a fisheye model. The coordinate mapping relationship in different imaging models is different from the corresponding relationship between the depth information, the position information, and the angle information of the sample feature points in the sample image. Therefore, when determining the coordinates of the feature points, it is advantageous to determine the coordinates of the feature points more accurately by considering the imaging model of the image collector.

In one embodiment, taking the pinhole model as an example, the model can be represented by the following relationship:

s·m'=A[R|t]·M';

Where m' is the uv coordinate of the feature point, A is the camera internal parameter, [R|t] is the relationship between the camera and the preset coordinate system (such as the world coordinate system), and M' is the feature point and the preset coordinate system (for example, world coordinates) Relationship), s is the z coordinate of the object in the camera coordinate system. The camera internal reference mentioned here refers to the parameter determined only by the camera itself, that is, once a value is calculated for a certain camera, it is not necessary to perform calculation again.

FIG. 5 is a schematic flow diagram of extracting an image from the image by acquiring an image by the image collector, according to an embodiment of the invention. As shown in FIG. 5, the image is collected by the image collector, and extracting feature points from the image includes: step S101, when the robot is started, an image is collected by the image collector, and the image is extracted from the image. Feature points.

In one embodiment, step S1 may be performed when the robot is started, that is, an image is acquired by the image collector when the robot is started, and feature points are extracted from the image. According to this, it can be ensured that as long as the robot is started, the coordinates in the preset coordinate system can be determined, thereby completing the autonomous navigation.

FIG. 6 is a schematic flow chart of still another robot positioning method according to an embodiment of the present invention. As shown in FIG. 6, on the basis of the embodiment shown in FIG. 1, the robot positioning method may further include:

Step S11, generating a navigation map by scanning the area where the robot is located by the laser sensor;

The navigation map generated by the laser sensor scanning the area where the robot is located may be a two-dimensional map. The laser sensor can scan an obstacle in a range of a predetermined distance from the area where the robot is located to the robot, and the laser reflected by the obstacle can determine the position of the obstacle in the area, and then generate a navigation map according to the position of the obstacle. A navigation map is generated, for example, by SLAM.

Step S12, matching the navigation map and the preset coordinate system.

In one embodiment, if the navigation map is a two-dimensional map and the preset coordinate system is a three-dimensional coordinate system, then only two dimensions in the three-dimensional coordinate system may be matched to the navigation map. For example, a two-dimensional map is a map parallel to a horizontal plane. In the three-dimensional coordinate system, the x-axis and the y-axis are axes parallel to the horizontal plane, and then the x-axis and the y-axis in the three-dimensional coordinate system can be matched to the navigation map, thereby navigating the map. The x-axis coordinate and the y-axis coordinate can be calibrated.

Step S13: Perform navigation path planning on the navigation map matching the preset coordinate system according to the coordinates of the image collector in the preset coordinate system.

In one embodiment, since the image collector is disposed on the robot, after determining the coordinates of the image collector in the preset coordinate system, the coordinates of the robot in the preset coordinate system can be determined, and the calibration is determined in the navigation map. The coordinates can therefore be calculated according to the coordinates so that the navigation path can be planned in the navigation map starting from the coordinates of the image collector in the preset coordinate system. Therefore, it is not necessary to manually instruct the coordinates of the robot to realize completely autonomous navigation of the robot.

Among them, the navigation path planning can be performed according to the amcl (adaptive Monte Carlo Localization) positioning algorithm, costmap (cost map) and path planning algorithm.

FIG. 7 is a schematic flow chart showing navigation path planning in a navigation map matching a preset coordinate system according to coordinates of the image collector in a preset coordinate system according to an embodiment of the present invention. As shown in FIG. 7, the navigation path planning in the navigation map matching the preset coordinate system according to the coordinates of the image collector in the preset coordinate system includes: Step S1301, according to the image collector Positioning on the robot determines a projection of the contour of the robot in the preset coordinate system; step S1302, according to the projection, performs navigation path planning in a navigation map matching the preset coordinate system.

In one embodiment, since the robot has a certain volume, in order to avoid the problem that the robot is blocked or unbalanced when the obstacle is collided during the movement, the contour of the robot can be determined according to the position of the image collector on the robot at the preset coordinates. Projection in the system, and according to the projection in the navigation map matching the preset coordinate system for navigation path planning, to ensure that the robot does not touch the obstacles in the path, to ensure that the robot moves smoothly and smoothly. And according to the projection of the robot, the orientation of the robot in the preset coordinate system can also be determined, so that the navigation path can be easily planned.

Corresponding to the aforementioned embodiment of the robot positioning method, the present application also provides an embodiment of the robot positioning device.

The embodiment of the robot positioning device of the present application can be applied to a device such as a robot. The device embodiment may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking the software implementation as an example, as a logical device, the processor of the device in which it is located reads the corresponding computer program instructions in the non-volatile memory into the memory. From the hardware level, as shown in FIG. 8, a hardware structure diagram of the device where the robot positioning device is located, except for the processor 801, the memory 802, the network interface 803, and the non-volatile memory shown in FIG. The device in which the device is located in the embodiment is usually other hardware according to the actual function of the device, and details are not described herein.

9 is a schematic block diagram of a robotic positioning device, in accordance with an embodiment of the present invention. The robot includes a laser sensor and an image collector, as shown in FIG. 9, the robot positioning device includes:

a feature point extraction module 1 for acquiring an image by the image collector, and extracting feature points from the image;

a feature point matching module 2, configured to determine, in a pre-stored feature point library, a target sample feature point that matches the feature point;

a first coordinate determining module 3, configured to: according to pre-stored coordinates of the target sample feature point in a preset coordinate system, and coordinate mapping between the target sample feature point and the image collector in a preset coordinate system And determining coordinates of the image collector in a preset coordinate system.

Figure 10 is a schematic block diagram of another robotic positioning device shown in accordance with an embodiment of the present invention. As shown in FIG. 10, on the basis of the embodiment shown in FIG. 9, the robot positioning device further includes:

a relationship determining module 4, configured to determine a positional relationship and a posture relationship of the laser sensor with respect to the image collector;

a second coordinate determining module 5, configured to determine a first coordinate of the laser sensor in a preset coordinate system;

a coordinate conversion module 6 configured to convert the first coordinate according to the positional relationship and the attitude relationship to obtain a second coordinate of the image collector in a preset coordinate system;

The feature point extraction module 1 is further configured to collect a sample image by using the image collector, and extract a plurality of sample feature points from the sample image;

The mapping determination module 7 is configured to determine the coordinate mapping relationship according to the depth information, the position information of the sample feature point in the sample image, and the angle information when the image collector acquires the sample image;

The third coordinate determining module 8 is configured to determine, according to the second coordinate and the coordinate mapping relationship, a third coordinate of the sample feature point in a preset coordinate system;

The storage module 9 is configured to store a third coordinate of the sample feature point in a preset coordinate system and a coordinate mapping relationship between the sample feature point and the image collector in a preset coordinate system.

In one embodiment, the relationship determination module 4 is configured to determine a positional relationship and an attitude relationship of the laser sensor relative to the image collector according to a nonlinear optimization algorithm.

In an embodiment, the mapping determining module 7 is configured to determine, according to the depth information, the position information, the angle information, and the imaging model of the image collector of the sample feature point in the sample image. Coordinate mapping relationship.

In one embodiment, the feature point extraction module 1 is configured to acquire an image from the image by the image collector when the robot is started, and extract feature points from the image.

11 is a schematic block diagram of still another robotic positioning device shown in accordance with an embodiment of the present invention. As shown in FIG. 11, on the basis of the embodiment shown in FIG. 9, the robot positioning device further includes:

a map generating module 10, configured to generate a navigation map by scanning, by the laser sensor, an area where the robot is located;

a map matching module 11 configured to match the navigation map and the preset coordinate system;

The path planning module 12 is configured to perform navigation path planning in a navigation map matching the preset coordinate system according to coordinates of the image collector in a preset coordinate system.

12 is a schematic block diagram of a path planning module, shown in accordance with an embodiment of the present invention. As shown in FIG. 10, on the basis of the embodiment shown in FIG. 11, the path planning module 12 includes:

a projection determining sub-module 1201, configured to determine a projection of the contour of the robot in the preset coordinate system according to a position of the image collector on the robot;

The path planning sub-module 1202 is configured to perform navigation path planning in the navigation map matching the preset coordinate system according to the projection.

Embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program that, when executed by a processor, performs the robot positioning method of any of the above embodiments.

Embodiments of the present invention also provide a robot, including a laser sensor and an image collector, further comprising a processor, wherein the processor is configured to perform the robot positioning method of any of the above embodiments.

For details of the implementation process of the functions and functions of the modules in the foregoing devices, refer to the implementation process of the corresponding steps in the foregoing methods, and details are not described herein again.

For the device embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment. The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the present application. Those of ordinary skill in the art can understand and implement without any creative effort.

The above is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., which are made within the spirit and principles of the present application, should be included in the present application. Within the scope of protection.

Claims

A robot positioning method includes:

Acquiring an image through an image collector on the robot;

Extracting feature points from the image;

Determining a target sample feature point that matches the feature point in a pre-stored feature point library;

Determining the image collection according to a coordinate of the target sample feature point stored in a preset coordinate system and a coordinate mapping relationship between the target sample feature point and the image collector in the preset coordinate system. The coordinates of the device in the preset coordinate system.
The method of claim 1 further comprising:

Determining a positional relationship and a posture relationship of the laser sensor on the robot with respect to the image collector before acquiring the sample image by the image collector;

Determining a first coordinate of the laser sensor in the preset coordinate system;

Converting the first coordinate according to the positional relationship and the attitude relationship to obtain a second coordinate of the image collector in the preset coordinate system;

Collecting the sample image by the image collector;

Extracting a plurality of sample feature points from the sample image is stored in the feature point library, and the target sample feature point is one of the plurality of sample feature points;

Determining the coordinate mapping relationship according to the depth information, the position information of each of the sample feature points in the sample image, and the angle information when the image collector acquires the sample image;

Determining, according to the second coordinate and the coordinate mapping relationship, a third coordinate of the sample feature point in the preset coordinate system;

And storing the third coordinate and the coordinate mapping relationship.
The method according to claim 2, wherein determining a positional relationship and an attitude relationship of the laser sensor with respect to the image collector comprises:

A positional relationship and a posture relationship of the laser sensor with respect to the image collector are determined according to a nonlinear optimization algorithm.
The method according to claim 2, wherein the depth information, the position information in the sample image, and the angle information when the image collector acquires the sample image are determined according to the angle information of the sample feature point The mapping relationship includes:

And determining the mapping relationship according to the depth information, the location information, the angle information, and an imaging model of the image collector.
The method according to any one of claims 1 to 4, wherein the image is collected by the image collector on the robot, comprising:

The image is acquired by the image collector when the robot is activated.
The method according to any one of claims 1 to 4, further comprising:

Generating a navigation map by scanning the area where the robot is located by the laser sensor;

Matching the navigation map and the preset coordinate system;

According to the coordinates of the image collector in the preset coordinate system, the navigation path planning is performed in the navigation map matching the preset coordinate system.
The method according to claim 6, wherein the navigation path planning in the navigation map matching the preset coordinate system according to the coordinates of the image collector in the preset coordinate system comprises:

Determining a projection of the contour of the robot in the preset coordinate system according to a position of the image collector on the robot;

Navigation path planning is performed in the navigation map matching the preset coordinate system according to the projection.
A robot positioning device comprising:

a feature point extraction module, configured to extract a feature point from an image collected by an image collector on the robot;

a feature point matching module, configured to determine a target sample feature point that matches the feature point in a pre-stored feature point library;

a first coordinate determining module, configured to: according to pre-stored coordinates of the target sample feature point in a preset coordinate system, and coordinates of the target sample feature point and the image collector in the preset coordinate system Mapping the relationship, determining coordinates of the image collector in the preset coordinate system.
A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to perform the robot positioning method according to any one of claims 1 to 7.
A robot characterized by comprising a laser sensor and an image collector, further comprising a processor, wherein the processor is configured to perform the robot positioning method according to any one of claims 1 to 7.