Obstacle identification method and device, electronic equipment and storage medium

Abstract

This disclosure provides an obstacle recognition method, apparatus, electronic device, and storage medium. The method includes: acquiring a laser image of a target area; extracting candidate laser stripes from the laser image; obtaining the theoretical position of a reference laser line in the laser image; filtering valid laser stripes from the candidate laser stripes based on the theoretical position; and obtaining the position of the obstacle based on the position of the valid laser stripes in a world coordinate system. This method, by filtering candidate laser stripes from the theoretical position of the reference laser line in the laser image, can improve the accuracy of valid laser stripe recognition, thereby improving the accuracy of obstacle recognition.

Description

Technical Field

[0001] This invention relates to the field of obstacle recognition technology, and in particular to an obstacle recognition method, device, electronic device, and storage medium. Background Technology

[0002] During cleaning tasks, mobile robots need to accurately identify the relative positions of obstacles to the robot and mark the obstacles on a 2D grid map to achieve obstacle avoidance. The environment in which mobile robots operate contains a large number of obstacles with unique materials and shapes. Obstacles with reflective, light-absorbing, or low-profile properties typically place higher demands on the mobile robot's environmental perception capabilities. Summary of the Invention

[0003] This invention provides an obstacle recognition method, device, mobile robot electronic device, and storage medium to improve the accuracy of obstacle recognition.

[0004] According to a first aspect of the present invention, an obstacle recognition method is provided, comprising:

[0005] Acquire laser images of the target area;

[0006] Extract candidate laser stripes from the laser image;

[0007] Obtain the theoretical position of the reference laser line in the laser image;

[0008] Based on the theoretical position, effective laser beams are selected from the candidate laser beams;

[0009] The position of the obstacle is obtained based on the position of the effective laser beam in the world coordinate system.

[0010] In some embodiments, obtaining the theoretical position of the reference laser line in the laser image includes:

[0011] Obtain the light plane equation of the laser in the camera coordinate system;

[0012] Obtain the equation of the reference plane in the camera coordinate system;

[0013] The theoretical position is obtained by obtaining the intersection expression of the equation of the light plane and the equation of the reference plane.

[0014] In some embodiments, obtaining the equation of the reference plane in the camera coordinate system specifically includes:

[0015] Based on the transformation matrix T from the camera coordinate system to the world coordinate system wc Convert the coordinates of multiple points on the reference plane in the world coordinate system to coordinates in the camera coordinate system;

[0016] The equation of the reference plane in the camera coordinate system is established based on the coordinates of the multiple points after transformation.

[0017] In some embodiments, for a mobile robot, the transformation matrix T from the camera coordinate system to the world coordinate system is... wc The methods for obtaining it include:

[0018] Obtain the transformation matrix T between the mobile robot coordinate system and the camera coordinate system. RC ;

[0019] The current attitude T of the mobile robot in the world coordinate system is obtained through the inertial measurement unit. WI ;

[0020] Obtain the transformation matrix T between the inertial measurement unit coordinate system and the mobile robot coordinate system. RI ;

[0021] Calculate the transformation matrix T from the camera coordinate system to the world coordinate system. wc :

[0022]

[0023] In some embodiments, obtaining the intersection expression of the light plane equation and the reference plane equation to obtain the theoretical position specifically includes: selecting two points P of the reference laser line in the camera coordinate system. a =(x a y a , z a ) and P b =(x b y b , z b Let z a =1,z b =2, substituting the equation of the light plane and the equation of the reference plane, we get x. a y a x b and y b ;

[0024] Based on x a and v a Find P a coordinates in pixel coordinate system (u) a v a );

[0025] Based on x b and y b Find P b coordinates in pixel coordinate system (u) b v b );

[0026] Establish the intersection expression:

[0027] A fl x+B fl y+C fl z = 0

[0028] Based on (u a v a ) and (u b v b The parameters of the intersection line expression are obtained.

[0029] In some embodiments, acquiring laser images of the target area includes:

[0030] A horizontal laser line is emitted toward the target area, wherein the angle between the horizontal laser line and the reference plane is greater than 0° and less than 90°.

[0031] Acquire a laser image of the target area.

[0032] In some embodiments, it also includes:

[0033] Obtain the background image of the target area;

[0034] After acquiring the laser image of the target area, the method further includes:

[0035] Background subtraction is performed on the laser image based on the background image.

[0036] In some embodiments, for a mobile robot, before performing background subtraction on the laser image based on the background image, the method further includes:

[0037] Acquire motion information of the mobile robot;

[0038] Motion compensation is performed on the background image based on the motion information.

[0039] In some embodiments, extracting candidate laser streaks from the laser image specifically includes:

[0040] Pixel regions with gray values ​​greater than a preset gray value are extracted from the laser image and used as candidate laser beams.

[0041] In some embodiments, selecting effective laser stripes from the candidate laser stripes based on the theoretical position specifically includes:

[0042] Obtain the distance between each candidate laser stripe and the theoretical position;

[0043] The candidate laser beam with the smallest distance is taken as the effective laser beam.

[0044] In some embodiments, determining the position of the obstacle based on the position of the effective laser beam in the world coordinate system specifically includes:

[0045] The position of the center pixel of the effective laser beam in the world coordinate system is obtained to determine the position of the obstacle.

[0046] According to a second aspect of the present invention, an obstacle recognition device is provided, comprising:

[0047] The acquisition module is used to acquire laser images of the target area;

[0048] The extraction module is used to extract candidate laser streaks from the laser image;

[0049] The acquisition module is used to acquire the theoretical position of the reference laser line in the laser image;

[0050] The filtering module is used to filter out effective laser beams from the candidate laser beams based on the theoretical position;

[0051] The conversion module is used to obtain the position of the obstacle based on the position of the effective laser beam in the world coordinate system.

[0052] According to a third aspect of the present invention, a mobile robot is provided, comprising:

[0053] The robot itself;

[0054] A horizontal laser module is mounted on the robot body. The horizontal laser module includes an infrared laser emitter and a camera. The horizontal laser module is used to acquire laser images of the target area and send them to the control module.

[0055] An inertial measurement unit, located within the robot body, is used to acquire the mobile robot's attitude in the world coordinate system and send it to the control module;

[0056] The control module is used to execute the obstacle recognition method described in any of the above embodiments.

[0057] According to a fourth aspect of the present invention, an electronic device is provided, comprising:

[0058] Processor; and

[0059] Stored program memory,

[0060] The program includes instructions that, when executed by the processor, cause the processor to perform the method described in any of the above embodiments.

[0061] According to a fifth aspect of the present invention, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the method described in any of the above embodiments.

[0062] The obstacle recognition method provided in this disclosure improves the accuracy of effective laser stripe recognition by filtering candidate laser stripes from those with reference to the theoretical position of the laser line in the laser image, thereby improving the accuracy of obstacle recognition. Attached Figure Description

[0063] Figure 1 A flowchart of an obstacle recognition method provided in this disclosure embodiment;

[0064] Figure 2 A schematic diagram of a mobile robot provided in an embodiment of this disclosure;

[0065] Figure 3 This is a schematic diagram of motion compensation provided in an embodiment of this disclosure;

[0066] Figure 4 This is a laser image when there are no obstacles.

[0067] Figure 5 This is a laser image with obstacles present.

[0068] Figure 6 This is a schematic diagram of an obstacle recognition device provided in an embodiment of the present disclosure. Detailed Implementation

[0069] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0070] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0071] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0072] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0073] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0074] Figure 1 This is a flowchart illustrating an obstacle recognition method provided in an embodiment of this disclosure. Figure 1 As shown in the figure, this disclosure provides an obstacle recognition method, including the following steps:

[0075] S101: Acquire laser images of the target area.

[0076] S102: Extract candidate laser stripes from the laser image;

[0077] S103: Obtain the theoretical position of the reference laser line in the laser image;

[0078] S104: Selecting effective laser stripes from candidate laser stripes based on theoretical positions;

[0079] S105: Obtain the position of the obstacle based on the position of the effective laser beam in the world coordinate system.

[0080] This embodiment provides an obstacle recognition method that filters candidate laser beams by referencing the theoretical position of the laser line in the laser image. This effectively solves the problem of reflections and refractions in the scene affecting the laser image, thereby improving the accuracy of effective laser beam recognition and thus improving the accuracy of obstacle recognition.

[0081] Specifically, the ground can be used as a reference plane, and the ground line can be used as a reference laser line.

[0082] In some embodiments, the obstacle recognition method is used for a mobile robot, which may be a cleaning robot. The mobile robot includes:

[0083] The robot itself;

[0084] A horizontal laser module, mounted on the robot body, includes an infrared laser emitter and a camera. The horizontal laser module is used to acquire laser images of the target area and send them to the control module. In this embodiment, the target area is the target movement area of ​​the robot body. The infrared laser emitter emits a horizontal laser line in the direction of the robot body's movement. The angle between the plane of the horizontal laser line and the reference plane is greater than 0° and less than 90°, and can be 45°, 50°, or 60°. When the horizontal laser line hits an obstacle, it changes the position of the laser stripe in the laser image. Utilizing this phenomenon, through imaging in the camera, effective laser stripes representing obstacles can be effectively found in the laser image. The position of the effective laser stripe in the camera coordinate system can be used to calculate the position information of the obstacle surface in the world coordinate system.

[0085] An inertial measurement unit, housed within the robot body, is used to acquire the mobile robot's attitude in the world coordinate system and send it to the control module; the control module is used to execute the obstacle recognition method provided in any embodiment.

[0086] This embodiment effectively avoids the influence of ambient light by actively emitting a horizontal line laser using an infrared laser emitter. The intersection of the horizontal line laser's light plane and the reference plane is close to the mobile robot, reducing secondary reflections and refractions and preventing adverse effects on the subsequent extraction of effective laser beams. Furthermore, compared to vertical line lasers, it creates a smaller obstacle avoidance blind zone, effectively identifying low-lying obstacles at close range.

[0087] Figure 2 This is a schematic diagram of a mobile robot provided in an embodiment of this disclosure. Figure 2 As shown, in actual use, the world coordinate system is first defined as follows: The coordinate system of the mobile robot is The coordinate system of the inertial measurement unit is Camera coordinate system is

[0088] Load camera intrinsic and extrinsic parameters, including the mapping from the camera coordinate system to the pixel coordinate system. and the transformation matrix from the camera coordinate system to the robot coordinate system When the robot is not moving, the robot's coordinate system is the same as the world coordinate system.

[0089] The equation of the laser beam plane in the camera coordinate system is A.laser x+B laser y+C laser z+D laser =0.

[0090] The equation of the reference plane in the camera coordinate system is A. ref x+B ref y+C ref z+D ref =0.

[0091] In the world coordinate system, select three points on the reference plane: Transformed to camera coordinate system Therefore, the parameters of the reference plane equation in the camera coordinate system can be obtained as follows:

[0092] A ref =(y2-y1)·(z3-z1)-(y3-y1)·(z2-z1)

[0093] B ref =(z2-z1)·(x3-x1)-(z3-z1)·(x2-x1)

[0094] C ref =(x2-x1)·(y3-y1)-(x3-x1)·(y2-y1)

[0095] D ref =0-(A ref ·x1+B ref ·y1+C ref ·z1)

[0096] The position of the intersection line of the two planes in the camera coordinate system is determined by the equations of the reference plane and the light plane in the camera coordinate system, which is the theoretical position expression of the reference laser line in the laser image.

[0097] In the camera coordinate system, select two points P that fall on the theoretical position expression of the reference laser line. a =(x a y a , z a ) and P b =(x b y b , z b Let z a =1,z b =2. With P a For example, the following equations are satisfied.

[0098] A laser x a +B laser y a +Claser z a +D laser =0

[0099] A ref x a +B ref y a +C ref z a +D ref =0

[0100] It can be obtained.

[0101]

[0102]

[0103] Similarly, P b It can also be obtained in the same way.

[0104] b) Calculate P a and P b In the pixel coordinate system, the line connecting two points determines the theoretical position expression A of the reference laser line in the pixel coordinate system. fl x+B fl y+C fl z = 0:

[0105] With P a For example, to obtain the coordinates of the point in the pixel coordinate system (u a v a )

[0106]

[0107] Similarly, we can find P. b coordinates in pixel coordinate system (u) b v b Connect the two points to determine the parameters of the theoretical position expression of the reference laser line:

[0108] A fl =v b -u b B fl =u a -u b C fl =(v a -v b )*u a +(u b -u a )*u b .

[0109] In some embodiments, after the mobile robot moves, the mobile robot's coordinate system differs from the world coordinate system, and the transformation matrix T from the camera coordinate system to the world coordinate system... wc The methods for obtaining it include:

[0110] Obtain the transformation matrix T between the mobile robot coordinate system and the camera coordinate system. RC ;

[0111] The attitude T of the mobile robot in the world coordinate system at the current moment is obtained through the inertial measurement unit. WI ;

[0112] Obtain the transformation matrix T between the inertial measurement unit coordinate system and the mobile robot coordinate system. RI ;

[0113] The transformation relationship between the robot's coordinate system and the world coordinate system at the current moment is obtained as follows:

[0114] Therefore, the transformation matrix T from the camera coordinate system to the world coordinate system can be calculated. wc :

[0115]

[0116] The obstacle recognition method provided in this embodiment can correct the transformation matrix from the camera coordinate system to the world coordinate system in real time through the inertial measurement unit to adapt to the movement of the mobile robot.

[0117] In some embodiments, step S101 specifically includes:

[0118] A horizontal laser line is emitted toward the target area, with the angle between the horizontal laser line and the reference plane being greater than 0° and less than 90°.

[0119] Acquire laser images of the target area.

[0120] Also includes:

[0121] Acquire a background image of the target area; the background image is acquired with the horizontal laser line turned off.

[0122] After acquiring the laser image of the target area, the following steps are also included:

[0123] Background subtraction is performed on the laser image based on the background image.

[0124] The obstacle recognition method provided in this embodiment performs background subtraction by illuminating and de-illuminating the horizontal line laser, which can filter out the influence of ambient light and improve the accuracy of obstacle recognition.

[0125] Figure 3 This is a schematic diagram of motion compensation provided in an embodiment of this disclosure. For example... Figure 3 As shown, when the robot has an angular velocity, due to the different times when the horizontal line laser is lit and turned off, there is a pixel misalignment between the laser image and the background image in the horizontal direction. Therefore, before performing background subtraction on the laser image based on the background image, motion compensation for the background image is also performed using the rotation angle measured by the inertial measurement unit.

[0126] The obstacle recognition method provided in this embodiment of the invention takes into account the possible bumps that may occur during the movement of the mobile robot, and uses an inertial measurement unit to acquire motion data. On the one hand, it is used to correct the position of the line laser light plane during the movement; on the other hand, it performs motion compensation on the background image that needs to be used for background subtraction, thereby realizing the alignment of the background image and the laser image.

[0127] like Figure 3 As shown, when the mobile robot circles z R When the axis is rotated clockwise by an angle θ, it is equivalent to the y-axis of point P relative to the camera coordinate system. C The axis is rotated clockwise by an angle θ. For the image, the same point is imaged from point p to point p′ in the pixel coordinate system. When the background image is captured first at time t and then the laser image is captured at time t′, the pixel coordinates of point P in the background image are p = (u, v). Then its pixel coordinates in the laser image are p′ = (u′, v′), which can be calculated as:

[0128]

[0129] In some embodiments, step S102 specifically includes: extracting pixel regions with pixel gray values ​​greater than a preset gray value from the laser image after background subtraction as candidate laser light stripes.

[0130] Specifically, each column of pixels in the laser image is traversed, and pixel regions with a width greater than a preset width and a brightness greater than a preset brightness are extracted as candidate laser stripes.

[0131] Figure 4 This is a laser image when there are no obstacles. Figure 5 This is a laser image with obstacles present. For example... Figure 4 , 5 As shown, when a single-line laser beam is emitted, only one line laser beam can be formed on a segment of a column; the remaining bright spots are reflections or noise. Therefore, only one candidate laser beam can exist on the same column. The closer the candidate laser beam is to the theoretical position of the reference laser line, the higher the probability that it is a valid laser beam. Simultaneously, the larger the grayscale value of the center pixel, the higher the probability that the candidate laser beam is a valid laser beam. In some embodiments, step S104 specifically includes: obtaining the distance between each candidate laser beam and its theoretical position;

[0132] Obtain the grayscale value of the center pixel of each candidate laser stripe;

[0133] A score for each candidate laser stripe is calculated based on distance and grayscale value;

[0134] The candidate laser stripe with the highest score is selected as the valid laser stripe.

[0135] Among them, the higher the grayscale value, the higher the score; the smaller the distance, the higher the score.

[0136] In some embodiments, step S105 specifically includes:

[0137] After determining the center pixel point p = (u, v) of the effective laser stripe, first recover the obstacle point cloud coordinates P in the camera coordinate system corresponding to this pixel point. C = (x, y, z):

[0138] Based on the mapping from the camera coordinate system to the pixel coordinate system The following constraints can be established:

[0139]

[0140]

[0141] Meanwhile, points originating from the line laser plane must fall on the line laser plane. Therefore, based on the equation of the line laser plane in the camera coordinate system, the following constraints can be established:

[0142] A laser x+B laser y+C laser z+D lascr =0,

[0143] Therefore, we can solve for:

[0144]

[0145]

[0146]

[0147] To obtain the obstacle point cloud coordinates P in the camera coordinate system C After (x, y, z), the transformation matrix from the camera coordinate system to the mobile robot coordinate system is used. And the current pose of the mobile robot in the world coordinate system The coordinates in the mobile robot's coordinate system can be recovered:

[0148]

[0149] Figure 6This is a schematic diagram of an obstacle recognition device provided in an embodiment of this disclosure. Figure 6 As shown, based on the same concept, an exemplary embodiment of this disclosure also provides an obstacle recognition device, including:

[0150] Acquisition module 1 is used to acquire laser images of the target area;

[0151] Extraction module 2 is used to extract candidate laser streaks from the laser image;

[0152] Module 3 is used to obtain the theoretical position of the reference laser line in the laser image;

[0153] Module 4 is used to select effective laser stripes from candidate laser stripes based on their theoretical positions;

[0154] The conversion module 5 is used to obtain the position of the obstacle based on the position of the effective laser light stripe in the world coordinate system.

[0155] Exemplary embodiments of this disclosure also provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the electronic device to perform a method according to an embodiment of this disclosure.

[0156] Exemplary embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to embodiments of this disclosure.

[0157] It should be understood that the specific embodiments described above are merely illustrative or explanatory of the principles of this disclosure and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of this disclosure should be included within the protection scope of this disclosure. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. An obstacle recognition method, characterized in that, include: Acquire laser images of the target area; Extract candidate laser stripes from the laser image; Obtain the theoretical position of the reference laser line in the laser image; Based on the theoretical position, effective laser beams are selected from the candidate laser beams; The position of the obstacle is obtained based on the position of the effective laser beam in the world coordinate system; Obtaining the theoretical position of the reference laser line in the laser image includes: Obtain the light plane equation of the laser in the camera coordinate system; Obtain the equation of the reference plane in the camera coordinate system; The theoretical position is obtained by obtaining the intersection expression of the equation of the light plane and the equation of the reference plane.

2. The obstacle recognition method according to claim 1, characterized in that, Obtaining the equation of the reference plane in the camera coordinate system specifically includes: Based on the transformation matrix Twc from the camera coordinate system to the world coordinate system, the coordinates of multiple points on the reference plane in the world coordinate system are transformed into coordinates in the camera coordinate system. The equation of the reference plane in the camera coordinate system is established based on the coordinates of the multiple points after transformation.

3. The obstacle recognition method according to claim 2, characterized in that, For mobile robots, the method for obtaining the transformation matrix Twc from the camera coordinate system to the world coordinate system includes: Obtain the transformation matrix T between the mobile robot coordinate system and the camera coordinate system. RC ; The current attitude of the mobile robot in the world coordinate system is obtained through the inertial measurement unit. ; Obtain the transformation matrix between the inertial measurement unit coordinate system and the mobile robot coordinate system. ; Calculate the transformation matrix Twc from the camera coordinate system to the world coordinate system: 。 4. The obstacle recognition method according to claim 1, characterized in that, Obtaining the intersection expression of the light plane equation and the reference plane equation to arrive at the theoretical position specifically includes: selecting two points of the reference laser line in the camera coordinate system. and ,make Substituting the equations for the light plane and the reference plane, we obtain xa, ya, xb, and yb; The coordinates of Pa in the pixel coordinate system are obtained based on xa and ya. ; The coordinates of Pb in the pixel coordinate system are obtained based on xb and yb. ; Establish the intersection expression: based on and Obtain the parameters of the intersection line expression.

5. The obstacle recognition method according to claim 1, characterized in that, The acquisition of laser images of the target area includes: A horizontal laser line is emitted toward the target area, wherein the angle between the horizontal laser line and the reference plane is greater than 0° and less than 90°. Acquire a laser image of the target area.

6. The obstacle recognition method according to claim 5, characterized in that, Also includes: Obtain the background image of the target area; After acquiring the laser image of the target area, the method further includes: Background subtraction is performed on the laser image based on the background image.

7. The obstacle recognition method according to claim 6, characterized in that, For mobile robots, before performing background subtraction on the laser image based on the background image, the method further includes: Acquire motion information of the mobile robot; Motion compensation is performed on the background image based on the motion information.

8. The obstacle recognition method according to claim 1, characterized in that, Extracting candidate laser streaks from the laser image specifically includes: Pixel regions with gray values ​​greater than a preset gray value are extracted from the laser image and used as candidate laser beams.

9. The obstacle recognition method according to claim 1, characterized in that, Selecting effective laser stripes from the candidate laser stripes based on the theoretical position specifically includes: Obtain the distance between each candidate laser stripe and the theoretical position; The candidate laser beam with the smallest distance is taken as the effective laser beam.

10. The obstacle recognition method according to claim 1, characterized in that, The location of the obstacle is obtained based on the position of the effective laser beam in the world coordinate system, specifically including: The position of the center pixel of the effective laser beam in the world coordinate system is obtained to determine the position of the obstacle.

11. An obstacle recognition device, characterized in that, include: The acquisition module is used to acquire laser images of the target area; The extraction module is used to extract candidate laser streaks from the laser image; The acquisition module is used to acquire the theoretical position of the reference laser line in the laser image; The filtering module is used to filter out effective laser beams from the candidate laser beams based on the theoretical position; The conversion module is used to obtain the position of the obstacle based on the position of the effective laser beam in the world coordinate system; The acquisition module is used to acquire the light plane equation of the laser in the camera coordinate system; acquire the reference plane equation in the camera coordinate system; and acquire the intersection expression of the light plane equation and the reference plane equation to obtain the theoretical position.

12. A mobile robot, characterized in that, include: The robot itself; A horizontal laser module is mounted on the robot body. The horizontal laser module includes an infrared laser emitter and a camera. The horizontal laser module is used to acquire laser images of the target area and send them to the control module. An inertial measurement unit, located within the robot body, is used to acquire the mobile robot's attitude in the world coordinate system and send it to the control module; A control module for executing the obstacle recognition method according to any one of claims 1-10.

13. An electronic device, comprising: processor; as well as Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-10.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

Images