WO2019104740A1

WO2019104740A1 - Method and system for measuring odometer compensation coefficient of vision cleaning robot

Info

Publication number: WO2019104740A1
Application number: PCT/CN2017/114339
Authority: WO
Inventors: 王声平; 周毕兴
Original assignee: 深圳市沃特沃德股份有限公司
Priority date: 2017-12-01
Filing date: 2017-12-01
Publication date: 2019-06-06

Abstract

A method and a system for measuring an odometer compensation coefficient of a vision cleaning robot. Said method is used to calculate, on the basis of actual displacement as calculated from a fixed-size picture acquired by a cleaning robot during movement, and of displacement as acquired by an odometer, an odometer compensation coefficient. The present method can automatically calculate the compensation coefficient using a sensor of the vision cleaning robot, improving the calibration efficiency and accuracy.

Description

\¥0 2019/104740 卩(:17 \2017/114339

1

Method and system for measuring compensation coefficient of visual sweeping robot odometer

[0001] The present invention relates to the field of factory inspection of visual sweeping robots, and more particularly to a method and system for measuring the compensation coefficient of a visual sweeping robot odometer.

Background technique

[0002] The odometer is a key component of a visual sweeping robot used to measure the displacement and movement speed of a visual sweeping robot. The odometer is typically provided with an encoder that calculates the distance traveled based on the angle at which the encoder rotates and the circumference of the wheel. Due to environmental factors or structural factors, the calculated distance between the odometer and the actual distance is different. Generally, the odometer is calibrated before leaving the factory, and the compensation coefficient is calculated to compensate the distance calculated by the odometer. The detected distance is accurate.

[0003] Nowadays, the visual sweeping robot is manually manually calibrated to calculate the compensation coefficient before leaving the factory, so that the measured speed is relatively slow and the accuracy is not very high.

technical problem

[0004] A primary object of the present invention is to provide a method for quickly and automatically calibrating a visual sweeping robot odometer.

Problem solution

Technical solution

[0005] The present invention provides a method for measuring a compensation coefficient of a visual sweeping robot odometer having a fixed size picture, the method comprising the steps of:

[0006] controlling the visual sweeping robot to move a distance within a specified environment, wherein the visual sweeping robot has a fixedly set fixed-size image in the field of view during the moving process;

[0007] According to the fixed size picture, calculate the displacement of the actual movement of the visual sweeping robot 1 _^ 2;

[0008] obtaining the displacement 0 of the odometer record;

[0009] The compensation coefficient is calculated by dividing the displacement of the actual movement of the visual sweeping robot by 1 _^ 2 by the displacement recorded by the odometer by 1 _^ 1.

[0010] Further, the step of calculating the displacement 1 _^ 2 of the actual movement of the visual sweeping robot according to the visual system of the visual sweeping robot comprises: \¥0 2019/104740 卩(:17 \2017/114339

2

[0011] according to the picture collected by the visual sweeping robot, the feature points in the picture are spatially reconstructed three-dimensionally, and the three-dimensional space coordinates of the feature points are obtained, thereby obtaining three-dimensional information of the image;

[0012] calculating a displacement 2 of the actual movement of the visual cleaning robot according to the three-dimensional information of the image.

[0013] Further, the step of calculating the displacement 1 _^ 2 of the actual movement of the visual cleaning robot according to the three-dimensional information of the image comprises:

[0014] obtaining a scale number 11 of the distance between the initial motion position of the visual sweeping robot and the fixed size image in the three-dimensional space and the scale of the distance between the end motion position and the fixed size image in the three-dimensional space by 2;

[0015] calculating scale information corresponding to each scale according to a preset rule

[0016] first calculating a difference between the scale number 11 of the initial motion position in the three-dimensional space and the image distance of the fixed size and the scale number of the scale number of the initial motion position in the three-dimensional space and the image distance of the fixed size, Then multiply the difference by the scale information ₈ to calculate the displacement of the actual movement of the visual sweeping robot by 1 _^ 2 .

[0017] Further, the step of calculating the scale information ₈ corresponding to each scale according to a preset rule includes:

[0018] The size of the obtained picture in the three-dimensional space is 3;

[0019] The scale information 8 is calculated by dividing the value of the fixed size preset by the picture by the size of the picture in the three-dimensional space by a scale of three.

[0020] Further, the step of controlling the movement of the visual cleaning robot within the specified environment comprises:

[0021] The camera controlling the visual cleaning robot is moving in the direction of the vertical picture facing the picture.

[0022] Further, after the calculating the compensation coefficient, the method includes the following steps:

[0023] A plurality of compensation coefficients are calculated a plurality of times, and an average value of the plurality of compensation coefficients is calculated.

[0024] Further, the picture is a two-dimensional code.

[0025] The present invention also provides a system for measuring a compensation coefficient of a visual sweeping robot odometer having a fixed size picture, the system comprising:

[0026] a mobile device, configured to control the visual cleaning robot to move a distance within a specified environment, wherein the visual cleaning robot always has a fixedly set picture with a fixed size in the field of view during the moving process;

[0027] an actual displacement device, configured to calculate an actual movement of the visual cleaning robot according to the fixed size picture \¥0 2019/104740 卩(:17 \2017/114339

3 moving displacement! _^ 2;

[0028] an odometer displacement device for obtaining a displacement recorded by the odometer 1 _^ 1;

[0029] The compensation coefficient device is configured to calculate the compensation coefficient by dividing the displacement 1 _^ 2 of the actual movement of the visual sweeping robot by the displacement 1 _^ 1 recorded by the odometer.

[0030] Further, the actual displacement device includes:

[0031] a building module, configured to perform spatial three-dimensional reconstruction of feature points in the image according to the image captured by the visual sweeping robot, to obtain a three-dimensional space of the feature point, and thereby obtain three-dimensional information of the image;

And a calculating module, configured to calculate, according to the three-dimensional information of the image, a displacement of the actual movement of the visual cleaning robot by 1 _^ 2.

[0033] Further, the calculating module includes:

[0034] a moving scale sub-module, configured to acquire a scale number II of an initial moving position of the visual sweeping robot in the three-dimensional space and an image distance of the fixed size, and a target distance between the end moving position and the fixed size image Degree is 2;

[0035] a scale information sub-module, configured to calculate scale information corresponding to each scale according to a preset rule

[0036] a calculation sub-module, configured to first calculate a difference between the scale numbers 11 and 72 of the initial motion position in the three-dimensional space and the fixed-size image distance, and multiply the difference by the scale information ₈ to calculate the visual sweeping robot. The actual movement displacement is 1 _^ 2.

[0037] Further, the scale information sub-module includes:

[0038] obtaining a size unit, the size of the size used to obtain the picture in the three-dimensional space is 3;

[0039] The calculating unit calculates the scale information 8 by dividing the value of the fixed size preset by the picture by the size of the picture in the three-dimensional space by 3.

[0040] Further, the mobile device includes:

[0041] a vertical module, the camera for controlling the visual cleaning robot is moving in the direction of the vertical picture facing the picture.

[0042] Further, the system for measuring a compensation coefficient of a visual sweeping robot odometer further includes:

[0043] A plurality of calculation means for repeatedly calculating a plurality of compensation coefficients and calculating an average value of the plurality of compensation coefficients.

[0044] Further, the picture is a two-dimensional code. \¥0 2019/104740 卩(:17 \2017/114339

4 beneficial effects of the invention

Beneficial effect

[0045] Compared with the prior art, the beneficial effects of the present invention are: using the sensor of the visual sweeping robot to automatically calculate the compensation coefficient, improve the calibration efficiency of the visual sweeping robot, reduce the time of manual calibration, and provide trademarks. Precision.

Brief description of the drawing

DRAWINGS

1 is a schematic diagram showing the steps of a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

2 is a schematic diagram showing the steps of a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

3 is a schematic diagram showing the steps of a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

4 is a schematic diagram showing the steps of a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

5 is a schematic diagram showing the steps of a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

6 is a schematic structural view of a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

7 is a schematic structural diagram of an actual displacement device of a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

8 is a schematic structural diagram of a calculation module of a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

9 is a schematic structural diagram of a scale information sub-module of a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

10 is a schematic structural diagram of a moving device of a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention;

11 is a structural diagram showing a system for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention. \¥0 2019/104740 卩(:17 \2017/114339

5 Intention.

[0057] The implementation, functional features, and advantages of the present invention will be further described with reference to the accompanying drawings.

BEST MODE FOR CARRYING OUT THE INVENTION

The specific embodiments described herein are intended to be illustrative only and not to limit the invention.

[0059] Referring to FIG. 1, a method for measuring a compensation coefficient of a visual sweeping robot odometer according to an embodiment of the present invention is provided. The measurement environment has a fixed size picture, and the method includes the following steps:

[0060] 81, controlling the visual cleaning robot to move a distance within a specified environment, wherein the visual cleaning robot always has a fixedly set picture with a fixed size in the field of view during the movement;

[0061] 82, according to the fixed size picture, calculate the displacement of the actual movement of the visual sweeping robot 1 _^ 2;

[0062] 33, obtain the displacement 0 recorded by the odometer;

[0063] 4. The compensation coefficient is calculated by dividing the displacement of the actual movement of the visual sweeping robot by 1 _^ 2 by the displacement recorded by the odometer 1 _^ 1.

[0064] In this embodiment, the visual sweeping robot moves within the environment, the floor is a smooth plane, the visual sweeping robot can move normally, the visual sweeping machine has a vision system, and the visual system uses the machine instead of the human eye to make measurements and Judge. The vision system refers to converting the ingested target into an image signal through a machine vision product (ie, an image capturing device, divided into 0 MOS and 0), and transmitting it to a dedicated image processing system, according to pixel distribution, brightness, color, and the like, Turning into a digitized signal; the vision system performs various operations on these signals to extract features of the target, and then controls the behavior of the device in the field based on the result of the discrimination. It can be used to measure distances. The visual sweeping robot is equipped with a vision system that can measure the distance of obstacles in front and obtain map information of the cleaning environment. In this embodiment, when the visual cleaning robot moves, the picture of the fixed size is always in the field of view thereof, and the visual cleaning robot takes a picture in the field of view of the visually-scanning robot, and uses the fixed-size picture as a reference to measure the visual sweeping. The actual displacement of the robot is 1 _^ 2, and then the displacement calculated by the oscilloscope of the visual sweeping robot is read 1 _^ 1, and 1 _^ 2 is divided by 0 to calculate the compensation coefficient.

[0065] Referring to FIG. 2, the step of calculating the displacement 1 _^ 2 32 of the actual movement of the visual sweeping robot according to the fixed size picture includes: \¥0 2019/104740 卩(:17 \2017/114339

6

[0066] 21. According to the picture collected by the visual sweeping robot, the feature points in the picture are spatially reconstructed three-dimensionally, and the three-dimensional space coordinates of the feature points are obtained, thereby obtaining three-dimensional information of the image;

[0067] 822, information of the three-dimensional image, the cleaning robot calculates the actual movement of the visual displacement! _^

2.

[0068] In the embodiment, the visual cleaning robot takes a picture of the visual system during the cleaning, and reconstructs the three-dimensional structure of the space according to the taken photo to obtain a three-dimensional space, and then marks the position before the movement of the visual cleaning robot and the position after the movement. In the three-dimensional space, the actual moving distance of the visual sweeping robot is calculated to be 1 _^ 2 in the three-dimensional space. Establishing a three-dimensional space, more accurate acquisition of the position of the visual sweeping robot, the calculated actual moving distance 1 _^ 2 is more accurate.

[0069] Referring to FIG. 3, the step of calculating the displacement 1 _^ 2 322 of the actual movement of the visual cleaning robot according to the three-dimensional information of the image includes:

[0070] 8221. Obtain a scale number 11 of the distance between the initial motion position of the visual cleaning robot and the fixed size in the three-dimensional space, and a scale number of the distance between the end motion position and the fixed size image in the three-dimensional space. ;

[0071] 8222. Calculate scale information corresponding to each scale according to a preset rule.

[0072] 3223, first calculating the number of scales of the initial motion position in the three-dimensional space and the image distance of the fixed size

II and the scale of the scale of the initial motion position in the three-dimensional space and the image distance of the fixed size are two, and then multiply the difference by the scale information ₈ to calculate the displacement of the actual movement of the visual sweeping robot 1 _^ 2 .

[0073] In the embodiment, in the three-dimensional space, each dimension has a scale at intervals, and the distance corresponding to the scale refers to the scale information ₈ . In the three-dimensional space, the distance scale number 11 of the visual sweeping robot and the fixed size is calculated at the starting position, and the distance scale number of the visual sweeping robot and the fixed size is calculated at the end position by 2, and then according to each The scale information 8 of the number of scales can be calculated as 1 _^ 2 . Specifically, first calculate the difference between 0 and 1 _^ 2, and then multiply the difference by ₈ to get 1 _^ 2. The size of ₈ can be calculated according to preset rules and some parameters preset by the user. Wherein, the scale number is a two-dimensional vector. In a specific embodiment, a two-dimensional coordinate system is established with a fixed-size image as an origin.

The coordinates of the initial position of the sweeping robot are: the eleven of the shell tree is ^1), the coordinates of the end position are (X 2^2), and the corresponding 12 is 2, \2), then the difference between 11 and 12 is calculated according to the formula.

\¥0 2019/104740 卩(:17 \2017/114339

7 can be calculated.

[0074] Referring to FIG. 4, further, the scale information corresponding to each scale is calculated according to a preset rule. 8

The steps of 222 include:

[2215] 82221 _^ The size of the obtained picture in the three-dimensional space has a scale of 3;

[0076] 82222. The value of the fixed size preset by the picture is divided by the size of the picture in the three-dimensional space.

3 Calculate the scale information 8.

[0077] In this embodiment, in a three-dimensional space, a fixed-size picture is a picture occupying a certain length and a width, and the length and the width are known, and the length and the width occupied by the standard in the three-dimensional space are calculated. With a degree of 13, the actual length value corresponding to each scale can be clearly obtained. According to the preset third calculation formula, the fixed length is divided by the fixed length of the picture by a number of 3, that is, ₈ can be calculated. Or, 13 indicates the number of scales of the width of the picture, and the fixed width is divided by 13 to obtain the scale information 8.

[0078] Referring to FIG. 5, further, the step of controlling the movement of the visual cleaning robot within the specified environment includes:

[0079] 311. The camera controlling the visual cleaning robot is moving in the direction of the vertical picture facing the picture.

[0080] In this embodiment, the camera of the visual sweeping robot is facing the picture, so that the mirror surface of the camera is parallel to the picture, and the central axis of the camera is directly opposite the middle of the picture, and the picture captured by the camera is always facing, so that the collection is performed. The size error of the picture is smaller, so that the corresponding compensation coefficient is more accurate.

[0081] Further, after the calculating the compensation coefficient, the method includes the following steps:

[0082] 85. Calculate a plurality of compensation coefficients repeatedly, and calculate an average value of the plurality of compensation coefficients.

[0083] In this embodiment, after the compensation coefficient is calculated, the compensation coefficient inevitably has an error. Moreover, the error is a random error. To further reduce the error, the best method is to perform multiple experimental calculations. Repeat the above steps of 31^4 to obtain a plurality of compensation coefficients, and calculate an average value of the plurality of compensation coefficients. The average value is used as the final compensation coefficient to improve the accuracy of the detection distance of the visual sweeping robot.

[0084] Further, the picture is a two-dimensional code.

[0085] In the embodiment, the two-dimensional code refers to a picture of data symbol information recorded in a black and white pattern in a plane (two-dimensional direction) by a certain geometric pattern, and the recognition degree is high, the camera After collecting the picture, it is easy to distinguish. \¥0 2019/104740 卩(:17 \2017/114339

8

[0086] In summary, the method for measuring the compensation coefficient of the visual sweeping robot odometer of the present invention can automatically calculate the compensation coefficient by using the sensor of the visual sweeping robot, improve the calibration efficiency of the visual sweeping robot, and reduce the manual calibration. Time, the accuracy of the trademark.

Referring to FIG. 6, the present invention further provides a system for measuring a compensation coefficient of a visual sweeping robot odometer, wherein the measurement environment has a fixed size picture, and the system includes:

[0088] The mobile device 1 is configured to control the visual sweeping robot to move a distance within a specified environment, wherein the visual sweeping robot always has a fixedly set fixed-size image in the field of view during the moving process;

[0089] The actual displacement device 2 is configured to calculate a displacement of the actual movement of the visual sweeping robot by 1 _^ 2 according to the fixed size picture;

[0090] odometer displacement device 3, used to obtain the displacement recorded by the odometer 1 _^ 1;

[0091] The compensation coefficient means 4 is for calculating the compensation coefficient by dividing the displacement 1 _^ 2 of the actual movement of the visual sweeping robot by the displacement 1 _^ 1 recorded by the odometer.

[0092] In this embodiment, the visual sweeping robot moves in the environment, the floor is a smooth plane, the visual sweeping robot can move normally, the visual sweeping machine has a vision system, and the visual system uses the machine instead of the human eye to make measurements and Judge. The vision system refers to converting the ingested target into an image signal through a machine vision product (ie, an image capturing device, divided into 0 MOS and 0), and transmitting it to a dedicated image processing system, according to pixel distribution, brightness, color, and the like, Turning into a digitized signal; the vision system performs various operations on these signals to extract features of the target, and then controls the behavior of the device in the field based on the result of the discrimination. It can be used to measure distances. The visual sweeping robot is equipped with a vision system that can measure the distance of obstacles in front and obtain map information of the cleaning environment. In this embodiment, when the visual sweeping robot moves, the moving device 1 keeps the fixed-size picture always within its field of view, and the visual sweeping robot takes a picture in the field of view thereof, with the fixed-size picture as a reference, the actual displacement. The device 2 measures the actual movement displacement of the visual sweeping robot by 1 _^ 2, and then the odometer displacement device 3 reads the displacement calculated by the odometer of the visual sweeping robot at this distance 1 _^ 1, and the compensation coefficient device 4 is divided by 1 _^ 2 With 1 _^ 1, the compensation coefficient can be calculated.

[0093] Referring to FIG. 7, further, the actual displacement device 2 includes:

[0094] The building module 21 is configured to: empty the feature points in the image according to the picture collected by the visual cleaning robot \¥0 2019/104740 卩(:17 \2017/114339

9 three-dimensional reconstruction, obtaining a three-dimensional space of the feature point, thereby obtaining three-dimensional information of the image;

[0095] The calculation module 22 is configured to calculate a displacement 1 _^ 2 of the actual movement of the visual cleaning robot according to the three-dimensional information of the image.

[0096] In this embodiment, when the visual sweeping robot cleans, the visual system takes a picture, and the constructing module 21 reconstructs the three-dimensional structure of the space according to the photograph taken to obtain a three-dimensional space, and then labels the position before the moving of the visual sweeping robot and the position after the moving. In the three-dimensional space, the calculation module 22 calculates the actual moving distance 1 _^ 2 of the visual sweeping robot in the three-dimensional space. Establishing a three-dimensional space, more accurate acquisition of the position of the visual sweeping robot, the calculated actual moving distance 1 _^ 2 is more accurate.

[0097] Referring to FIG. 8, further, the calculating module 22 includes:

[0098] a moving scale sub-module 221, configured to acquire a scale number II of an initial moving position of the visual sweeping robot in the three-dimensional space and an image distance of the fixed size, and an image distance between the end moving position and the fixed size Scale quantity 2;

[0099] The scale information sub-module 222 is configured to calculate scale information corresponding to each scale according to a preset rule.

[0100] The calculation sub-module 223 is configured to first calculate a difference between the scale numbers 11 and 72 of the initial motion position in the three-dimensional space and the image distance of the fixed size, and then multiply the difference by the scale information _{8 to} calculate the vision. The displacement of the sweeping robot actually moves 1 _^ 2.

[0101] In this embodiment, in the three-dimensional coordinate system, each dimension has a scale at intervals, and the distance corresponding to the scale refers to the scale information 8. In the three-dimensional space, the movement scale sub-module 221 calculates the distance scale number II of the visual sweeping robot and the fixed size at the starting position, and calculates the distance scale number 12 of the visual sweeping robot and the fixed size at the end position. Then, the calculation sub-module 223 can calculate 1 _^ 2 according to the scale information _{8 of} each scale number. Specifically, the calculation sub-module 223 first calculates the difference between 1 _^ 1 and 1 _^ 2, and then multiplies the difference by ₈ to obtain 1 _^ 2. The size of 8 is calculated by the scale information sub-module 222 according to preset rules and some parameters preset by the user. Wherein, the scale number is a two-dimensional vector. In a specific embodiment, a two-dimensional coordinate system is established with a fixed-size image as an origin, and the coordinates of the initial position of the sweeping robot are: 11 of the shell tree is ^1), ending The coordinates of the position are 2^2), and the corresponding 12 is (\2, \2), then the difference between 11 and 12 is calculated according to the formula.

Can be calculated.

[0102] Referring to FIG. 9, further, the scale information sub-module 222 includes:

[0103] obtaining a size unit 2221, for obtaining the scale data T3 of the size of the picture in the three-dimensional space;

[0104] The calculating unit 2222 is configured to calculate the scale information s by dividing the value of the fixed size preset by the picture by the number of scales T3 of the size of the picture in the three-dimensional space.

[0105] In the embodiment, in the three-dimensional space, the fixed-size picture is a picture occupying a certain length and a width, and the length and the width are known, and the obtained size unit 2221 calculates the length and the width in the three-dimensional space. The number of scales T3 occupied in the scale, the actual length value corresponding to each scale can be obtained. The calculating unit 2222 divides the fixed length by the fixed number of scales T3 of the picture according to the preset third calculation formula, that is, s can be calculated. Or, if T3 represents the number of scales of the width of the picture, divide the fixed width by T3.

[0106] Referring to FIG. 10, further, the mobile device 1 includes:

[0107] The vertical module 11 is configured to control the camera of the visual cleaning robot to move in the direction of the vertical picture facing the picture.

[0108] In this embodiment, the vertical module 11 faces the camera of the visual cleaning robot so that the mirror surface of the camera is parallel to the picture, and the central axis of the camera is directly opposite the middle of the picture, and the picture captured by the camera is always facing. , so that the size error of the captured picture is smaller, and the corresponding compensation coefficient is more accurate.

[0109] Referring to FIG. 11, further, the system for measuring a compensation coefficient of a visual sweeping robot odometer further includes

[0110] The multi-calculation device 5 is configured to repeatedly calculate a plurality of compensation coefficients and calculate an average value of the plurality of compensation coefficients.

[0111] In this embodiment, after the compensation coefficient is calculated, the compensation coefficient inevitably has an error. Moreover, the error is a random error. To further reduce the error, the best method is to perform multiple experimental calculations. The multiple calculation device 5 repeats the operation of the above devices multiple times to obtain a plurality of compensation coefficients, and calculates an average of multiple compensation coefficients. The value is used as the final compensation coefficient to improve the accuracy of the detection distance of the visual sweeping robot.

[0112] Further, the picture is a two-dimensional code. \¥0 2019/104740 卩(:17 \2017/114339

11

[0113] In the embodiment, the two-dimensional code refers to a picture of data symbol information recorded in a black and white pattern in a plane (two-dimensional direction) by a certain geometric pattern, and the recognition degree is high, the camera After collecting the picture, it is easy to distinguish.

[0114] In summary, the system for measuring the compensation coefficient of the visual sweeping robot odometer can automatically calculate the compensation coefficient by using the sensor of the visual sweeping robot, improve the calibration efficiency of the visual sweeping robot, and reduce the manual calibration. Time, the accuracy of the trademark.

The above is only a preferred embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the invention and the drawings are used directly or indirectly. Other related technical fields are equally included in the scope of patent protection of the present invention.

Claims

\¥0 2019/104740 卩(:17 \2017/114339 12 Claims

[Claim 1] A method of measuring a compensation coefficient of a visual sweeping robot odometer, wherein the measurement environment has a fixed size picture, and the method includes the steps of:

Controlling the visual sweeping robot to move a distance within a specified environment, wherein the visual sweeping robot always has a fixedly set fixed-size image in the field of view during the moving process;

Calculating a displacement 2 of the actual movement of the visual sweeping robot according to the fixed size picture;

Obtain the displacement recorded by the odometer! _^ 1 ;

The compensation coefficient is calculated by dividing the displacement of the actual moving robot by 1 _^ 2 by the displacement 0 recorded by the odometer.

[Claim 2] The method for visually measuring the oscilloscope compensation coefficient of the cleaning robot according to claim 1, wherein the step of calculating the displacement of the actual movement of the visual cleaning robot by the visual system of the visual cleaning robot is 1 _^ 2 include:

According to the image captured by the visual sweeping robot, the feature points in the image are spatially reconstructed three-dimensionally, and the three-dimensional space coordinates of the feature points are obtained, thereby obtaining three-dimensional information of the image; and the three-dimensional information of the image is used to calculate the The displacement of the visual sweeping robot actually moves 2.

[Claim 3] The method for measuring a compensation coefficient of a visual cleaning robot odometer according to claim 2, wherein the calculating a displacement of the actual movement of the visual cleaning robot according to the three-dimensional information of the image is 1 _^ The steps of 2 include:

Obtaining a number of scales II of the distance between the initial moving position of the visual sweeping robot and the image of the fixed size in the three-dimensional space; and a scale number of the distance between the end moving position and the fixed size in the three-dimensional space;

Calculating the scale information corresponding to each scale according to a preset rule, first calculating the scale number 11 of the initial motion position and the fixed size image distance in the three-dimensional space, and the initial motion position and the fixed size image in the three-dimensional space. The scale of the distance scale is a difference of 2, and the difference is multiplied by the scale information ₈ to calculate the visual sweeper. \¥0 2019/104740 卩(:17 \2017/114339

13 The actual movement of the person is shifted by 1 _^ 2.

[Claim 4] The method for measuring the compensation coefficient of the visual sweeping robot odometer according to claim 3, wherein the step of calculating the scale information ₈ corresponding to each scale according to a preset rule comprises:

The size of the obtained image in the three-dimensional space is 3;

The scale information _{8 is} calculated by dividing the value of the fixed size preset by the picture by the number of scales 13 of the size of the picture in the three-dimensional space.

[Claim 5] The method for measuring a visual sweeping robot odometer compensation coefficient according to claim 1, wherein the step of controlling the movement of the visually-swept robot within the specified environment comprises controlling the camera of the visual cleaning robot to face The picture moves in the direction of the vertical picture.

[Claim 6] The method for measuring a compensation coefficient of a visual sweeping robot odometer according to claim 1, wherein the calculating the compensation coefficient comprises the steps of: calculating a plurality of compensation coefficients repeatedly, and calculating a plurality of times The average of the compensation coefficients.

[Claim 7] The method of measuring a visual sweeping robot odometer compensation coefficient according to claim 1, wherein the picture is a two-dimensional code.

[Claim 8] A system for measuring a compensation coefficient of a visual sweeping robot odometer, wherein the measurement environment has a fixed size picture, the system comprising: a mobile device for controlling a visual sweeping robot at a designated Moving a distance within the environment, wherein the visual cleaning robot always has a fixedly set picture with a fixed size in the field of view during the movement;

An actual displacement device, configured to calculate a displacement of the actual movement of the visual sweeping robot by 1 _^ 2 according to the fixed size picture;

An odometer displacement device for obtaining a displacement of the odometer recorded by 1 _^ 1 ;

The compensation coefficient device is used to calculate the compensation coefficient by dividing the displacement of the actual movement of the visual sweeping robot by 1 _^ 2 by the displacement recorded by the odometer by 1 _^ 1.

[Claim 9] The system for measuring a visual sweeping robot odometer compensation coefficient according to claim 8, \¥0 2019/104740 卩(:17 \2017/114339

14 is characterized in that the actual displacement device comprises:

a building module, configured to perform spatial three-dimensional reconstruction of the feature points in the image according to the image captured by the visual sweeping robot, to obtain a three-dimensional space of the feature point, and thereby obtain three-dimensional information of the image;

[Claim 10] The system for measuring the compensation coefficient of the visual sweeping robot odometer according to claim 9, wherein the calculating module comprises:

a moving scale sub-module, the scale number 11 for obtaining the distance between the initial moving position of the visual sweeping robot and the fixed-size image in the three-dimensional space, and the scale of the distance between the ending moving position and the fixed-size image are 2 ;

a scale information sub-module, configured to calculate scale information corresponding to each scale according to a preset rule;

a calculation sub-module, configured to first calculate a difference between the scale numbers 11 and 72 of the initial motion position in the three-dimensional space and the fixed-size image distance, and multiply the difference by the scale information ₈ to calculate the actual movement of the visual sweeping robot. The displacement is 1 _^ 2.

[Claim 11] The system for measuring the compensation coefficient of the visual sweeping robot odometer according to claim 10, wherein the scale information sub-module comprises:

Obtaining a size unit, the size of the image used to obtain the image is 3 in the three-dimensional space; the calculation unit is used to divide the value of the fixed size preset by the image by the size of the image in the three-dimensional space. , Calculate the scale information 8.

[Claim 12] The system for measuring a visual sweeping robot odometer compensation coefficient according to claim 8, wherein the mobile device comprises:

A vertical module, the camera for controlling the visual sweeping robot is moving in the direction of the vertical picture facing the picture.

[Claim 13] The system for measuring a compensation coefficient of a visual cleaning robot odometer according to claim 8, further comprising:

Multiple calculation devices for repeatedly calculating multiple compensation coefficients and calculating multiple compensation systems \¥0 2019/104740 卩(:17 \2017/114339

The average of 15 numbers.

[Claim 14] The system for measuring a visual sweeping robot odometer compensation coefficient according to claim 8, wherein the picture is a two-dimensional code.