Laser radar stain detection method and robot

Abstract

The present invention provides a method for detecting laser radar stains. The laser radar is mounted on a robot. The method comprises the following steps: S101: after detecting a trigger condition, the robot stops in front of a target object; S102: controlling the laser radar to emit detection pulses in the surrounding area, receiving echo pulses of the detection pulses, and generating a point cloud based on the echo pulses; S103: determining whether the laser radar has recognized the target object based on the point cloud; S104: when it is determined that the laser radar has recognized the target object, determining whether there are points in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object; S105: when there are points in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object, determining the presence of stains on the laser radar. The method of the present invention can quickly and cost-effectively detect whether there are stains on the airborne radar, allowing for timely cleaning and maintenance, reducing abnormalities such as robot malfunction caused by stains attached to the radar affecting obstacle avoidance, and improving the robustness of the robot and the customer experience.

Description

Technical Field

[0001] The present invention generally relates to the field of intelligent robot technology, and in particular to a laser radar stain detection method, a robot, and a computer-readable storage medium. Background Art

[0002] With the development of science and technology, robots are widely used in various fields of work and life, and are becoming increasingly popular. Sensors play a vital role in robot control, especially LiDAR. LiDAR has been widely used in robots in recent years for ranging and obstacle avoidance due to its advantages such as excellent detection performance, small size, and light weight.

[0003] LiDAR is an active detection device that uses a laser as its light source and photoelectric detection technology. It can determine the distance to a target object by the time difference between the transmission and reception of laser signals. However, in practice, the surface of a robot's onboard radar can accumulate stains over time. These stains can affect the accuracy of radar scans and, in severe cases, even cause the radar to malfunction, leading to the robot's inability to function properly. Furthermore, the onboard radar is typically embedded in the center of the robot, making it difficult to detect and address any stains. While there are radars on the market that automatically warn of stains, these are often expensive, making them difficult to meet demand given the price and deployment costs of the robot itself.

[0004] The contents of the background technology section are merely the technologies known to the inventors and do not necessarily represent the existing technologies in this field. Summary of the Invention

[0005] In order to solve one or more problems in the prior art, the present invention provides a method for detecting stains using a laser radar, wherein the laser radar is installed on a robot, and the method comprises:

[0006] S101: After the robot detects the trigger condition, it stops in front of the target object;

[0007] S102: Controlling the laser radar to transmit detection pulses to the surroundings, receiving echo pulses of the detection pulses, and generating a point cloud based on the echo pulses;

[0008] S103: Determining whether the laser radar recognizes the target object based on the point cloud;

[0009] S104: When it is determined that the laser radar recognizes the target object, determining whether there is a point in the point cloud within the field of view corresponding to the target object whose deviation exceeds a threshold; and

[0010] S105: When there is a point in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object, it is determined that there is stain on the laser radar.

[0011] According to one aspect of the present invention, the trigger condition includes when the robot finishes charging, or when the robot is at a first distance from the target object;

[0012] The step of docking in front of the target object includes: the robot docking at a second distance from the target object, the second distance is greater than the first distance, and the range of the second distance is 10 cm-50 cm.

[0013] According to one aspect of the present invention, the target object has strong reflective material and weak reflective material at a height substantially the same as that of the laser radar, and the strong reflective material and weak luminescent material are arranged in a preset arrangement and facing the laser radar.

[0014] According to one aspect of the present invention, the step of controlling the laser radar to emit detection pulses to the surroundings includes: controlling the robot to rotate with the laser radar as the center, and simultaneously controlling the laser radar to emit detection pulses to the surroundings to cover the range in the horizontal direction.

[0015] According to one aspect of the present invention, the step of determining whether the laser radar recognizes the target object includes:

[0016] Determining shape characteristics and reflectivity of the point cloud;

[0017] If the shape characteristics and / or reflectivity correspond to the shape characteristics and / or reflectivity of the strong reflective material and the weak reflective material on the target object, it is determined that the laser radar has identified the target object.

[0018] According to one aspect of the present invention, the step of determining whether there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object comprises:

[0019] The points of the point cloud within the field of view corresponding to the target object are divided into a first group of points and a second group of points according to reflectivity, the first group of points corresponding to the strong reflective material, and the second group of points corresponding to the weak reflective material.

[0020] According to one aspect of the present invention, the step of determining whether there is a point in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object includes: performing straight line fitting on the first group of points to obtain a first straight line, and determining whether there is a point in the first group of points whose distance from the first straight line exceeds the threshold.

[0021] According to one aspect of the present invention, the step of determining whether there is a point in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object also includes: performing straight line fitting on the second group of points to obtain a second straight line, and determining whether there is a point in the second group of points whose distance from the second straight line exceeds the threshold.

[0022] According to one aspect of the present invention, the method further includes: when it is determined that there is dirt on the laser radar, repeating S102-S105 to check the dirt.

[0023] According to one aspect of the present invention, the method further includes: issuing a warning message if the calibration result confirms that the laser radar is contaminated.

[0024] According to one aspect of the present invention, the target object has continuous grooves and convex blocks, and the strong reflective material and the weak reflective material are respectively arranged on the grooves and convex blocks; the target object includes a charging pile used in conjunction with the robot.

[0025] The present invention also provides a robot, comprising:

[0026] The main body has a walking mechanism;

[0027] LiDAR, used to detect the environment around the robot;

[0028] The controller is coupled to the walking mechanism and the laser radar, configured to control the walking mechanism and the laser radar, and configured to execute the method as described above.

[0029] The present invention also provides a computer-readable storage medium, comprising computer-executable instructions stored thereon, wherein the computer-executable instructions implement the method described above when executed by a controller.

[0030] The method of the present invention can quickly and inexpensively detect whether there are stains on the airborne radar without the assistance of external devices, so that it can be cleaned and maintained in time, reducing abnormal conditions such as robot failure caused by stains attached to the radar affecting the obstacle avoidance effect, which is beneficial to improving the robustness of the robot and customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0032] Figure 1 A flowchart of a method for detecting stains by a laser radar according to an embodiment of the present invention is shown;

[0033] Figure 2A schematic diagram of a target object according to a preferred embodiment of the present invention is shown;

[0034] Figure 3 A schematic diagram showing a robot docked in front of a target object according to a preferred embodiment of the present invention is shown;

[0035] Figure 4 A schematic diagram showing a point cloud of a target object recognized by a laser radar according to a preferred embodiment of the present invention is shown;

[0036] Figure 5A A schematic diagram showing a method of determining the presence of stains on a laser radar using a first set of points according to a preferred embodiment of the present invention is shown;

[0037] Figure 5B A schematic diagram showing a method of determining that a laser radar is free of contamination by using a first set of points according to a preferred embodiment of the present invention is shown;

[0038] Figure 6A A schematic diagram showing the determination of the presence of stains on a laser radar by using a second set of points according to a preferred embodiment of the present invention is shown;

[0039] Figure 6B A schematic diagram showing a method of determining that a laser radar is free of contamination by a second set of points according to a preferred embodiment of the present invention; and

[0040] Figure 7 A schematic diagram of a robot according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0042] In the description of the present invention, it should be understood that the terms "center," "longitudinal," "transverse," "length," "width," "thickness," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," "clockwise," "counterclockwise," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended solely for the purpose of facilitating the description of the present invention and simplifying the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features referred to. Thus, features designated "first" or "second" may explicitly or implicitly include one or more of the designated features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0043] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, removable, or integral connections; mechanical, electrical, or intercommunication connections; direct or indirect connections through an intermediary; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0044] In the present invention, unless otherwise expressly specified or limited, a first feature being "above" or "below" a second feature may include the first and second features being in direct contact, or may also include the first and second features not being in direct contact but being in contact via another feature between them. Furthermore, a first feature being "above," "above," and "above" a second feature may include the first feature being directly above or diagonally above the second feature, or may simply mean that the first feature is at a higher level than the second feature. A first feature being "below," "below," and "below" a second feature may include the first feature being directly above or diagonally above the second feature, or may simply mean that the first feature is at a lower level than the second feature.

[0045] The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numbers and / or reference letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides examples of various specific processes and materials, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0047] The present invention provides a method for detecting laser stains. The laser radar is installed on a robot. Using the method of the present invention, it is possible to quickly and cost-effectively detect whether there are stains on the laser radar, so that the laser radar can be cleaned and maintained in a timely manner. The method is described in detail below.

[0048] Figure 1 FIG. 1 shows a flow chart of a laser radar stain detection method 100 according to an embodiment of the present invention. Figure 1 As shown, the method 100 includes steps S101-S105. Before describing the method 100 in detail, the target object that assists the robot in implementing the method 100 is first introduced.

[0049] The target object has a strong reflective material and a weak reflective material at substantially the same height as the laser radar, and the strong reflective material and the weak reflective material are arranged in a preset arrangement and face the laser radar. The purpose of providing the strong reflective material and the weak reflective material on the target object is to distinguish the target object from other obstacles in the robot's surrounding environment. It is easy to understand that the more distinctive the shape and arrangement of the strong reflective material and the weak reflective material, the greater the difference in reflectivity, and the easier it is to distinguish the target object from other obstacles. In actual application, in order to enable the laser radar to detect the strong reflective material and the weak reflective material, the height of the strong reflective material and the weak reflective material is usually set to be slightly higher than the height of the laser radar.

[0050] Figure 2 A schematic diagram of a target object according to a preferred embodiment of the present invention is shown in FIG. Figure 2As shown, the target object has continuous grooves and convex blocks, and the strong-reflective material and the weak-reflective material are respectively provided on the grooves and convex blocks, and the number of the grooves and convex blocks is not limited by the present invention. The present invention also does not limit the shape, arrangement, width and category of the strong-reflective material and the weak-reflective material. According to a preferred embodiment of the present invention, the shape of the strong-reflective material and the weak-reflective material can be, for example, a strip. According to a preferred embodiment of the present invention, the arrangement of the strong-reflective material and the weak-reflective material can be an alternating arrangement. Specifically, for example, the strong-reflective material can be provided on the groove, and the weak-reflective material can be provided on the convex blocks (refer to Figure 2 ); of course, the highly reflective material may also be provided on the convex blocks, and the weakly reflective material may also be provided on the concave blocks, and the present invention is not limited thereto. According to a preferred embodiment of the present invention, the widths of the highly reflective material and the weakly reflective material may be consistent with the widths of the concave blocks or convex blocks in which they are located. According to a preferred embodiment of the present invention, the highly reflective strip may be made of, for example, diamond reflective film, gold, copper, aluminum, etc., and the weakly reflective strip may be made of, for example, black plastic, paper, cloth, etc.

[0051] According to a preferred embodiment of the present invention, the target object can be a charging station used in conjunction with the robot. Since the charging station is an essential accessory for the robot, the advantage of using the charging station as the target object is that it eliminates the need for additional detection equipment, thereby saving time and labor costs and being convenient and quick. It should be understood that in actual application, the target object can also be other objects with strong or weak reflective strips, such as walls, cabinets, pillars, etc., which are not limited by the present invention and can be selected according to needs.

[0052] The above embodiment introduces the situation of the target object. After understanding the situation of the target object, each step of the method 100 is described in detail below.

[0053] In step S101 , after detecting a trigger condition, the robot stops in front of a target object.

[0054] According to a preferred embodiment of the present invention, the trigger condition may be when the robot finishes charging. Figure 3 FIG2 shows a schematic diagram of a robot docked in front of a target object according to a preferred embodiment of the present invention. Figure 3 As shown, when the end of charging is detected, the robot leaves the charging pile (target object) and stops at a second distance from the charging pile (target object), where the second distance ranges from 10 cm to 50 cm.

[0055] According to another preferred embodiment of the present invention, the trigger condition may also be when the robot is at a first distance from the target object (e.g., a charging station). The first distance is less than the second distance, and the first distance is, for example, 5 cm. It should be understood that the trigger condition is not limited to this, and the trigger condition may also be, for example, when the robot is just turned on, when the robot starts charging, at 12 noon every day, etc., and the specific setting can be based on actual conditions.

[0056] In step S102, the laser radar is controlled to transmit detection pulses to the surroundings, receive echo pulses of the detection pulses, and generate a point cloud based on the echo pulses.

[0057] Continue to refer Figure 3 According to a preferred embodiment of the present invention, the robot is controlled to rotate in a preset direction (clockwise or counterclockwise) with the laser radar as the center, and at the same time, the laser radar is controlled to emit detection pulses to the surroundings at a preset frequency. It should be understood that the robot should rotate at a slower frequency to cover the range in the horizontal direction. The detection pulse is incident on the obstacle and is diffusely reflected. The generated echo pulse is received by the laser radar and a point cloud is generated through photoelectric conversion. Due to the complex working environment of the robot, there may be other obstacles around the robot in addition to the target object. Therefore, it is necessary to determine whether the target object (such as a charging pile) has been identified. The description is continued below.

[0058] In step S103, it is determined whether the laser radar has identified the target object based on the point cloud.

[0059] The point cloud is a dataset of points in the LiDAR coordinate system. These points contain rich information, such as two-dimensional coordinates (x, y) (for single-line LiDAR) or three-dimensional coordinates (x, y, z) (for multi-line LiDAR), reflectivity, time, and more. Based on the point cloud, it can be determined whether the LiDAR has recognized the target object.

[0060] According to one embodiment of the present invention, whether the laser radar has identified the target object (e.g., a charging station) can be determined based on reflectivity. Specifically, if the reflectivity of a point in the point cloud matches the reflectivity of a strong reflective strip and / or a weak reflective strip on the target object (e.g., a charging station), it is determined that the laser radar has identified the target object (e.g., a charging station).

[0061] According to another embodiment of the present invention, whether the laser radar has identified the target object (e.g., a charging station) can be determined based on the distance. The laser radar performs distance measurement based on the time-of-flight (TOF) method and can calculate the distance to the obstacle according to the following formula:

[0062] d = c × t / 2, where c is the speed of light, c = 3 × 10 8m / s, t is the pulse flight time. If the calculated distance matches the second distance, it is determined that the LiDAR has identified the target object (e.g., a charging station). It should be understood that determining the distance to an obstacle is not limited to the time-of-flight method. In other words, other methods such as the ICP algorithm can also be used to determine the position or distance of the obstacle relative to the LiDAR.

[0063] According to another preferred embodiment of the present invention, it is possible to determine whether the laser radar has identified the target object (such as a charging pile) based on the shape characteristics of the point cloud. As mentioned above, the target object has continuous grooves and convex blocks, and the grooves and convex blocks are respectively provided with strong reflective materials and weak reflective materials. It can be seen that if the detection pulse of the laser radar is incident on the target object (such as a charging pile), the point cloud generated based on the echo pulse should have the same shape characteristics as the target object (such as a charging pile). Therefore, it is possible to determine whether the laser radar has identified the target object (such as a charging pile) based on the shape characteristics of the point cloud.

[0064] Figure 4 FIG2 shows a schematic diagram of a point cloud of a target object recognized by a laser radar according to a preferred embodiment of the present invention. Figure 4 As shown, the point cloud of the target object (such as a charging pile) is roughly divided into five parts. The first three parts of the point cloud are the point clouds of the convex blocks of the target object (such as a charging pile), and the last two parts of the point cloud are the point clouds of the grooves of the target object (such as a charging pile). According to the shape characteristics of the point cloud, it is easy to determine that the laser radar has identified the target object (such as a charging pile). In this embodiment, the target object (such as a charging pile) has three convex blocks and two grooves. It should be understood that this embodiment is only an example and does not constitute a limitation of the present invention. In actual applications, the convex blocks and grooves of the target object (such as a charging pile) can also be other numbers, such as one convex block and two grooves.

[0065] The above embodiments respectively describe determining whether the laser radar has identified the target object (e.g., a charging station) by using one of the reflectivity, distance, and shape features. In practice, to obtain more accurate recognition results, preferably, any or all of the above three methods can be used for judgment. According to another preferred embodiment of the present invention, a label can be added to the target object (e.g., a charging station) to construct a machine learning model to speed up recognition.

[0066] In step S104, when it is determined that the laser radar has identified the target object, it is determined whether there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object. In step S105, when there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object, it is determined that there is stain on the laser radar.

[0067] Ideally, the laser beam emitted by the LiDAR can successfully impinge on obstacles, and the point cloud generated based on the echo can also effectively restore the shape characteristics of the corresponding obstacle. However, if the LiDAR is contaminated, the laser beam emitted by the LiDAR may be blocked by the contamination and unable to successfully impinge on some obstacles, resulting in points with large deviations in the generated point cloud, also known as noise. Therefore, the presence of contamination on the LiDAR can be determined by determining whether there are points in the generated point cloud with deviations exceeding a threshold. This is described in detail below.

[0068] According to a preferred embodiment of the present invention, when it is determined that the laser radar has identified the target object (such as a charging pile), the point cloud of other obstacles can be removed and only the point cloud of the target object (such as a charging pile) can be retained to reduce the subsequent calculation amount and facilitate subsequent processing.

[0069] In order to more efficiently determine whether the laser radar has stains, according to a preferred embodiment of the present invention, the point cloud of the target object (such as a charging pile) can be divided into a first group of points and a second group of points according to the reflectivity, the first group of points corresponding to the strong reflective material, and the second group of points corresponding to the weak reflective material. The present invention does not limit the specific method of segmenting the point cloud. The purpose of segmentation is to process only the first group of points or the second group of points in the subsequent processing process to reduce the amount of calculation and speed up the processing efficiency. How to process only the first group of points or the second group of points will be described below.

[0070] According to a preferred embodiment of the present invention, the RANSAC algorithm can be used to perform straight line fitting on the first group of points to obtain a first straight line, and determine whether there is a point in the first group of points whose distance from the first straight line exceeds a threshold. If so, it is determined that there is stain on the laser radar.

[0071] Figure 5A FIG. 4 shows a schematic diagram of determining the presence of stains on a laser radar by using a first set of points according to a preferred embodiment of the present invention. Figure 5A As shown, there are points in the first group of points whose distance from the first straight line exceeds a threshold value (reference Figure 5A Point A shown), thereby determining that there is stain on the laser radar.

[0072] Figure 5B FIG. 1 shows a schematic diagram of determining that the laser radar is free of stains by using a first set of points according to a preferred embodiment of the present invention. Figure 5B As shown, there is no point in the first group of points whose distance from the first straight line exceeds a threshold, that is, the first group of points are evenly distributed near the first straight line, thereby determining that there is no stain on the laser radar.

[0073] The above embodiment describes how to determine whether the laser radar has stains by using the first set of points. Similar to the above method of determining whether the laser radar has stains by using the first set of points, according to another preferred embodiment of the present invention, the laser radar may also be determined by using the second set of points. That is, a straight line is fitted to the second set of points to obtain a second straight line, and it is determined whether there is a point in the second set of points whose distance from the second straight line exceeds a threshold. If there is a point (refer to Figure 6A Point B) shown, it is determined that there is dirt on the laser radar. Figure 6A and Figure 6B Schematic diagrams showing the presence and absence of stains on the laser radar using the second set of points are shown respectively.

[0074] The above embodiments describe determining whether the LiDAR is contaminated using only the first or second set of points. However, according to a preferred embodiment of the present invention, a comprehensive assessment of the presence of contamination can also be performed using both the first and second sets of points. Specifically, for example, if either the first or second set of points alone indicate the presence of contamination, then the LiDAR is determined to be contaminated. This comprehensive assessment is intended to improve the accuracy of detection results.

[0075] To further improve the accuracy of detection results, according to a preferred embodiment of the present invention, when the presence of contamination on the LiDAR is determined, relevant variables can be adjusted, and steps S102-S105 can be repeated, with multiple measurements performed to verify the contamination. Examples of relevant variables include the second distance between the LiDAR and the target object (e.g., a charging station); the robot's rotation direction; the frequency of the LiDAR's detection pulses, and so on, which are not limited by the present invention. The following description uses adjusting the second distance between the LiDAR and the target object (e.g., a charging station) as an example.

[0076] According to a preferred embodiment of the present invention, the value of the second distance between the laser radar and the target object (such as a charging pile) is changed (for example, adjusted from 10 cm to 20 cm), and steps S102-S105 are repeated for multiple measurements to observe whether there is a point in the new group of points whose distance from the new straight line is greater than a threshold. If so, it is further determined whether the position of the point relative to the new straight line is consistent with the position of the previously measured deviation point relative to the straight line. If so, it is determined that there is indeed stain on the laser radar.

[0077] According to a preferred embodiment of the present invention, if the laser radar is indeed contaminated according to the calibration results, a warning message is issued so that it can be cleaned promptly. The warning message can be presented by an electronic device on the robot, such as a voice module, a display screen, an indicator light, etc., which is not limited by the present invention.

[0078] The present invention also provides a robot 20, Figure 7 A schematic diagram of a robot according to an embodiment of the present invention is shown. Figure 7 As shown, the robot 20 includes:

[0079] The main body 21 has a walking mechanism 211;

[0080] A laser radar 22 for detecting the environment around the robot 20;

[0081] The controller 23 is coupled to the walking mechanism 211 and the laser radar 22 , and is configured to control the walking mechanism and the laser radar 22 , and to execute the method 100 described above. It should be noted that the controller 23 is built into the robot 20 .

[0082] The present invention also provides a computer-readable storage medium comprising computer-executable instructions stored thereon, wherein the executable instructions implement the method described above when executed by a controller. The memory may be non-volatile and / or volatile memory. The non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), resistive random access memory (ReRAM), phase change memory (PCRAM), or flash memory. Volatile memory may include random access memory (RAM), registers, or cache. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0083] The method of the present invention can quickly and inexpensively detect whether there are stains on the airborne radar without the assistance of external devices, so that it can be cleaned and maintained in time, reducing abnormal conditions such as robot failure caused by stains attached to the radar affecting the obstacle avoidance effect, which is beneficial to improving the robustness of the robot and customer experience.

[0084] It should be noted that, in the present invention, the robot can work in various environments such as restaurants, hotels, hospitals, libraries, etc., and the present invention does not impose any restrictions.

[0085] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for detecting stains using a laser radar, wherein the laser radar is mounted on a robot, the method comprising: S101: After the robot detects the trigger condition, it stops in front of the target object; The target object is provided with a strong reflective material and a weak reflective material so as to distinguish the target object from other obstacles in the robot's surrounding environment; S102: Controlling the laser radar to transmit detection pulses to the surroundings, receiving echo pulses of the detection pulses, and generating a point cloud based on the echo pulses; S103: Determining whether the laser radar recognizes the target object based on the point cloud; S104: When it is determined that the laser radar recognizes the target object, determining whether there is a point in the point cloud within the field of view corresponding to the target object whose deviation exceeds a threshold; and S105: When there is a point in the point cloud whose deviation exceeds a threshold within the field of view corresponding to the target object, it is determined that there is stain on the laser radar.

2. The method according to claim 1, wherein the trigger condition includes when the robot finishes charging, or when the robot is at a first distance from the target object; The step of stopping in front of the target object includes: The robot stops at a second distance from the target object, where the second distance is greater than the first distance and the range of the second distance is 10 cm-50 cm.

3. The method according to claim 1, wherein the target object has strong reflective material and weak reflective material at a height substantially the same as that of the laser radar, and the strong reflective material and weak luminous material are arranged in a preset arrangement and facing the laser radar.

4. The method according to claim 1, wherein the step of controlling the laser radar to emit detection pulses to the surroundings comprises: The robot is controlled to rotate with the laser radar as the center, and the laser radar is controlled to emit detection pulses to the surroundings to cover the range in the horizontal direction.

5. The method according to claim 1, wherein the step of determining whether the laser radar recognizes the target object comprises: Determining shape characteristics and reflectivity of the point cloud; If the shape characteristics and / or reflectivity correspond to the shape characteristics and / or reflectivity of the strong reflective material and the weak reflective material on the target object, it is determined that the laser radar has identified the target object.

6. The method according to claim 5, wherein the step of determining whether there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object comprises: The points of the point cloud within the field of view corresponding to the target object are divided into a first group of points and a second group of points according to reflectivity, the first group of points corresponding to the strong reflective material, and the second group of points corresponding to the weak reflective material.

7. The method according to claim 6, wherein the step of determining whether there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object comprises: Perform straight line fitting on the first group of points to obtain a first straight line, and determine whether there is a point in the first group of points whose distance from the first straight line exceeds the threshold.

8. The method according to claim 6, wherein the step of determining whether there is a point in the point cloud with a deviation exceeding a threshold within the field of view corresponding to the target object further comprises: Perform straight line fitting on the second group of points to obtain a second straight line, and determine whether there is a point in the second group of points whose distance from the second straight line exceeds the threshold.

9. The method according to any one of claims 1 to 8, further comprising: When it is determined that there is dirt on the laser radar, the steps S102 to S105 are repeated to check the dirt.

10. The method according to claim 9, further comprising: If the calibration result confirms that the laser radar is contaminated, a warning message is issued.

11. The method according to any one of claims 1-8, wherein the target object has continuous grooves and convex blocks, and the strong reflective material and the weak reflective material are respectively arranged on the grooves and convex blocks; the target object includes a charging pile used in conjunction with the robot.

12. A robot comprising: The main body has a walking mechanism; LiDAR, used to detect the environment around the robot; A controller is coupled to the walking mechanism and the laser radar, configured to control the walking mechanism and the laser radar, and configured to execute the method as described in any one of claims 1-11.

13. A computer-readable storage medium comprising computer-executable instructions stored thereon, wherein the computer-executable instructions implement the method according to any one of claims 1 to 11 when executed by a controller.

Images