CN114690755A - Cleaning robot and obstacle detouring method thereof - Google Patents

Abstract

The utility model discloses a cleaning robot and obstacle detouring method thereof, the cleaning robot is provided with a camera, and the obstacle detouring method comprises the following steps: acquiring an image in front of the cleaning robot through a camera; generating a virtual line of travel and a virtual line of sight on the image, wherein the virtual line of travel on the image corresponds to a virtual line formed by forward extension of the left edge and the right edge of the cleaning robot in the actual environment, and the virtual line of sight in the image corresponds to a virtual line at a preset safety distance in front of the cleaning robot in the actual environment; and controlling the cleaning robot to walk around the obstacle by taking the obstacle in the image at the virtual traveling line and the side of the virtual sight distance line far away from the cleaning robot as a constraint condition. The cleaning robot of this disclosure not only can be through camera discernment barrier, can also be through generating virtual line of going and virtual stadia line on the image is gathered to the camera, by-pass the barrier at the in-process of walking.

Description

Cleaning robot and method for bypassing obstacles

technical field

The present disclosure relates to the technical field of cleaning equipment, and in particular, to a cleaning robot and a method for bypassing obstacles.

Background technique

A cleaning robot is a smart device that can autonomously clean the home environment. In the process of cleaning complex and diverse home environments or building maps, cleaning robots usually need to rely on laser ranging sensors to determine whether there are obstacles in front of the cleaning robots, so as to avoid collisions between the cleaning robots and obstacles ahead. The cleaning robot is then guided around obstacles with the help of sensors along the wall, collision sensors, etc.

At present, there is no cleaning robot that can walk around the identified obstacles through the camera.

SUMMARY OF THE INVENTION

The present disclosure provides a cleaning robot and a method for bypassing obstacles, which can walk around the identified obstacles through a camera.

In a first aspect, the present disclosure provides a method for circumventing an obstacle for a cleaning robot, the cleaning robot is provided with a camera, and the method for circumventing an obstacle includes:

Obtain the image in front of the cleaning robot through the aforementioned camera;

A virtual travel line and a virtual line of sight are generated on the aforementioned image. The virtual travel line on the aforementioned image corresponds to the virtual line formed by the left and right edges of the cleaning robot extending forward in the actual environment. The virtual line of sight in the aforementioned image corresponds to Corresponds to the virtual line at the preset safety distance in front of the aforementioned cleaning robot in the actual environment;

Taking the obstacle in the above image on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint condition, the cleaning robot is controlled to walk around the obstacle.

Optionally, the aforementioned obstacle is located on the side of the aforementioned virtual travel line and the aforementioned virtual line of sight away from the aforementioned cleaning robot as a constraint condition, and the aforementioned cleaning robot is controlled to walk around the aforementioned obstacle, including:

When the obstacle in the image is in contact with the virtual line of sight, the cleaning robot is controlled to walk around the obstacle with the tangent of the obstacle and the virtual travel line in the image as a constraint.

Optionally, the aforementioned obstacle is located on the side of the aforementioned virtual travel line and the aforementioned virtual line of sight away from the aforementioned cleaning robot as a constraint condition, and the aforementioned cleaning robot is controlled to walk around the aforementioned obstacle, including:

When the obstacle in the aforementioned image is in contact with the aforementioned virtual line of sight, determining the estimated value of the width and length of the aforementioned obstacle according to the aforementioned image;

According to the estimated value of the length of the obstacle, determine the obstacle circumvention end point of the cleaning robot, and the obstacle circumvention end point and the current position of the cleaning robot are respectively located on opposite sides of the obstacle;

According to the current position and the end point of the obstacle, the obstacle route is planned;

Make the aforementioned cleaning robot walk along the aforementioned obstacle course, and when the aforementioned virtual line of sight and/or the aforementioned virtual travel line touches the aforementioned obstacle, update the aforementioned obstacle bypass end point according to the image obtained during the traveling process, and according to the updated The end point of the obstacle bypass adjusts the subsequent obstacle bypass path.

Optionally, the aforementioned planning of the obstacle bypass path according to the aforementioned current position and the aforementioned obstacle bypass end point includes:

The distance between the current position and the end point of the obstacle is determined, and the diameter is the distance and the arc connecting the current position and the end point of the obstacle is taken as the obstacle path.

Optionally, the aforementioned planning of the obstacle bypass path according to the aforementioned current position and the aforementioned obstacle bypass end point includes:

Take the connection between the current position and the end point of the obstacle as the first axis;

Determine a second axis perpendicular to the first axis according to the width of the obstacle and the size of the cleaning robot;

The long axis and the short axis are respectively the first axis and the second axis, and the elliptical arc connecting the current position and the end point of the obstacle is taken as the obstacle bypass path.

Optionally, the aforementioned planning of the obstacle bypass path according to the aforementioned current position and the aforementioned obstacle bypass end point includes:

Determine a plurality of intermediate points between the current position and the end point of the obstacle, and the intermediate points are located outside the obstacle;

The line connecting the current position, the middle point, and the end point of the obstacle bypass in sequence is used as the obstacle bypass path.

Optionally, the aforementioned generation of a virtual travel line and a virtual line of sight on the aforementioned image includes:

The virtual travel line and the virtual line of sight are added to the image according to the predetermined virtual travel line and the virtual line of sight mapped to the position in the calibration image captured by the camera.

Optionally, the aforementioned method for bypassing the barrier further includes:

The calibration image of the calibration object is obtained by the camera; the calibration object has a first line representing the virtual travel line and a second line representing the virtual line of sight;

The positions of the first line and the second line in the calibration image are determined.

Optionally, the aforementioned method for bypassing the barrier further includes:

In response to the aforementioned cleaning robot turning, determining the steering trajectory of the aforementioned cleaning robot;

The aforementioned virtual travel line is adjusted to extend along the aforementioned turning trajectory.

In a second aspect, the present disclosure provides a cleaning robot, which includes a processor, a memory, and execution instructions stored on the memory, the execution instructions being configured to enable the cleaning robot to execute the first step when executed by the processor. In one aspect, the method for bypassing the barrier described in any one of the technical solutions.

Based on the foregoing description, those skilled in the art can understand that the present disclosure acquires an image in front of the cleaning robot through a camera, and generates a virtual travel line and a virtual line of sight in the image, so that the virtual travel line can be used to determine that the cleaning robot will The walking path determines the safe distance of the cleaning robot in the traveling direction through the virtual line of sight. Then, the obstacle in the image is located on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint condition, and the cleaning robot is controlled to walk around the obstacle. Therefore, the present disclosure can not only identify obstacles through the camera, but also generate a virtual travel line and a virtual line of sight on the images collected by the camera, so that the obstacle is always located in a part of the virtual travel line and the virtual line of sight far away from the cleaning robot. side, to avoid the collision between the cleaning robot and the obstacle in the process of walking.

Further optionally, when the obstacle in the image is in contact with the virtual line of sight, the cleaning robot is controlled to walk around the obstacle by taking the tangent of the obstacle in the image and the virtual travel line as the constraint condition, so that the cleaning robot is walking around the obstacle. In the process of moving obstacles, always keep a relatively close distance with the obstacles, so as to clean the environment around the obstacles finely.

Further optionally, when the obstacle in the image is in contact with the virtual line of sight, by determining the estimated value of the width and length of the obstacle in the image, the end point of the cleaning robot around the obstacle can be preliminarily determined, so that the cleaning robot can be based on the current position and around the obstacle. The obstacle end point is planned to bypass the obstacle, so that the cleaning robot can quickly bypass the obstacle. At the same time, when the virtual line of sight and/or the virtual travel line touches an obstacle, the obstacle bypass end point is updated according to the image obtained during the travel process, and the subsequent obstacle bypass path is adjusted according to the updated obstacle bypass end point, so as to effectively avoid the obstacle. The situation in which the cleaning robot collides with the obstacle during the obstacle course is analyzed.

Description of drawings

In order to illustrate the technical solutions of the present disclosure more clearly, some embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In the accompanying drawings:

1 is a schematic flowchart of the main steps of a method for bypassing a barrier in the first embodiment of the present disclosure;

2 is a schematic diagram of the effect of an image with a virtual travel line and a virtual line of sight in the first embodiment of the present disclosure;

3 is a schematic diagram of a fine obstacle-circumferential path of the cleaning robot in the first embodiment of the present disclosure;

FIG. 4 is a schematic diagram of the effect of the image of the cleaning robot in the process of finely circumventing obstacles in the first embodiment of the present disclosure;

5 is a flow chart of steps for a cleaning robot to quickly bypass obstacles in the first embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a fast obstacle course of the cleaning robot in the first embodiment of the present disclosure (completed in one planning);

7 is a schematic diagram of a path of a rapid obstacle-circumvention process of the cleaning robot in the first embodiment of the present disclosure (the path is an arc);

8 is a schematic diagram of a path of a rapid obstacle-circumvention process of the cleaning robot in the first embodiment of the present disclosure (the path is an elliptical arc);

FIG. 9 is a schematic diagram of a path of a quick obstacle course of the cleaning robot in the first embodiment of the present disclosure (the path is a polygon);

10 is a schematic diagram of a path of a quick obstacle-circumvention process of the cleaning robot in the first embodiment of the present disclosure (the path is a multi-I-shaped);

FIG. 11 is a schematic diagram of a fast obstacle course of the cleaning robot in the first embodiment of the present disclosure (multiple planning is completed);

FIG. 12 is a schematic flowchart of part of the steps of the barrier bypass method in the second embodiment of the present disclosure;

13 is a schematic diagram of calibrating a camera in the second embodiment of the present disclosure;

FIG. 14 is a schematic flowchart of part of the steps of the barrier bypass method in the third embodiment of the present disclosure;

15 is a schematic diagram of a virtual travel line and a virtual line of sight when the cleaning robot turns a corner in the third embodiment of the present disclosure;

16 is a geometric schematic diagram of a virtual line of travel steering angle in the third embodiment of the present disclosure;

FIG. 17 is a schematic flowchart of part of the steps of the barrier bypass method in the fourth embodiment of the present disclosure;

FIG. 18 is a schematic structural diagram of a cleaning robot in a fifth embodiment of the present disclosure.

List of reference numbers:

1. Virtual traveling line; 11. Left virtual traveling line; 12. Right virtual traveling line; 13. Middle virtual traveling line;

2. Virtual line of sight; 21. The first virtual line of sight; 22, The second virtual line of sight; 23, The third virtual line of sight;

3. Obstacles;

4. Cleaning robot; 41. Camera

5. Path around obstacles;

6. Calibration board.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be clearly and completely described below with reference to specific embodiments and corresponding drawings. It should be understood by those skilled in the art that the embodiments described in the detailed description in this section are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. Based on the embodiments described in the detailed description of this section, all other embodiments obtained by those of ordinary skill in the art without creative work will not deviate from the technical principles of the present disclosure, and therefore should fall within the scope of within the protection scope of the present disclosure.

It should be noted that, in the description of the present disclosure, each functional module may be a physical module composed of multiple structures, components or electronic components, or a virtual module composed of multiple programs; each functional module may be It is a module that exists independently of each other, or it can be a module divided by a whole module according to its functions. It should be understood by those skilled in the art that, on the premise that the technical solutions described in the present disclosure can be realized, no matter how the composition mode, implementation mode, and positional relationship of each functional module change, they will not deviate from the technical principles of the present disclosure. should fall within the scope of protection of the present disclosure.

The cleaning robots of the present disclosure include robots with cleaning functions, such as sweeping robots, mopping robots, and sweeping-suction-mopping integrated robots. The cleaning robot of the present disclosure is provided with a camera, and the camera can capture an image in front of the cleaning robot. The cleaning robot of the present disclosure further includes two driving wheels, the two driving wheels are respectively located on the left and right sides of the cleaning robot, and the two driving wheels are used to drive the cleaning robot to walk and turn.

Some embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

In the first embodiment of the present disclosure:

As shown in FIG. 1 , the obstacle circumvention method for the cleaning robot in this embodiment includes:

In step S110, an image in front of the cleaning robot is acquired through a camera.

In this embodiment, during the walking process of the cleaning robot, the camera can obtain an image in front of the cleaning robot at intervals (for example, 0.5 seconds, 1 second, 1.8 seconds, 5 seconds, etc.) to capture a video of the front of the cleaning robot, and then extract the frames of the video.

In step S120, a virtual travel line 1 and a virtual line of sight 2 are generated on the image.

As shown in FIG. 2, pre-stored virtual travel line data and virtual line of sight data are added to the image acquired in step S110, or according to the image acquired in step S110 and the pre-stored virtual travel line data and virtual line of sight The line data generates a new image so as to combine the image acquired in step S110 with the pre-stored virtual travel line data and virtual line of sight line data.

Continuing to refer to FIG. 2 , the virtual travel line 1 on the image corresponds to the virtual line formed by the left and right edges of the cleaning robot extending forward in the actual environment. Preferably, the left virtual travel line 11 and the right virtual travel line 12 on the image are the same width as the cleaning robot, so that the image appears in contact with or between the left and right virtual travel lines 11 and 12 When there is an obstacle, it can be determined that there is an obstacle in front of the cleaning robot that hinders the cleaning robot. In addition, on the premise that the obstacle that hinders the cleaning robot from traveling can be identified from the image, those skilled in the art can also make the distance between the left virtual traveling line 11 and the right virtual traveling line 12 on the image as required. Greater or less than the width of the cleaning robot.

Continuing to refer to FIG. 2 , the virtual line of sight 2 in the image corresponds to the virtual line at the preset safety distance in front of the cleaning robot in the actual environment. The preset safety distance refers to the distance from the time the cleaning robot obtains the image ahead through the camera, to the time the cleaning robot recognizes that there is an obstacle ahead through the obtained image, and then stops moving or turning. maximum distance. On the premise that the cleaning robot does not collide with obstacles ahead, the preset safety distance can be any feasible value, such as 5cm, 15cm, 20cm, 40cm, 50cm, 100cm, etc.

Further, the number of virtual line of sight 2 in the image may be one or more, such as the first virtual line of sight 21 , the second virtual line of sight 22 and the third virtual line of sight as shown in FIG. 2 Line 23. Wherein, the value range of the distance between the first virtual line of sight 21 and the cleaning robot is [5cm, 15cm]; the value range of the distance between the second virtual line of sight 22 and the cleaning robot is [20cm, 40cm] ]; the value range of the distance between the third virtual line of sight line 23 and the cleaning robot is [50cm, 100cm].

Step S130: Control the cleaning robot to walk around the obstacle with the obstacle located on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint condition.

As an example, when the obstacle in the image is in contact with the virtual line of sight 2, the cleaning robot is controlled to walk around the obstacle with the tangent of the obstacle in the image and the virtual travel line 1 as a constraint. The present example will be described in detail below with reference to FIGS. 3 and 4 .

As shown in FIG. 3 , when the cleaning robot 4 travels to the position 1, the obstacle 3 is in contact with the first virtual line of sight 21, so that the cleaning robot 4 turns in place until the obstacle 3 leaves the left virtual travel line 11 and When tangent to it (see FIG. 4 ), the cleaning robot 4 is then made to travel from position 1 to position 2 in a straight line.

Further, when the cleaning robot 4 moves to position 2, the left virtual travel line 11 is not tangent to the obstacle 3, so that the cleaning robot 4 is turned until the left virtual travel line 11 is tangent to the obstacle 3, and then the cleaning robot is turned. 4 Travel from position 2 to position 3 in a straight line.

Repeat the above process, make the cleaning robot 4 drive to position 3, position 4, and position 5, until it drives to position 6, so that the cleaning robot returns to the original straight line without obstacles, and then makes the cleaning robot stay in place Steering, return to the forward travel attitude in position 1, and continue to perform the original walking operation. Alternatively, the cleaning robot 4 is made to repeat the above process, and the obstacle 3 is circled around the obstacle 3 to realize edge cleaning.

It can be understood by those skilled in the art that the path planning strategy in Example 1 of this embodiment can enable the cleaning robot to clean the edge area of obstacles in an all-round way without dead ends, and is especially suitable for narrow spaces such as corners and corners and under the bed under the cabinet. cleaning job. However, this kind of path planning strategy requires a lot of repeated obstacle detection and condition judgment, resulting in a large consumption of computing resources and occupation of computing power. To this end, this embodiment also provides a route planning strategy for quick cleaning. For details, please refer to Example 2 described below.

As shown in Figure 5, the path planning of Example 2 includes:

Step S131, when the obstacle in the image is in contact with the virtual line of sight, determine the estimated value of the width and length of the obstacle according to the image.

Step S132: Determine the obstacle-circumferential end point of the cleaning robot according to the estimated length of the obstacle.

Step S133 , planning the obstacle bypass path according to the current position and the obstacle bypass end point.

Step S134, making the cleaning robot walk along the path around the obstacle.

Step S135, does the virtual line of sight and/or the virtual travel line touch an obstacle? If it is touched, go to step S136; if not, go to step S134.

Step S136 , update the obstacle bypass end point according to the image acquired during the traveling process, and adjust the subsequent obstacle bypass path according to the updated obstacle bypass end point, and then continue to perform step S134 .

The path planning of Example 2 is illustrated below with reference to FIG. 6 to FIG. 11 .

In FIGS. 6 to 11 , circles 1, 2, 3, 4, 5, and 6 represent different nodes in the obstacle-traversing process of the cleaning robot. The dotted circle represents the trajectory in the horizontal plane formed by the center points of the first virtual line of sight 21 and the second virtual line of sight 22 when the cleaning robot rotates in situ by 360°. Set, the initial coordinate of the current position of the cleaning robot is (0,0), and the coordinate of the end point of the obstacle after bypassing the obstacle is (D0,0). Among them, D0 is the straight-line distance when the cleaning robot is at the front and rear sides of the obstacle, where D0 is greater than D, for example, set D0=D+2*d2, D is the estimated value of the length of the obstacle 3, and d2 is the preset value to Leave a certain safety gap between the cleaning robot and obstacles.

In this example, the virtual line of sight that is in contact with the obstacle in the image is the second virtual line of sight 22, or those skilled in the art can select any other feasible virtual line of sight as the line of contact with the obstacle as needed For example, the first virtual sight line 21, the third virtual sight line 23, any virtual sight line located inside the first, second or third virtual sight line.

It can be understood by those skilled in the art that, since the cross-sections of most obstacles are not square or circular, the cleaning robot cannot accurately obtain the real data of the thickness (length) of the obstacles in the image. The estimated length of the obstacle 3 can only be determined by the actual width of the obstacle 3 , and the estimated length can be a preset multiple of the actual width of the obstacle 3 , such as 1 time or 2 times.

As shown in FIG. 6 , when the estimated length value is greater than or equal to the actual length value of the obstacle 3 , the cleaning robot only needs to plan a path 5 around the obstacle once. The obstacle circumvention path 5 planned at one time may be the circular arc shown in FIG. 7 , the elliptical arc shown in FIG. 8 , the polygon shown in FIG. 9 , the arcuate shape shown in FIG. 10 , and the like.

In FIG. 7 , the real width distance W of the obstacle 3 is calculated according to the pixel information of the obstacle 3 in the image, and then the estimated value D of the length of the obstacle 3 is estimated by W, and D0=D+2*d2 is set. Wherein, d2 is the distance from the second virtual line of sight 22 to the center of the cleaning robot. Finally, generate an arc with a diameter of D0, and connect the start point (0,0) and the end point (D0,0) together as the obstacle path 5.

In FIG. 8 , unlike in FIG. 7 , an elliptical arc connecting the start point (0, 0) and the end point (D0, 0) together is used as the path 5 around the obstacle. Among them, the long axis (first axis) of the elliptical arc is the line connecting the start point (0,0) and the end point (D0,0), and the short axis (second axis) of the elliptical arc is (W+2 *R0). Among them, R0 represents the farthest distance from the center point of the cleaning robot to the cleaning robot.

In Fig. 9, the barrier path 5 has 6 nodes connected in sequence: (0,0)(0,D0/6)(D0/3,D0/2), (2*D0/3,D0/2) , (D0,D0/6), (D0,0).

In FIG. 10 , the barrier bypass path 5 has four nodes connected in sequence: (0, 0), (0, D0/2), (D0, D0/2), (D0, 0).

As shown in FIG. 11 , when the estimated length value is smaller than the actual length value of the obstacle 3 , the cleaning robot needs to plan the path 5 around the obstacle many times. Specifically, when the obstacle in the image is in contact with the virtual line of sight, first determine the estimated value of the width and length of the obstacle according to the image, and then determine the preliminary path 5 for circumventing the obstacle in any of the methods shown in FIGS. 7 to 10 , and make The cleaning robot starts to travel along the obstacle detour path 5 .

When the virtual line of sight and/or the virtual travel line touches the obstacle 3 again, first increase the end point of the obstacle in the direction away from the starting point of the obstacle, for example, increase a distance d _L to become (D0+d _L ), And adjust the subsequent obstacle bypass path 5 according to the updated obstacle bypass end point, and make the cleaning robot continue to travel along the adjusted obstacle bypass path 5 . If the virtual line of sight and/or the virtual travel line touches the obstacle 3 again, move the end point of the obstacle around a distance d _L away from the starting point of the obstacle. Wherein, d _L can be any feasible value, such as 2cm, 5cm, 9cm, 11.5cm, etc.

Alternatively, when the virtual line of sight and/or the virtual travel line touches the obstacle 3 again, use the image captured during the traveling of the cleaning robot to recalculate the estimated length of the obstacle 3, and then update the end point of the obstacle, and according to the updated The end point of the obstacle bypassing adjusts the subsequent obstacle bypassing path 5 , and makes the cleaning robot continue to travel along the adjusted obstacle bypassing path 5 .

Based on the foregoing description, those skilled in the art can understand that the cleaning robot of the present disclosure can not only identify the obstacle ahead through the camera, but also can identify the relationship between the virtual travel line 1 and the virtual line of sight 2 and the obstacle in the image to guide the cleaning robot to perform fine obstacle or rapid obstacle bypass operations on the obstacle.

It should be noted that the first embodiment of the present disclosure is only a basic embodiment of the barrier bypassing method of the present disclosure, and other optional embodiments can also be obtained on the basis of the method, such as the following second embodiment.

In the second embodiment of the present disclosure:

As shown in FIG. 12 , different from the first embodiment, before step S110 , the barrier bypass method of this embodiment further includes:

In step S210, a calibration image of the calibration object is acquired through a camera.

As shown in FIG. 13 , in this embodiment, the calibration board 6 in the checkerboard format is first selected as the calibration object. The calibration plate 6 has the same width as the cleaning robot 4 , both of which are W0 , and the length L0 of the calibration plate 6 exceeds the imaging range of the image of the camera 41 .

Then, fix the cleaning robot 4 on the horizontal ground, and the specific position is shown in FIG. 13 : make the straight-line traveling direction of the cleaning robot 4 and the width direction of the calibration plate 6 perpendicular on the horizontal ground, and make the straight-line traveling centerline of the cleaning robot 4 Coinciding with the center line of the width of the calibration plate 6 , the front end of the body of the cleaning robot 4 is fixed at the starting position of the calibration plate 6 .

Then, the parameter variables such as the position, focal length, field of view, and imaging of the camera 41 are adjusted so that the image captured by the camera 41 satisfies the following conditions: the wide side w is consistent with the Y direction in FIG. 13 , and the high side h is consistent with FIG. 13 The X direction in the middle is the same, and the X axis in Fig. 13 bisects the wide side w of the image vertically, so that the calibration plate 6 in the image is left-right symmetrical about the X axis, and the origin of the XY coordinate axis in the image appears at the width of the lowermost edge of the image. 1/2 of edge w.

Then, the camera 41 is made to acquire the calibration image of the calibration plate 6 .

Finally, map the position and measurement information of the calibration plate 6 in the calibration image to the two-dimensional image space, and create a new mask layer for the calibration image to store the generated virtual travel line 1 and virtual line of sight 2 .

Step S220, determining the positions of the first line and the second line in the calibration image.

Wherein, the first line and the second line respectively exist on the calibration plate 6 , and the first line represents the virtual travel line 1 , and the second line represents the virtual sight distance 2 . Specifically, the first lines are the upper edge line (left edge line in the calibration image) and the lower edge line (right edge line in the calibration image) of the calibration plate 6 in FIG. 13 . The second line is the line parallel to the Y-axis of the calibration plate 6 in FIG. 13 . Normally, there are multiple second lines in the calibration plate 6 .

Step S230: Determine the virtual travel line according to the first line, and determine the virtual line of sight according to the second line.

利用PL0、PL1、KL数据在掩膜图层生成第一虚拟行进线11(左侧限位标志线Leftline)，第一虚拟行进线11与标定图像中标定板6的左侧边缘线重合。同样地，从标定图像中提取标定板6的右侧边缘线，计算直线的起点位置PR0(xr0,yr0)、终点位置PR1(xr1,yr1)和斜率

利用PR0、PR1、KR数据在掩膜图层生成第二虚拟行进线12(右侧限位标志线Rightline)，第二虚拟行进线12与标定图像中标定板6的右侧边缘线重合。进一步，在掩膜图层生成第三虚拟行进线13(中心标志线Centerline)，第三虚拟行进线13为标定图像左右方向上的垂直平分线。As shown in Figure 2 and Figure 13, the left edge line of the calibration plate 6 is extracted from the calibration image, and the starting point position PL0 (xl0, yl0), the end position PL1 (xl1, yl1) and the slope of the left edge line are calculated.

Using PL0, PL1, and KL data, a first virtual travel line 11 (left limit mark line Leftline) is generated in the mask layer. The first virtual travel line 11 coincides with the left edge line of the calibration plate 6 in the calibration image. Similarly, the right edge line of the calibration plate 6 is extracted from the calibration image, and the starting point position PR0 (xr0, yr0), the end position PR1 (xr1, yr1) and the slope of the straight line are calculated.

The second virtual travel line 12 (right limit mark line Rightline) is generated in the mask layer by using the data of PRO, PR1 and KR. The second virtual travel line 12 coincides with the right edge line of the calibration plate 6 in the calibration image. Further, a third virtual traveling line 13 (center mark line Centerline) is generated in the mask layer, and the third virtual traveling line 13 is a vertical bisector in the left-right direction of the calibration image.

It is not difficult to see from FIG. 2 and FIG. 13 that the area between the first virtual travel line 11 and the second virtual travel line 12 is the safety lane where the cleaning robot 4 travels in a straight line.

Further, according to the traveling speed of the cleaning robot and the actual needs, several virtual sight lines 2 are generated in the mask layer, such as the first virtual sight line 21, the second virtual sight line 22 and the The third virtual line of sight 23. Wherein, each virtual line of sight is perpendicular to the third virtual travel line 13 and is located between the first virtual travel line 11 and the second virtual travel line 12 . Preferably, the actual distance d1 from the bottom edge of the mask layer to the first virtual line of sight 21 after affine transformation is 5 cm to 15 cm, and the bottom edge of the mask layer to the second virtual line of sight The actual distance corresponding to the distance d2 of the line 22 after the affine transformation is 20cm～40cm, and the distance d3 from the bottom edge of the mask layer to the third virtual line of sight line 23 after the affine transformation corresponds to the actual distance of 50cm～40cm 100cm.

Among them, the virtual line of sight is the basis for judging the distance between the cleaning robot and the front.

Further, in order to prevent the cleaning robot from colliding with an obstacle, the scaling factor α of the virtual line of sight may also be set according to the walking speed of the cleaning robot. α can be dynamically adjusted according to the real-time linear travel speed of the cleaning robot. When the cleaning robot is at a normal speed, α=1, the larger the speed, the larger the α, and the smaller the speed, the smaller the α. Taking the distance d1' from the bottom edge of the mask layer to the first virtual travel line 11 as an example, d1'=α*d1.

After that, when step S120 is performed, the mask layer having the virtual travel line 1 and the virtual line of sight 2 can be superimposed on the image obtained in step S110, so as to generate the virtual travel line 1 and the virtual line of sight on the image. line 2.

Based on the foregoing description, those skilled in the art can understand that the calibration plate 6 in this embodiment enables the cleaning robot to generate a virtual travel line 1 and a virtual line of sight 2 for accurately detecting obstacles, which improves the ability of the cleaning robot to detect obstacles. Accuracy and reliability around obstacles.

In the third embodiment of the present disclosure:

As shown in FIG. 14 , different from the first embodiment and/or the second embodiment, the obstacle circumvention method of this embodiment further includes:

Step S310, in response to the turning of the cleaning robot, determine the turning trajectory of the cleaning robot.

As shown in Figure 15 and Figure 16, point O is the center point of the cleaning robot's turning trajectory; r is the turning radius of the cleaning robot's center point; d0 is the distance between the left and right driving wheels of the cleaning robot; VL is the left driving wheel VR is the driving speed of the right driving wheel; the linear velocity at the center point between the two driving wheels is VM=(VL+VR)/2; d is the right driving wheel more than the left driving wheel in Δt Distance traveled; θ3 is the change in heading angle of the cleaning robot. According to the geometric relationship, θ1=θ2=θ3 in FIG. 16 .

The heading angle of the cleaning robot:

Since θ1=θ2=θ3, the angular velocity w of the cleaning robot moving around the center of the circle:

The arc radius of the cleaning robot's steering motion:

Therefore, according to VR, VL, d0 and r, the current steering trajectory of the cleaning robot can be determined.

Step S320, adjusting the virtual travel line to extend along the steering trajectory.

As shown in FIG. 15 , the virtual travel line 1 is extended along the extending direction in which the steering trajectory extends, and each virtual line of sight is made perpendicular to the tangent of the steering trajectory of the drive wheels.

Based on the foregoing description, those skilled in the art can understand that the virtual travel line 1 and the virtual line of sight 2 in this embodiment can be adjusted with the steering angle of the cleaning robot, so that the cleaning robot can also pass through during the steering process. Virtual travel line 1 and virtual line of sight 2 are used to circumvent obstacles.

In the fourth embodiment of the present disclosure:

As shown in FIG. 16 , different from the first embodiment, the second embodiment and/or the third embodiment, the barrier bypassing method of this embodiment further includes:

Step S401, obstacle detection.

Specifically, during the traveling process of the cleaning robot, the image in front of the cleaning robot is continuously acquired by the camera, and then whether there is an obstacle in the image is continuously identified.

Step S402, whether there is a moving obstacle ahead.

Specifically, if an obstacle is detected in the image, the frame difference method is used to determine whether the obstacle is a moving obstacle. If not, go to step S403; if yes, go to step S404.

Step S403, update the path table.

Specifically, every preset duration (eg, 5 seconds, 7 seconds, 15 seconds, etc.) or preset distance (eg, 3cm, 5cm, 9cm, etc.) at intervals, and/or the cleaning robot is updated every time the posture of the cleaning robot changes The robot's path table. The path table is used to guide the cleaning robot.

Step S404, it is determined whether the moving obstacle is within the first virtual line of sight.

Specifically, it can be determined from the image acquired at the current moment whether the obstacle is located between the bottom edge of the image and the first virtual line of sight. If it is, go to step S405, if not, go to step S406.

Step S405, avoid obstacles, turn, stop or retreat in place.

Specifically, the cleaning robot can be stopped at the current position to wait for the moving obstacle to leave; the cleaning robot can also be made to retreat to avoid collision between the cleaning robot and the moving obstacle; the cleaning robot can also be turned and then continued to travel to Move the cleaning robot around moving obstacles and continue cleaning.

Step S406, it is determined whether the moving obstacle is within the second virtual line of sight.

Specifically, it can be determined from the image acquired at the current moment whether the obstacle is located between the first virtual line of sight and the second virtual line of sight. If it is, go to step S407, if not, go to step S408.

In step S407, the obstacle is avoided, and the travel is turned, stopped or traveled.

Specifically, the cleaning robot can be stopped at the current position to wait for the moving obstacle to leave; the cleaning robot can also be made to retreat to avoid collision between the cleaning robot and the moving obstacle; the cleaning robot can also be turned and then continued to travel to Move the cleaning robot around moving obstacles and continue cleaning.

Step S408, it is determined whether the moving obstacle is within the third virtual line of sight.

Specifically, it can be determined from the image acquired at the current moment whether the obstacle is located between the second virtual line of sight and the third virtual line of sight. If it is, go to step S409, if not, go to step S403.

Step S409, motion evaluation, stop or go.

Specifically, the moving state and moving speed of the obstacle are first evaluated to determine whether the cleaning robot will collide with the moving obstacle according to the current walking direction and speed. If no collision occurs, the cleaning robot will continue to travel. , which stops the cleaning robot from traveling if a collision will occur.

Based on the foregoing description, those skilled in the art can understand that the obstacle circumvention method in this embodiment can also identify moving obstacles, and evaluate the moving obstacles, so that the moving obstacles can affect the cleaning robot's traveling. When , adjust the traveling strategy of the cleaning robot to prevent the cleaning robot from colliding with the moving obstacle, and at the same time, it can continue to clean the corresponding area after the moving obstacle leaves. Therefore, the obstacle circumvention method of this embodiment can also enable the cleaning robot to clean the area where the moving obstacle stays.

In the fifth embodiment of the present disclosure:

As shown in FIG. 18 , the present disclosure also provides a cleaning robot. The cleaning robot includes a processor at the hardware level, optionally a memory and a bus, and the cleaning robot is also allowed to include hardware required by other services.

The memory is used for storing execution instructions, and the execution instructions are specifically computer programs that can be executed. Further, the memory may include memory and non-volatile memory and provide execution instructions and data to the processor. Exemplarily, the memory may be a high-speed random-access memory (Random-Access Memory, RAM), and the non-volatile memory may be at least one disk storage.

Among them, the bus is used to interconnect the processor, memory and network interface. The bus may be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, and the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one bidirectional arrow is shown in FIG. 18, but this does not mean that there is only one bus or one type of bus.

In a feasible implementation manner of the above cleaning robot, the processor may first read the corresponding execution instructions from the non-volatile memory into the memory before running, or may first obtain the corresponding execution instructions from other devices before running . When the processor executes the execution instructions stored in the memory, the processor can implement the barrier bypassing method in any one of the foregoing barrier bypassing method embodiments of the present disclosure.

Those skilled in the art can understand that the above-mentioned method for bypassing the barrier can be applied to a processor, and can also be implemented by a processor. Illustratively, a processor is an integrated circuit chip capable of processing signals. During the process of the processor executing the above-mentioned method for bypassing the barrier, each step of the above-mentioned method for bypassing the barrier may be completed by an integrated logic circuit in the form of hardware or an instruction in the form of software in the processor. Further, the above-mentioned processor may be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU), a network processor (NetworkProcessor, NP), a digital signal processor (Digital SignalProcessor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit) , ASIC), field programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, microprocessors and any other conventional processors.

Those skilled in the art can also understand that, the steps of the above embodiments of the obstacle bypassing method of the present disclosure may be executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, and other storage media mature in the art. The storage medium is located in the memory, and after the processor reads the information in the memory, the processor completes the execution of the steps in the above embodiments of the barrier bypassing method in combination with its hardware.

So far, the description of the technical solutions of the present disclosure has been completed with reference to the accompanying drawings and in conjunction with the above embodiments.

It should be noted that, in order to highlight the differences between the above-mentioned embodiments of the present disclosure, the above-mentioned embodiments of the present disclosure are arranged and described in a juxtaposed manner and/or in a progressive manner , and the following embodiments only focus on the differences between them and other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For example, for the device/product embodiment, since the device/product embodiment is basically similar to the method embodiment, the description is relatively simple, and for related details, please refer to the description of the corresponding part of the method embodiment.

The above descriptions are merely embodiments of the present disclosure, and are not intended to limit the present disclosure. Various modifications and variations of the present disclosure will occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the technical principles of the present disclosure shall fall within the protection scope of the present disclosure.

Claims (10)

1. a method for circumventing an obstacle of a cleaning robot, the cleaning robot is provided with a camera, and it is characterized in that, the method for circumventing an obstacle comprises: Obtain an image in front of the cleaning robot through the camera; A virtual travel line and a virtual line of sight are generated on the image. The virtual travel line on the image corresponds to the virtual line formed by the left and right edges of the cleaning robot extending forward in the actual environment. The virtual line of sight corresponds to the virtual line at the preset safety distance in front of the cleaning robot in the actual environment; Controlling the cleaning robot to walk around the obstacle with the obstacle located on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint condition in the image. 2 . The method for circumventing an obstacle according to claim 1 , wherein the obstacle is located on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint. 3 . condition, control the cleaning robot to walk around the obstacle, including: When the obstacle in the image is in contact with the virtual line of sight, the cleaning robot is controlled to go around the obstacle with the tangent of the obstacle and the virtual travel line in the image as a constraint condition obstacle walking. 3 . The method for circumventing obstacles according to claim 1 , wherein the obstacle in the image is located on the side of the virtual travel line and the virtual line of sight away from the cleaning robot as a constraint. 4 . condition, control the cleaning robot to walk around the obstacle, including: When the obstacle in the image is in contact with the virtual line of sight, determining the estimated value of the width and the length of the obstacle according to the image; Determine the obstacle-passing end point of the cleaning robot according to the estimated length of the obstacle, and the obstacle-passing end point and the current position of the cleaning robot are respectively located on opposite sides of the obstacle; Plan a path around the obstacle according to the current position and the end point of the obstacle; causing the cleaning robot to walk along the obstacle course, and when the virtual line of sight and/or the virtual travel line touches the obstacle, update the obstacle according to the image acquired during the journey end point, and adjust the subsequent obstacle bypass path according to the updated obstacle bypass end point. 4 . The method for bypassing obstacles according to claim 3 , wherein the planning of a bypassing path according to the current position and the end point of the obstacle bypassing comprises: 5 . The distance between the current position and the end point of the obstacle is determined, and the diameter is the distance and the arc connecting the current position and the end of the obstacle is used as the obstacle path. 5 . The method for bypassing obstacles according to claim 3 , wherein the planning of a bypassing path according to the current position and the end point of the obstacle bypassing comprises: 5 . Taking the connection between the current position and the end point of the obstacle as the first axis; determining a second axis perpendicular to the first axis according to the width of the obstacle and the size of the cleaning robot; The long axis and the short axis are respectively the first axis and the second axis, and the elliptic arc connecting the current position and the end point of the obstacle is taken as the obstacle bypass path. 6 . The method for bypassing obstacles according to claim 3 , wherein the planning of the obstacle bypassing path according to the current position and the end point of the obstacle bypassing comprises: 6 . determining a plurality of intermediate points between the current position and the end point of the obstacle, the intermediate points are located outside the obstacle; A line connecting the current position, the intermediate point, and the end point of the obstacle bypass in sequence is used as the obstacle bypass path. 7. The method for bypassing obstacles according to any one of claims 1-6, wherein the generating a virtual travel line and a virtual line of sight on the image comprises: The virtual travel line and the virtual line of sight are added to the image according to the positions in which the predetermined virtual travel line and the virtual line of sight are mapped to the calibration image captured by the camera. 8. The method for bypassing a barrier according to claim 7, wherein the method for bypassing the barrier further comprises: Acquire a calibration image of the calibration object through the camera; the calibration object has a first line representing the virtual travel line and a second line representing the virtual line of sight; The positions of the first line and the second line in the calibration image are determined. 9. The method for bypassing a barrier according to any one of claims 1-6, wherein the method for bypassing the barrier further comprises: determining a steering trajectory of the cleaning robot in response to the cleaning robot turning; The virtual travel line is adjusted to extend along the steering trajectory. 10. A cleaning robot, characterized in that the cleaning robot comprises a processor, a memory, and execution instructions stored on the memory, the execution instructions being configured to enable the cleaning when executed by the processor The robot executes the obstacle circumvention method described in any one of claims 1 to 9.

Images