Transparent obstacle mark construction method and system and self-moving robot

Abstract

The invention discloses a transparent obstacle mark construction method and system and a self-moving robot. The method comprises the following steps: acquiring a reflected light signal received by a laser radar; determining whether a transparent obstacle exists in the environment to be detected or not according to the intensity value of the reflected light signal; and if it is determined that the transparent obstacle exists, constructing a preset mark representing the transparent obstacle on a corresponding area of the target map according to the distance value corresponding to the reflected light signal. Whether the transparent obstacle exists in the environment to be detected or not is judged according to the intensity value of the reflected light signal, and if yes, the preset mark representing the transparent obstacle is constructed on the corresponding area of the map according to the distance value corresponding to the reflected light signal, so that the problems that time and labor are wasted by manual marking in related technologies, and time and labor are wasted are solved. According to the method, the problems that in the prior art, the marking precision cannot be guaranteed and the like are solved, the labor cost is saved, transparent obstacle marking errors caused by human errors are reduced, the map precision is improved, and the safety of the self-moving robot is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of transparent object identification marking, and in particular to a transparent obstacle marking construction method, system and self-moving robot. Background Art

[0002] At present, laser navigation robots need to rely on 2D maps for positioning and navigation to complete specific tasks. The 2D maps generated by LiDAR mostly use probabilistic grid maps. Each grid represents a small area in the actual scene, and the grid value represents the possibility of obstacles in the area. Robots can use the data in these grids to complete navigation, obstacle avoidance and other functions.

[0003] Generally speaking, the ranging effect of lidar for transparent objects is relatively average, mainly manifested in inaccurate ranging, such as the inability to return the ranging value or the laser beam passing through the transparent object to return the ranging value of the non-transparent object behind the transparent object. This makes it difficult for transparent obstacles such as glass windows and glass walls to generate high-confidence grid points at the corresponding positions on the map, causing the robot to mistakenly identify transparent obstacles as movable areas when completing navigation, obstacle avoidance and other tasks, and collide with the transparent obstacles, causing danger.

[0004] Therefore, in order for the robot to work safely, it is necessary to construct transparent obstacle markings with high confidence on the map. At present, the construction of transparent obstacle markings in the working area generally adopts the method of manual auxiliary marking, requiring the staff to draw specific marks on the corresponding areas of transparent obstacles on the map by comparing the environment and the map after the map is established, so that the robot can adjust the movement trajectory according to these manually added marks when navigating or avoiding obstacles. However, the manual marking method not only requires manpower investment in the early stage for marking, but also the accuracy of manual marking cannot be guaranteed. If there is a deviation in the marking, it will cause errors in the robot's related functions. Summary of the invention

[0005] In view of the above problems, the present application provides a transparent obstacle marking construction method, system and self-moving robot to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for constructing a transparent obstacle mark, the method comprising:

[0007] Acquire the reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected;

[0008] According to the intensity value of the reflected light signal, determine whether there is a transparent obstacle in the environment to be detected;

[0009] If it is determined that there is a transparent obstacle, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the lidar and the transparent obstacle.

[0010] In a possible implementation of the present application, before obtaining a reflected light signal received by a laser radar, the method includes:

[0011] When the self-propelled robot moves in the environment to be detected, the laser radar is controlled to emit a laser beam in the horizontal direction.

[0012] In a possible implementation of the present application, determining whether there is a transparent obstacle in the environment to be detected according to the intensity value of the reflected light signal includes:

[0013] If the intensity value of the reflected light signal is greater than or equal to a preset first intensity threshold, it is determined that there is a transparent obstacle in the environment to be detected.

[0014] In a possible implementation of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, and then the method further includes:

[0015] For two adjacent preset marks on the target map, obtaining the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks;

[0016] If the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks is less than a preset second intensity threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0017] In a possible implementation of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, and then the method further includes:

[0018] For two adjacent preset marks on the target map, if the distance between the two adjacent preset marks is less than a preset distance threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0019] In a possible implementation of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, and then the method further includes:

[0020] For a preset mark on the target map, edge extraction is performed on pixel points within a preset neighborhood range of the preset mark to expand the preset mark.

[0021] In a possible implementation of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, and then the method further includes:

[0022] For the preset mark on the target map, if the distance value corresponding to the reflected light signal is greater than the distance between the preset mark and the laser radar, the preset mark is retained.

[0023] In a possible implementation of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to a distance value corresponding to the reflected light signal, including:

[0024] The laser flight time is obtained according to the reception time of the reflected light signal received by the laser radar and the emission time of the emitted laser beam;

[0025] Determine the distance value based on the laser flight time;

[0026] Build preset markers on the corresponding area of ​​the target map according to the distance value.

[0027] In a second aspect, the present application further provides a transparent obstacle marking construction system, the transparent obstacle marking construction system comprising a control end and a self-moving robot in communication connection with the control end, the self-moving robot being equipped with a laser radar;

[0028] The control end is used to control the operation of the laser radar and the self-propelled robot, and implement the transparent obstacle marking construction method in the first aspect or any possible implementation method of the first aspect.

[0029] In a third aspect, the present application also provides a self-moving robot, which includes a memory and a processor, the memory being used to store a computer program, and when the computer program is executed by the processor, it is used to implement the transparent obstacle marking construction method in the first aspect or any possible implementation method of the first aspect.

[0030] From the above content, it can be concluded that the present application has the following beneficial effects:

[0031] In the present application, the characteristics of laser beams that produce specular reflection on the surface of transparent objects and diffuse reflection on the surfaces of other objects are utilized. When the self-propelled robot moves, the laser radar carried on it emits a laser beam in real time, and determines whether there are transparent obstacles in the environment to be detected based on the intensity value of the received reflected light signal. If it is determined that there are transparent obstacles, a preset mark representing the transparent obstacle is constructed on the corresponding area of ​​the map based on the distance value corresponding to the reflected light signal. This avoids the problem of manual labeling in related technologies that is not only time-consuming and labor-intensive, but also cannot guarantee the labeling accuracy. This saves labor costs, reduces the transparent obstacle marking errors caused by human errors, improves the accuracy of the map, and ensures the safety of the self-propelled robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solution in the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 It is a flow chart of a transparent obstacle marking construction method provided in an embodiment of the present application;

[0034] Figure 2 It is a schematic diagram of a light path of a laser beam provided in an embodiment of the present application that is diffusely reflected on the surface of a non-transparent object;

[0035] Figure 3 It is a schematic diagram of a light path of a laser beam provided in an embodiment of the present application that is specularly reflected on a smooth surface of a transparent object;

[0036] Figure 4 It is a schematic diagram of a light path of a laser beam provided in an embodiment of the present application vertically incident on a transparent obstacle surface to cause mirror reflection;

[0037] Figure 5 It is a functional module schematic diagram of a transparent obstacle marking construction device provided in an embodiment of the present application;

[0038] Figure 6 It is a structural schematic diagram of a transparent obstacle marking construction system provided in an embodiment of the present application;

[0039] Figure 7 is a structural schematic diagram of a self-moving robot provided in an embodiment of the present application;

[0040] Figure 8 is a schematic diagram of the walking trajectory of the wheeled robot in the second application scenario provided in the embodiment of the present application;

[0041] Fig. 9 It is a comparison chart of maps constructed by applying the method of the embodiment of the present application and maps constructed by not applying the method of the embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in this application to clearly and completely describe the technical solutions in this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0043] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first" and "second" are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0044] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0045] The present application provides a transparent obstacle marking construction method, system and self-moving robot, which are described in detail below.

[0046] First, the present application provides a method for constructing a transparent obstacle marker. The executor of the method can be a transparent obstacle marker construction device, or a self-moving robot, a server device, a physical host or a user equipment (UE) and other different types of devices that integrate the transparent obstacle marker construction device. The transparent obstacle marker construction device can be implemented in hardware or software, and the UE can specifically be a terminal device such as a smart phone, a tablet computer, a laptop computer, a PDA or a desktop computer.

[0047] The transparent obstacle marking construction method can be applied to intelligent robots such as cleaning robots, navigation robots, and security robots to detect and identify transparent obstacles in the environment and mark them on the map to facilitate the robot's navigation or obstacle avoidance deployment and prevent the robot from colliding with transparent obstacles.

[0048] The self-propelled robot of the embodiment of the present application may be equipped with a laser radar, which can detect transparent obstacles in the environment by making use of the characteristic of mirror reflection of the laser beam emitted by the laser radar on the surface of transparent objects. The laser radar can be communicated with the main control unit of the self-propelled robot to exchange data. The main control unit can be any existing type of control unit such as a microcontroller unit (MCU) and a single-chip microcomputer, which is used to control the movement of the laser radar and the self-propelled robot and perform corresponding work tasks. It can be understood that the main control unit can also execute the transparent obstacle marking construction method of the present application to construct transparent obstacle markings on the map.

[0049] In this embodiment, the laser radar can cover a 360° coverage range around the self-propelled robot to ensure the detection of transparent obstacles without blind spots, thereby ensuring the safety of the self-propelled robot.

[0050] like Figure 1 As shown, Figure 1 It is a flow chart of a transparent obstacle marking construction method provided in an embodiment of the present application. It should be noted that although a logical sequence is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than that here.

[0051] In an embodiment of the present application, the transparent obstacle marking construction method can be used to detect transparent obstacles in the environment and mark them on a map to ensure the safety of the self-propelled robot. The transparent obstacle marking construction method can include the following steps.

[0052] Step S101, obtaining a reflected light signal received by the laser radar; the reflected light signal is a light signal formed when a laser beam emitted by the laser radar is reflected by an object in the environment to be detected when a self-propelled robot equipped with the laser radar moves in the environment to be detected.

[0053] According to the working principle of LiDAR, it measures the distance to the surrounding environment by emitting a laser beam and then receiving the reflected light returned by objects in the environment, thereby calculating the distance to the object. The laser intensity of the reflected light will vary depending on the reflecting object.

[0054] like Figure 2 and Figure 3 As shown, Figure 2The figure shows the optical path of the laser beam diffusely reflected on the surface of a non-transparent object. Figure 3 The figure shows a schematic diagram of the optical path of a laser beam undergoing mirror reflection on a smooth surface of a transparent object such as glass. It can be understood that in mirror reflection, the reflection angle θ2 of the laser beam is equal to the incident angle θ1, and in mirror reflection, most of the laser beam will be emitted along the reflection direction. Therefore, the laser intensity of the reflected light will be significantly higher than that of the light beam undergoing diffuse reflection.

[0055] Therefore, in the embodiment of the present application, when the self-moving robot moves in the environment to be detected, the main control unit of the self-moving robot can obtain the reflected light signal received by the laser radar.

[0056] In the embodiment of the present application, the laser radar can be any existing laser radar sensor, including but not limited to single-line laser radar, multi-line laser radar, etc. The laser radar can emit a laser beam based on a preset emission frequency, and detect and sense the reflected light reflected by the object, so as to determine the type of the object and the distance between the self-moving robot and the object. For example, the laser radar can be set to emit a laser beam once per second. It can be understood that the emission frequency of the laser radar can be determined according to actual needs or actual application scenarios, and is not specifically limited here.

[0057] In some specific implementations, the laser radar can upload the received reflected light signal to the main control unit of the self-moving robot based on a preset upload frequency. That is, the main control unit can obtain the distance between the self-moving robot and the objects in the environment based on the upload frequency, thereby constructing the corresponding object mark on the map and subsequently planning the walking path or obstacle avoidance strategy based on the distance.

[0058] In some other specific implementations, the main control unit can also establish a communication link with the laser radar carried by the self-moving robot based on a preset access frequency, obtain the distance between the self-moving robot and the object from the laser radar, thereby constructing a corresponding object mark on the map and subsequently planning a walking path or obstacle avoidance strategy based on the distance.

[0059] Step S102: Determine whether there is a transparent obstacle in the environment to be detected according to the intensity value of the reflected light signal.

[0060] According to step S101, it can be known that in mirror reflection, most of the laser beam will be emitted along the reflection direction. Therefore, the laser intensity of the reflected light by mirror reflection will be significantly higher than the emitted light that undergoes diffuse reflection. Based on this, it is possible to determine whether there are transparent obstacles in the environment to be detected where the self-moving robot is located based on the intensity value of the reflected light signal.

[0061] Step S103: If it is determined that there is a transparent obstacle, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the laser radar and the transparent obstacle.

[0062] In an embodiment of the present application, after determining in step S102 that there are transparent obstacles in the environment to be detected, the main control unit can map the distance value corresponding to the reflected light signal to a target map corresponding to the environment to be detected with the self-moving robot as the starting point, thereby constructing a preset mark representing the transparent obstacle in the corresponding area on the target map, that is, drawing an icon or other mark representing the transparent obstacle in the area, thereby reflecting the transparent obstacles in the environment to be detected on the target map.

[0063] In an embodiment of the present application, the main control unit can determine the time it takes for the laser beam to propagate in the air, that is, the laser flight time, based on the difference between the emission time of the laser beam emitted by the laser radar and the reception time of the corresponding reflected light signal. Since the propagation speed of light in the air is known, a distance can be obtained based on the product of the propagation speed and the laser flight time.

[0064] It can be understood that since the laser beam propagates twice between the laser radar and the transparent obstacle, the distance calculated at this time is actually twice the distance between the laser radar or self-propelled robot and the transparent obstacle. Therefore, taking half of the value based on the product of the propagation speed and the laser flight time can obtain the distance value between the laser radar or self-propelled robot and the transparent obstacle.

[0065] Since the target map corresponds to the environment to be detected, after determining the distance in the actual environment, the distance value can be proportionally converted to the target map, thereby constructing a preset mark on the corresponding area of ​​the target map with the self-propelled robot as the starting point.

[0066] In the embodiment of the present application, the characteristics of laser beams that produce specular reflection on the surface of transparent objects and diffuse reflection on the surfaces of other objects are utilized. When the self-propelled robot moves, the laser radar carried on it emits a laser beam in real time, and determines whether there are transparent obstacles in the environment to be detected based on the intensity value of the received reflected light signal. If it is determined that there are transparent obstacles, a preset mark representing the transparent obstacle is constructed on the corresponding area of ​​the map based on the distance value corresponding to the reflected light signal. This avoids the problem in the related technology that manual labeling is not only time-consuming and labor-intensive, but also cannot guarantee the labeling accuracy. This saves labor costs, reduces the transparent obstacle marking errors caused by human errors, improves the accuracy of the map, and ensures the safety of the self-propelled robot.

[0067] Next, continue to Figure 1 Each step shown and a specific implementation method that may be used in practical applications are described in detail.

[0068] In some embodiments of the present application, before obtaining the reflected light signal received by the laser radar, the method may further include:

[0069] When the self-propelled robot moves in the environment to be detected, the laser radar is controlled to emit a laser beam in the horizontal direction.

[0070] It can be understood that when the laser beam is incident on the surface of an object, the emission angle of its reflected light is the same as the incident angle. Therefore, in order to further ensure that the intensity of the reflected light during mirror reflection is greater than the reflected light corresponding to diffuse reflection, in an embodiment of the present application, the laser radar can be controlled to emit a laser beam in a horizontal direction.

[0071] Normally, transparent obstacles in the environment, such as glass windows and glass fences, are set perpendicular to the ground. Therefore, in the embodiment of the present application, after controlling the laser beam emitted by the laser radar in the horizontal direction, the laser beam will be emitted perpendicularly to the surface of the object. If the object is a transparent obstacle, the reflected light will also be emitted perpendicularly to the surface of the object to the laser radar, so that the laser radar receives a high-intensity reflected light signal.

[0072] It should be noted that in some practical application scenarios, when installing the laser radar, the laser transmitter of the laser radar can be manually set horizontally so that the laser beam it emits is parallel to the horizontal plane.

[0073] like Figure 4 As shown in the figure, after the laser radar emits a laser beam in parallel in the horizontal direction, the laser beam vertically hits the surface of the transparent obstacle, and the reflected light is vertically emitted from the transparent obstacle surface to the laser radar. If the laser beam is vertically emitted into the surface of a non-transparent object, it will be diffusely reflected on its surface, so the intensity of the reflected light signal received by the laser radar is low, thereby being able to identify the transparent obstacles in the detection environment.

[0074] It is understandable that in some other application scenarios, the emission direction of the lidar laser beam may also have a certain angle with the horizontal plane, such as emitting upward at a small angle or emitting downward at a small angle. At this time, although the intensity of the reflected light signal is not as strong as when it is emitted in parallel, it will be significantly stronger than the intensity of the reflected light corresponding to the diffuse reflection. Therefore, the emission angle of the laser beam can be selected according to the actual application scenario, and is not limited here.

[0075] In an embodiment of the present application, a light intensity threshold can be pre-set to compare with the intensity of the reflected light signal. If the intensity value of the reflected light signal is greater than or equal to the light intensity threshold, such as the preset first intensity threshold, it can be considered that the reflected light signal is formed by mirror reflection on the surface of the transparent object. At this time, it can be determined that there is a transparent obstacle. Conversely, if the intensity value of the reflected light signal is less than the preset first intensity threshold, it can be considered that the reflected light signal is formed by diffuse reflection on the surface of the non-transparent object. At this time, it can be determined that there is no transparent obstacle.

[0076] It should be noted that the preset first intensity threshold in the embodiment of the present application can be determined based on past experience or multiple experiments and is not specifically limited here.

[0077] Since the detection of transparent obstacles requires the lidar to capture reflected light signals during movement, the detection conditions are relatively harsh. Therefore, the detected obstacle points, i.e., the preset marks on the target map, may be relatively sparse. In order to present the complete transparent obstacle effect on the target map, the present application can also amplify the preset marks.

[0078] In some embodiments of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal. After that, the method may further include:

[0079] For two adjacent preset marks on the target map, obtaining the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks;

[0080] If the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks is less than a preset second intensity threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0081] In the embodiment of the present application, for two adjacent preset marks on the target map, the grid in the middle area may correspond to a transparent obstacle in the actual environment, or may correspond to a wall or a passage in the actual environment, so for the middle area between the two adjacent preset marks, the main control unit can obtain the intensity value of the reflected light signal corresponding to the grid in the middle area recorded in the transparent obstacle detection stage. Since the laser beam that is not vertically shot into the transparent obstacle may pass through the transparent obstacle and shoot at the non-transparent object behind the transparent obstacle, the intensity of the reflected light signal returned at this time is small or no reflected light is returned, and the grid value on the target map corresponding to the area will be small, that is, the intensity value of the reflected light signal is small.

[0082] Therefore, in an embodiment of the present application, if the intensity value of the reflected light signal corresponding to the grid between two adjacent preset marks is less than the preset second intensity threshold, it can also be considered that the object in the actual environment corresponding to the grid area is a transparent obstacle. Therefore, a preset mark can be constructed on the grid between the two adjacent preset marks so that the continuous preset marks can better present the length of the transparent obstacle in the actual environment.

[0083] Similarly, the preset second intensity threshold in the embodiment of the present application can be determined based on past experience or multiple experiments, and is not specifically limited here.

[0084] It is understandable that if a large number of experiments are conducted in the early stage on the reflection, diffuse reflection, refraction, etc. of the laser beam on the surfaces of different objects, the range of the reflected light intensity corresponding to the reflection, diffuse reflection, refraction, etc. of the laser beam on the surface of each object can be determined. Therefore, the object in the actual environment corresponding to the grid area can be directly determined based on the intensity value of the reflected light signal corresponding to the grid between two adjacent preset marks, so as to construct a mark corresponding to the object in the grid area.

[0085] In some other embodiments of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal. After that, the method may further include:

[0086] For two adjacent preset marks on the target map, if the distance between the two adjacent preset marks is less than a preset distance threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0087] In an embodiment of the present application, for two preset marks that are relatively close to each other on the target map, since the distance between the two preset marks on the target map is relatively close, for example, less than a preset distance threshold, it can be considered that the two transparent obstacles in the actual environment are relatively close. In actual applications, the two relatively close transparent obstacles may not accommodate a passage for the mobile robot to move or no wall is detected, then it can be considered that the two transparent obstacles can actually extend into a whole transparent obstacle. Therefore, corresponding to the target map, a preset mark can be constructed on the map area between the two adjacent preset marks to present the continuity of the transparent obstacle.

[0088] It can be understood that the preset distance threshold in the embodiment of the present application can be determined based on past experience or multiple experiments, and is not specifically limited here.

[0089] In some other embodiments of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal. After that, the method may further include:

[0090] For a preset mark on the target map, edge extraction is performed on pixel points within a preset neighborhood range of the preset mark to expand the preset mark.

[0091] In an embodiment of the present application, for each preset mark on the target map, edge extraction can be performed on the pixel points within its preset neighborhood. The edge extraction here can adopt any existing edge extraction method. On the basis of the edge extraction method, combined with the characteristics of transparent objects, the area with the most drastic change in grayscale value within the preset neighborhood of the preset mark is determined, thereby determining the edge of the transparent obstacle corresponding to the area.

[0092] When a transparent obstacle is detected at a nearly vertical angle between the incident and reflected laser beam of the lidar, and the transparent obstacle is first identified and a preset mark is established on the target map, as the lidar moves, the transparent obstacle here may lose the conditions for being detected again, and may not be detected in subsequent lidar sensor data or may be detected as an obstacle-free area. For this situation, the method of the embodiment of the present application ensures that the constructed preset mark is stably retained and will not be eliminated due to the subsequent lidar failing to detect a transparent obstacle at this location.

[0093] Therefore, in some embodiments of the present application, a preset mark is constructed on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, and then the method may further include:

[0094] For the preset mark on the target map, if the distance value corresponding to the reflected light signal is greater than the distance between the preset mark and the laser radar, the preset mark is retained.

[0095] In an embodiment of the present application, for a preset mark that has been confirmed to be a transparent obstacle and has been constructed on the target map, the distance value of the non-transparent object behind it may be returned due to the laser beam passing through the transparent obstacle. Therefore, even if the distance value of the reflected light signal received by the laser radar is greater than the distance between the preset and the laser radar during the subsequent movement of the self-propelled robot, the preset mark will not be eliminated, but will be retained to achieve a stable high confidence level for the preset mark of the transparent obstacle in the target map, thereby improving the accuracy of the target map.

[0096] In order to better implement the transparent obstacle marking construction method of the present application, the present application also provides a transparent obstacle marking construction device, such as Figure 5 As shown, Figure 5 is a functional module diagram of a transparent obstacle mark construction device provided in an embodiment of the present application. The transparent obstacle mark construction device 500 may include:

[0097] The acquisition module 501 is used to acquire the reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected;

[0098] A determination module 502 is used to determine whether there is a transparent obstacle in the environment to be detected according to the intensity value of the reflected light signal;

[0099] Construction module 503 is used to construct a preset mark on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal if it is determined that there is a transparent obstacle; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the laser radar and the transparent obstacle.

[0100] In some embodiments of the present application, the transparent obstacle marking construction device 500 may further include a control module. Before the acquisition module 501 acquires the reflected light signal received by the laser radar, the control module may be specifically used to:

[0101] When the self-propelled robot moves in the environment to be detected, the laser radar is controlled to emit a laser beam in the horizontal direction.

[0102] In some embodiments of the present application, the determination module 502 may also be specifically used for:

[0103] If the intensity value of the reflected light signal is greater than or equal to a preset first intensity threshold, it is determined that there is a transparent obstacle in the environment to be detected.

[0104] In some embodiments of the present application, the construction module 503 may also be used to:

[0105] For two adjacent preset marks on the target map, obtaining the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks;

[0106] If the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks is less than a preset second intensity threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0107] In some embodiments of the present application, the construction module 503 may also be used to:

[0108] For two adjacent preset marks on the target map, if the distance between the two adjacent preset marks is less than a preset distance threshold, a preset mark is constructed on the map area between the two adjacent preset marks.

[0109] In some embodiments of the present application, the construction module 503 may also be used to:

[0110] For a preset mark on the target map, edge extraction is performed on pixel points within a preset neighborhood range of the preset mark to expand the preset mark.

[0111] In some embodiments of the present application, the construction module 503 may also be used to:

[0112] For the preset mark on the target map, if the distance value corresponding to the reflected light signal is greater than the distance between the preset mark and the laser radar, the preset mark is retained.

[0113] In some embodiments of the present application, the construction module 503 may also be used to:

[0114] The laser flight time is obtained according to the reception time of the reflected light signal received by the laser radar and the emission time of the emitted laser beam;

[0115] Determine the distance value based on the laser flight time;

[0116] Build preset markers on the corresponding area of ​​the target map according to the distance value.

[0117] It should be noted that, in the present application, the relevant contents of the acquisition module 501, the determination module 502, the construction module 503 and the control module correspond to the above one by one, and those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the transparent obstacle marking construction device and its corresponding unit modules described above can refer to the following. Figure 1 The description of the transparent obstacle marking construction method in any embodiment will not be repeated here.

[0118] In order to better implement the transparent obstacle marking construction method of the present application, the present application also provides a transparent obstacle marking construction system 600, which may include a control terminal 601 and a self-moving robot 602 in communication with the control terminal 601, wherein the self-moving robot 602 is equipped with a laser radar 603;

[0119] The control terminal 601 can be used to control the laser radar 603 and the self-propelled robot 602 to work and realize Figure 1 Corresponding to the transparent obstacle marking construction method in any embodiment.

[0120] The control terminal 601 can control the self-moving robot 602 to implement the present application as follows Figure 1 Corresponding to the steps of the transparent obstacle marking construction method in any embodiment, therefore, the present application can be implemented as follows Figure 1 The beneficial effects that can be achieved by the transparent obstacle marking construction method in any embodiment are detailed in the previous description and will not be repeated here.

[0121] In order to better implement the transparent obstacle marking construction method of the present application, the present application also provides a self-propelled robot, which may include a processor 701 and a memory 702, and the memory 702 may be used to store a computer program. When the computer program is executed by the processor 701, it can be used to implement the following functions:

[0122] Acquire the reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected;

[0123] According to the intensity value of the reflected light signal, determine whether there is a transparent obstacle in the environment to be detected;

[0124] If it is determined that there is a transparent obstacle, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the lidar and the transparent obstacle.

[0125] like Figure 7 As shown, it shows a structural schematic diagram of the self-moving robot involved in the present application, specifically:

[0126] The self-propelled robot may include one or more processors 701 of processing cores, one or more computer-readable storage media memories 702, a power supply 703, an input unit 704 and other components. Those skilled in the art will appreciate that Figure 7 The structure shown in the figure does not constitute a limitation on the self-propelled robot, and the self-propelled robot may also include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0127] The processor 701 is the control center of the self-moving robot. It uses various interfaces and lines to connect the various parts of the entire self-moving robot. By running or executing the software program and / or unit module stored in the memory 702, and calling the data stored in the memory 702, the processor 701 performs various functions of the self-moving robot and processes data, thereby monitoring the self-moving robot as a whole. Optionally, the processor 701 may include one or more processing cores; the processor 701 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0128] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the self-mobile robot, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

[0129] The self-propelled robot may also include a power supply 703 for supplying power to various components. Preferably, the power supply 703 may be logically connected to the processor 701 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 703 may also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0130] The self-propelled robot may further include an input unit 704 and an output unit 705. The input unit 704 may be used to receive input digital or character information, and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0131] Although not shown, the self-moving robot may also include a display unit, etc., which will not be described in detail here. Specifically in the present application, the processor 701 in the self-moving robot will load the executable files corresponding to the processes of one or more application programs into the memory 702 according to the following instructions, and the processor 701 will run the application programs stored in the memory 702, thereby realizing various functions, as follows:

[0132] Acquire the reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected;

[0133] According to the intensity value of the reflected light signal, determine whether there is a transparent obstacle in the environment to be detected;

[0134] If it is determined that there is a transparent obstacle, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the lidar and the transparent obstacle.

[0135] A person skilled in the art will appreciate that all or part of the steps in the various methods described above may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by the processor 701.

[0136] To this end, the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. Computer instructions are stored thereon, and the computer instructions are loaded by the processor 701 to execute the steps in any of the transparent obstacle marking construction methods provided in the present application. For example, when the computer instructions are executed by the processor 701, the following functions are realized:

[0137] Acquire the reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected;

[0138] According to the intensity value of the reflected light signal, determine whether there is a transparent obstacle in the environment to be detected;

[0139] If it is determined that there is a transparent obstacle, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the lidar and the transparent obstacle.

[0140] The computer instructions stored in the computer readable storage medium can execute the present application as follows: Figure 1 Corresponding to the steps in the method for constructing a transparent obstacle mark in any embodiment, the present application can be implemented as follows: Figure 1 The beneficial effects that can be achieved by the transparent obstacle marking construction method in any embodiment are detailed in the previous description and will not be repeated here.

[0141] The technical solution of the present application is described below in conjunction with specific application scenarios to facilitate understanding.

[0142] Application scenario 1

[0143] The laser radar mounted horizontally on the self-moving robot emits a laser beam, controls the self-moving robot to move in the area to be detected, determines the presence of a transparent obstacle based on the intensity of the received reflected light, and constructs a first obstacle mark at the corresponding grid on the target map based on the distance value corresponding to the reflected light.

[0144] The mobile robot again determines the presence of a transparent obstacle based on the received high-intensity reflected light, and constructs a second obstacle mark at the corresponding grid on the target map based on the distance value corresponding to the reflected light.

[0145] According to the line connecting the first obstacle mark and the second obstacle mark, the self-moving robot is controlled to move along a route parallel to the line in the actual environment, and continues to construct obstacle marks according to the received high-intensity reflected light to present a complete transparent obstacle on the target map.

[0146] Application scenario 2

[0147] Manually control a wheeled robot equipped with a LiDAR sensor. The LiDAR sensor is required to be horizontal and move parallel to the transparent obstacle to be constructed within a range of 10 cm to 5 meters near the transparent obstacle in the building, such as Figure 8As shown in (a), (b) and (c), some possible walking trajectories of the wheeled robot, wherein the dotted line represents a transparent obstacle, the bold solid line represents a non-transparent obstacle, the thin solid line represents a walking trajectory, and the circle represents a wheeled robot. The method of the present application can detect and identify transparent obstacles in the environment, and automatically construct transparent obstacle marks at the corresponding positions of the 2D map without manual labeling, thereby improving the accuracy of the constructed 2D map, improving the accuracy of the robot's navigation and obstacle avoidance, and avoiding the safety risks of crossing unidentified transparent obstacles.

[0148] Application scenario three

[0149] Please refer to Fig. 9 , where column A is a 2D map constructed based on the method of the present application, column B is a 2D map constructed without using the method of the present application, and column C is a real scene for constructing the map; in the figure, black represents obstacles, white represents obstacle-free areas, gray represents unknown areas, and red lines represent the robot's motion trajectory.

[0150] The first row is scene 1, and the corresponding channel side is a glass fence. The second row is scene 2, and the corresponding channel side is a glass fence.

[0151] according to Fig. 9 It can be seen that the 2D map constructed based on the method of this application can well display the distribution of transparent objects in the environment. The robot works using accurate maps. The accurate obstacle positions in the map improve the accuracy of navigation and obstacle avoidance, and avoid the safety risks of crossing unidentified obstacles. Compared with the existing solution of manual marking on the map, it can save labor costs, improve deployment efficiency, and reduce the transparent obstacle marking errors caused by human errors.

[0152] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0153] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous embodiments and will not be repeated here.

[0154] The above is a detailed introduction to a transparent obstacle marking construction method, system and self-moving robot provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The above description is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for constructing a transparent obstacle marker, characterized in that: The method comprises: Acquire a reflected light signal received by the laser radar; the reflected light signal is a light signal formed when the laser beam emitted by the laser radar is reflected by an object in the environment to be detected when the self-propelled robot equipped with the laser radar moves in the environment to be detected; Determining whether there is a transparent obstacle in the environment to be detected according to the intensity value of the reflected light signal; If it is determined that the transparent obstacle exists, a preset mark is constructed on the corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal; the preset mark is used to characterize the transparent obstacle, the target map is a map corresponding to the environment to be detected, and the distance value is used to characterize the distance between the laser radar and the transparent obstacle.

2. The method according to claim 2, characterized in that: Before obtaining the reflected light signal received by the laser radar, the method includes: When the self-propelled robot moves in the environment to be detected, the laser radar is controlled to emit the laser beam in a horizontal direction.

3. The method according to claim 1, characterized in that Determining whether there is a transparent obstacle in the environment to be detected according to the intensity value of the reflected light signal includes: If the intensity value of the reflected light signal is greater than or equal to a preset first intensity threshold, it is determined that the transparent obstacle exists in the environment to be detected.

4. The method according to claim 1, characterized in that: After constructing a preset mark on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, the method further comprises: For two adjacent preset marks on the target map, obtaining an intensity value of a reflected light signal associated with a map area between the two adjacent preset marks; If the intensity value of the reflected light signal associated with the map area between the two adjacent preset marks is less than a preset second intensity threshold, the preset mark is constructed on the map area between the two adjacent preset marks.

5. The method according to claim 1, characterized in that After constructing a preset mark on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, the method further comprises: For two adjacent preset marks on the target map, if the distance between the two adjacent preset marks is less than a preset distance threshold, the preset mark is constructed on the map area between the two adjacent preset marks.

6. The method according to claim 1, characterized in that After constructing a preset mark on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, the method further comprises: For the preset mark on the target map, edge extraction is performed on pixel points within a preset neighborhood range of the preset mark to expand the preset mark.

7. The method according to claim 1, characterized in that After constructing a preset mark on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal, the method further comprises: For the preset mark on the target map, if the distance value corresponding to the reflected light signal is greater than the distance between the preset mark and the laser radar, the preset mark is retained.

8. The method according to claim 1, characterized in that The step of constructing a preset mark on a corresponding area of ​​the target map according to the distance value corresponding to the reflected light signal includes: Obtaining the laser flight time according to the reception time of the reflected light signal received by the laser radar and the emission time of the laser beam; Determining the distance value according to the laser flight time; The preset mark is constructed on the corresponding area of ​​the target map according to the distance value.

9. A transparent obstacle marking construction system, characterized in that: It includes a control end and a self-moving robot in communication with the control end, wherein the self-moving robot is equipped with a laser radar; The control end is used to control the operation of the laser radar and the self-propelled robot, and implement the transparent obstacle marking construction method described in any one of claims 1-8.

10. A self-propelled robot, characterized in that: The self-propelled robot is equipped with a laser radar, and includes a memory and a processor. The memory is used to store a computer program. When the computer program is executed by the processor, it is used to implement the transparent obstacle marking construction method described in any one of claims 1 to 8.

Images