Robot sensor system self-checking method and robot

Abstract

The present invention provides a method for self-checking a robot sensor system, wherein the sensor system includes a laser radar and a stereo vision sensor installed on the robot, including: determining that the robot's parking position has a preset positional relationship with a target object; controlling the laser radar to emit detection pulses to the surroundings, receiving echo pulses of the detection pulses, and generating a first point cloud based on the echo pulses; determining the effective detection area of ​​the laser radar according to the first point cloud, and determining whether the installation position of the laser radar is correct according to the effective detection area; when it is determined that the installation position of the laser radar is correct, obtaining a second point cloud collected by the stereo vision sensor; and determining whether the installation position of the stereo vision sensor is correct according to the first point cloud and the second point cloud. The technical solution of the present invention can realize rapid detection of whether the installation position of the laser radar is correct, and check and correct the positional relationship between the stereo vision camera and the laser radar, with low time and labor costs and high efficiency.

Description

Technical Field

[0001] The present invention generally relates to the field of intelligent robots, and in particular to a method for self-checking a robot sensor system, 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 more and more popular. Sensors play a very important role in the control of robots. It is with sensors that robots have the perception and response capabilities similar to humans.

[0003] The robot is usually transported to the customer site after being assembled in the factory. However, during transportation, vibration may cause the fastening parts of the sensor, such as screws and bolts, to loosen, causing the installation position of the sensor to change. In addition, changes in temperature and humidity in the robot's surrounding environment may also cause the installation position of the sensor to change. When the installation position of the sensor changes, it is easy to cause the sensor's detection data to be inaccurate, affecting the measurement results and further affecting the normal operation of the robot. Therefore, it is particularly important to detect whether the sensor can work normally. At present, the installation position of the sensor is usually detected by manual visual inspection and other methods, and each time the robot is turned on, it is determined whether each sensor can transmit information normally (i.e., hardware connection detection). However, the time and labor costs are high and the efficiency is low.

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

[0005] In view of one or more of the problems existing in the prior art, the present invention provides a method for self-checking a robot sensor system, wherein the sensor system includes a laser radar and a stereo vision sensor installed on the robot, and the method includes:

[0006] Determine that the parking position of the robot has a preset position relationship with a preset target object;

[0007] Controlling the laser radar to transmit a detection pulse to the surroundings, receiving an echo pulse of the detection pulse, and generating a first point cloud based on the echo pulse;

[0008] Determine an effective detection area of ​​the laser radar according to the first point cloud, and determine whether the installation position of the laser radar is correct according to the effective detection area;

[0009] When it is determined that the installation position of the laser radar is correct, obtaining a second point cloud collected by the stereo vision sensor; and

[0010] Whether the installation position of the stereo vision sensor is correct is determined according to the first point cloud and the second point cloud.

[0011] According to one aspect of the present invention, the preset target object has a strong reflective strip and a weak reflective strip at a height substantially the same as that of the laser radar, and the strong reflective strip and the weak reflective strip are arranged in a preset arrangement and face the laser radar.

[0012] According to one aspect of the present invention, the step of determining whether the installation position of the laser radar is correct based on the effective detection area includes: comparing the effective detection area with the preset ideal detection area of ​​the laser radar to determine whether the installation position of the laser radar is correct.

[0013] According to one aspect of the present invention, the step of determining whether the installation position of the laser radar is correct based on the effective detection area includes: if the difference between the effective detection area and the ideal detection area is less than a first threshold, determining that the installation position of the laser radar is correct; if the difference between the two is not less than the first threshold, determining that the installation position of the laser radar is incorrect.

[0014] According to one aspect of the present invention, the step of determining the effective detection area of ​​the laser radar comprises:

[0015] determining a distance and a reflectivity based on the first point cloud;

[0016] Performing denoising and straight line fitting on the first point cloud;

[0017] The effective detection area of ​​the laser radar is determined by the distance, reflectivity and the fitted straight line.

[0018] According to one aspect of the present invention, it also includes: when the installation position of the laser radar is incorrect, an alarm message of the incorrect installation position of the laser radar is output.

[0019] According to one aspect of the present invention, it also includes:

[0020] Performing point cloud filtering on the second point cloud to remove noise points in the second point cloud;

[0021] Plane fitting is performed based on the second point cloud.

[0022] According to one aspect of the present invention, the step of determining whether the installation position of the stereo vision sensor is correct includes: when a straight line fitted according to the first point cloud overlaps with a plane fitted according to the second point cloud, determining whether the installation position of the stereo vision sensor is correct.

[0023] According to one aspect of the present invention, the step of determining whether the installation position of the stereoscopic vision sensor is correct further comprises:

[0024] When the straight line fitted according to the first point cloud overlaps with the plane fitted according to the second point cloud, determining the relative position relationship between the laser radar and the stereo vision sensor;

[0025] When the relative position and posture relationship is less than the ideal position and posture relationship by less than a threshold value, it is determined that the installation position of the stereoscopic vision sensor is correct;

[0026] When the difference between the relative posture relationship and the ideal posture relationship is greater than a threshold, it is determined that the installation position of the stereoscopic vision sensor is abnormal, and the position parameters of the stereoscopic vision sensor are corrected according to the relative posture relationship.

[0027] The present invention also provides a robot, comprising:

[0028] A main body having a walking mechanism;

[0029] Sensor systems, including lidar and stereo vision sensors, to detect the robot’s surroundings;

[0030] The controller is coupled to the walking mechanism and the sensor system, configured to control the walking mechanism and the sensor system, and configured to execute the method as described above.

[0031] The present invention also provides a computer-readable storage medium, comprising computer-executable instructions stored thereon, wherein the executable instructions implement the method as described above when executed by a processor.

[0032] By adopting the technical solution of the present invention, it is possible to quickly detect whether the installation position of the laser radar is correct, and check and correct the positional relationship between the stereo vision camera and the laser radar. The time and labor costs are low and the efficiency is high. It can make up for the current service robot's inability to professionally self-check when providing on-site technical support to customers, and is conducive to improving the efficiency and professionalism of on-site robot deployment and after-sales service for customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] 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:

[0034] Figure 1 A flowchart showing a method for self-checking a robot sensor system according to an embodiment of the present invention is shown;

[0035] Figure 2 A schematic diagram of a preset target object according to an embodiment of the present invention is shown;

[0036] Figure 3A schematic diagram showing the positional relationship between a robot and a preset target object according to an embodiment of the present invention;

[0037] Figure 4A A schematic diagram showing a point cloud fitting straight line when the laser radar is installed in a correct position according to a preferred embodiment of the present invention;

[0038] Figure 4B A schematic diagram showing a point cloud fitting straight line when the laser radar is installed in an incorrect position according to a preferred embodiment of the present invention; and

[0039] Figure 5 A schematic diagram of a robot according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0040] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0041] In the description of the present invention, 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", "clockwise", "counterclockwise" 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 invention and simplifying the description, rather than indicating or implying 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 limiting the present invention. In addition, the terms "first" and "second" are only used 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 of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0042] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be directly connected, or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is lower in level than the second feature.

[0044] The disclosure below provides many different embodiments or examples to realize different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplicity and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific examples of processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0045] The preferred embodiments of the present invention are described below in conjunction with 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.

[0046] The present invention provides a method 100 for self-checking a robot sensor system. Before introducing the method 100, the principle that a change in sensor position affects the normal operation of the robot is first introduced.

[0047] Normally, the robot has multiple sensors, each of which is installed in a fixed position on the robot and has a corresponding measurement range. When the installation position of the sensor changes, the sensor may tilt or shift to a certain extent, causing partial obstruction between the sensor and the robot's shell or internal data cable. When detecting, the sensor mistakenly thinks that there is an obstacle in the part obstructed by the robot's shell or data cable, and obtains incorrect measurement results, which in turn causes the robot to be unable to correctly build maps based on the incorrect measurement results, affecting the robot's positioning, navigation, and obstacle avoidance.

[0048] Now that the principle that the change in sensor position affects the normal operation of the robot has been understood, the method 100 is described in detail below.

[0049] Figure 1A flowchart of a method 100 for self-inspection of a robot sensor system according to an embodiment of the present invention is shown. The sensor system includes a laser radar and a stereo vision sensor installed on the robot. The method includes steps S101-S105. Each step of the method 100 is described in detail below.

[0050] In step S101 , it is determined that the parking position of the robot has a preset position relationship with a preset target object.

[0051] Figure 2 FIG. 1 is a schematic diagram of a preset target object according to an embodiment of the present invention, wherein the preset target object is used to assist the sensor system in performing self-test. Figure 2 As shown, the preset target object can be a number of flat plates with a certain size that can cover the field of view of the laser radar and the stereo vision sensor. The preset height of the preset target object has a number of strong reflective strips and a number of weak reflective strips, and the strong reflective strips and the weak reflective strips are arranged in a preset arrangement and facing the laser radar. According to one embodiment of the present invention, the preset height is, for example, substantially the same height as the laser radar. It should be understood that in actual use, in order to enable the laser radar to detect the strong reflective strips and the weak reflective strips, the heights of the strong reflective strips and the weak reflective strips are usually slightly higher than the height of the laser radar. In addition, the strong reflective strips and the weak reflective strips can be arranged in an equidistant alternating arrangement. Of course, they can also be arranged in other arrangements, specifically, for example, multiple (for example, two) strong reflective strips are arranged alternately with one weak reflective strip, multiple (for example, two) weak reflective strips are arranged alternately with one strong reflective strip, etc., and the present invention is not limited thereto. In addition, the present invention does not limit the width, quantity, and specific material of the strong reflective strips and the weak reflective strips. Specifically, the material of the strong reflective strips is, for example, diamond reflective film, gold, copper, aluminum, etc., and the material of the weak reflective strips is, for example, black plastic or cloth, etc. The purpose of providing the strong reflective strips and the weak reflective strips on the preset target object is to distinguish the preset target object from other obstacles in the robot's surrounding environment. It is easy to understand that the more distinctive the arrangement of the strong reflective strips and the weak reflective strips, the greater the difference in reflectivity, and the easier it is to distinguish the preset target object from other obstacles in the robot's surrounding environment. The above embodiment introduces the situation regarding the preset target object, so what kind of preset position relationship is there between the robot's parking position and the preset target object? The following will continue to describe.

[0052] Figure 3 FIG. 1 is a schematic diagram showing the positional relationship between a robot and a preset target object according to an embodiment of the present invention. Figure 3As shown, the robot is docked in front of the preset target object, the docking position of the robot is at a preset distance (e.g., 10cm-50cm) from the preset target object, the robot is perpendicular to the plane where the preset target object is located, and faces the preset target object.

[0053] In step S102, the laser radar is controlled to transmit a detection pulse to the surroundings, receive an echo pulse of the detection pulse, and generate a first point cloud based on the echo pulse.

[0054] The present invention does not limit the type of laser radar. For a service robot such as a food delivery robot, the laser radar is preferably a single-line laser radar. The single-line laser radar has a fast scanning speed, high resolution, and high reliability. It is faster than multi-line and 3D laser radars in angular frequency and sensitivity response. Therefore, it is more accurate in the distance and accuracy of detecting surrounding obstacles. The single-line laser radar usually works with a rotating mechanism, which is responsible for rotating the laser radar at a certain frequency, thereby realizing scanning and detection of a certain field of view in the horizontal direction to generate a first point cloud.

[0055] In step S103, the effective detection area of ​​the laser radar is determined according to the first point cloud, and whether the installation position of the laser radar is correct is determined according to the effective detection area.

[0056] According to a preferred embodiment of the present invention, the distance and reflectivity are determined based on the first point cloud, so as to determine whether the laser radar has identified the preset target object. The first point cloud is a data set of points in the laser radar coordinate system, and the points contain rich information, such as two-dimensional coordinates (x j ,y j )(for single-line radar) or three-dimensional coordinates (x j ,y j ,z j ) (for multi-line or 3D laser radar), reflectivity, time, etc. If the reflectivity of the point matches the reflectivity of the strong reflective strip and / or weak reflective strip on the preset target, and the distance of the target obtained by the time of the point matches the distance of the preset target, it can be basically determined that the laser radar has identified the preset target. Laser radar performs ranging based on time of flight (TOF), which can be calculated according to the following formula:

[0057] d = c × t / 2, where c is the speed of light, c = 3 × 10 8 m / s, t is the flight time of the pulse.

[0058] In order to further determine that the laser radar has identified the preset target and determine the effective detection area of ​​the laser radar, it is also necessary to perform denoising and straight line fitting on the first point cloud. The reason for the generation of noise is, for example, that the robot is disturbed by ambient light, smoke, etc. in its working environment (such as a restaurant). The purpose of removing noise is to reduce the interference of noise on the real point cloud data, improve the accuracy of detection, and facilitate subsequent processing. According to a preferred embodiment of the present invention, the first point cloud can be denoised by a radius filtering method. Specifically, the first point cloud can be traversed, and each point in the first point cloud can be specified to be centered on the point, and there are at least 10 adjacent points within a radius range of a preset radius (such as 0.05m), otherwise the point is identified as a noise point (i.e., an outlier point), and the noise point is removed. It should be understood that this embodiment is only an example and does not limit the preset radius size and / or the number of neighboring points. According to a preferred embodiment of the present invention, the least squares method can be used to perform straight line fitting on the denoised first point cloud to obtain a fitting straight line, and the effective detection area of ​​the laser radar can be determined by fitting the straight line. Once the effective detection area of ​​the laser radar is determined, whether the installation position of the laser radar is correct can be determined based on the effective detection area, which is described in detail below.

[0059] According to a preferred embodiment of the present invention, the effective detection area of ​​the laser radar can be compared with its ideal detection area, and the gap between the effective detection area and the ideal detection area is calculated. If the gap is less than a first threshold value (for example, 1% or 3%), it is determined that the installation position of the laser radar is correct; if the gap between the two is not less than the first threshold value (for example, 1% or 3%), it is determined that the installation position of the laser radar is incorrect.

[0060] According to another preferred embodiment of the present invention, it is also possible to determine whether the installation position of the laser radar is correct by using the shape characteristics of the fitting straight line.

[0061] Figure 4A A schematic diagram of a point cloud fitting straight line when the laser radar is installed in the correct position according to a preferred embodiment of the present invention is shown. Figure 4B FIG. 1 is a schematic diagram showing a point cloud fitting straight line when the laser radar is installed in an incorrect position according to a preferred embodiment of the present invention, referring to FIG. Figure 4A , the fitting line is relatively straight, indicating that the generated points are basically at the same height, which further indicates that the installation position of the laser radar is correct; otherwise, Figure 4B The fitting straight line is crooked, indicating that the generated points are not at the same height, which further indicates that the installation position of the laser radar has changed. This is because during the detection process, the laser radar vibrates due to the loosening of its fastening components such as screws and bolts, resulting in the generated points being at different heights.

[0062] According to a preferred embodiment of the present invention, when it is determined that the installation position of the laser radar is incorrect, an alarm message of the incorrect installation position of the laser radar is output, and the installation position of the laser radar is corrected.

[0063] The above embodiment introduces how to determine whether the installation position of the laser radar is correct. In addition to the laser radar, the robot sensor system also includes a stereo vision sensor. How to determine whether the installation position of the stereo vision sensor is correct is described in detail below.

[0064] Ideally, the LiDAR and stereo vision sensors are mounted in fixed positions on the robot (refer to Figure 5 ), the laser radar and the stereo vision sensor have a preset posture relationship, so when it is determined that the installation position of the laser radar is correct, the laser radar can be used to detect whether the installation position of the stereo vision sensor is correct. Next, continue the description.

[0065] In step S104, when it is determined that the installation position of the laser radar is correct, the second point cloud collected by the stereo vision sensor is obtained. The second point cloud is a data set of points in the coordinate system of the stereo vision sensor, and the points in the second point cloud also contain rich information, such as the three-dimensional coordinates of the points (xv, yv, zv), etc. When the second point cloud is obtained, in order to facilitate subsequent processing, the second point cloud is filtered (such as radius filtering) to remove noise points in the second point cloud, and a plane fitting is performed based on the second point cloud to obtain a fitting plane.

[0066] In step S105, it is determined whether the installation position of the stereo vision sensor is correct based on the first point cloud and the second point cloud.

[0067] According to a preferred embodiment of the present invention, when the straight line fitted according to the first point cloud (i.e., the fitted straight line) overlaps with the plane fitted according to the second point cloud (i.e., the fitted plane), it is determined whether the installation position of the stereo vision sensor is correct. Specifically, the straight line equation can be obtained according to the straight line fitted according to the first point cloud (i.e., the fitted straight line), and the plane equation can be obtained according to the plane fitted according to the second point cloud (i.e., the fitted plane).

[0068] The straight line equation can be expressed by the standard straight line equation, as shown in the following formula (1-1):

[0069] Ajx+Bjy+Bj=0 (1-1)

[0070] The plane equation can be expressed by the standard plane equation formula, as shown in the following formula (1-2):

[0071] Avx+Bvy+Cvz+Dv=0 (1-2)

[0072] According to the three-dimensional coordinates (xj, yj, zj) of the points of the first point cloud, the parameters of the straight line equation, namely Aj, Bj and Bj, can be obtained. By obtaining the parameters of the straight line equation, the specific expression of the straight line equation can be obtained. Similarly, according to the three-dimensional coordinates (xv, yv, zv) of the points of the second point cloud, the parameters of the plane equation, namely Av, Bv, Cv and Dv, can also be obtained. By obtaining the parameters of the plane equation, the specific expression of the plane equation can be obtained. The relative posture relationship between the laser radar and the stereo vision sensor can be determined based on the straight line equation and the plane equation.

[0073] According to a preferred embodiment of the present invention, the actual relative posture relationship between the laser radar and the stereo vision sensor can be compared with their ideal posture relationship. When the difference between the relative posture relationship and the ideal posture relationship is less than a threshold, it is determined that the installation position of the stereo vision sensor is correct; when the difference between the relative posture relationship and the ideal posture relationship is greater than a threshold, it is determined that the installation position of the stereo vision sensor is abnormal. The relative posture relationship includes rotation amounts θx, θy, θz and translation amounts tx, ty, tz. The rotation amounts θx, θy, θz are the rotation amounts around the x-axis, y-axis and z-axis respectively, and the translation amounts tx, ty, tz are the translation amounts along the x-axis, y-axis and z-axis respectively.

[0074] According to a preferred embodiment of the present invention, when the difference between the relative posture relationship (e.g., rotation amount) and the ideal posture relationship (e.g., rotation amount) is less than a threshold value (e.g., 0.5°), it is determined that the installation position of the stereoscopic vision sensor is correct; when the difference between the relative posture relationship (e.g., offset) and the ideal posture relationship (e.g., rotation amount) is greater than a threshold value (e.g., 0.5°), it is determined that the installation position of the stereoscopic vision sensor is abnormal.

[0075] According to another preferred embodiment of the present invention, when the difference between the relative posture relationship (e.g., offset) and the ideal posture relationship (e.g., offset) is less than a threshold value (e.g., 1 mm), it is determined that the installation position of the stereoscopic vision sensor is correct; when the difference between the relative posture relationship (e.g., offset) and the ideal posture relationship (e.g., offset) is greater than a threshold value (e.g., 1 mm), it is determined that the installation position of the stereoscopic vision sensor is abnormal.

[0076] According to a preferred embodiment of the present invention, when it is determined that the installation position of the stereo vision sensor is correct, information that the installation position of the stereo vision sensor is normal is output. When it is determined that the installation position of the stereo vision sensor is abnormal, an alarm message that the installation position of the stereo vision sensor is wrong is output, and the position parameters of the stereo vision sensor are corrected according to the relative posture relationship, that is, the robot will process according to the actual relative posture relationship between the stereo vision sensor and the laser radar without manual intervention.

[0077] The above embodiment introduces the situation where the preset target object is a flat plate. It should be understood that when the preset target object is multiple (for example, two) flat plates, since the multiple flat plates are connected to each other at a certain angle, the detection pulses emitted by the laser radar can be more concentratedly incident on the preset target object, so that the point cloud obtained by the laser radar has more shape characteristics, and the laser radar can more easily determine its effective detection area, and then determine whether its installation position is correct.

[0078] The present invention also provides a robot, Figure 5 A schematic diagram of a robot 20 according to an embodiment of the present invention is shown. Figure 5 As shown, the robot 20 comprises:

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

[0080] A sensor system 22, including a laser radar 221 and a stereo vision sensor 222, for detecting the environment around the robot 20; and

[0081] The controller 23 is coupled to the walking mechanism 211 and the sensor system 22 , and is configured to control the walking mechanism 211 and the sensor system 22 , and is configured to execute the method as described above. The controller 23 is actually located inside the robot 20 .

[0082] The present invention also provides a computer-readable storage medium, including computer executable instructions stored thereon, and the executable instructions implement the method as described above when executed by a processor. The computer-readable storage medium includes but is not limited to any type of memory, and the present invention does not limit the type of memory. The memory can be non-volatile and / or volatile memory. The non-volatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a variable resistive memory (ReRAM), a phase change memory (PCRAM) or a flash memory (Flash Memory). Volatile memory may include a random access memory (RAM), a register or a cache memory (cache). As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0083] By adopting the technical solution of the present invention, it is possible to quickly detect whether the installation position of the laser radar is correct, and check and correct the positional relationship between the stereo vision camera and the laser radar. The time and labor costs are low and the efficiency is high. It can make up for the current service robot's inability to professionally self-check when providing on-site technical support to customers, and is conducive to improving the efficiency and professionalism of on-site robot deployment and after-sales service for customers.

[0084] It should be noted that the preset targets in the above embodiments are several additional flat panels. In actual applications, the strong reflective strips and weak reflective strips can also be attached to other locations such as walls and doors. The preset targets are not limited to flat panels, but can also be other objects, which is not limited by the present invention. In addition, the present invention only takes the restaurant robot as an example, which does not constitute a limitation to the present invention. That is to say, the robot can also work in other scenarios, including but not limited to hospitals, libraries, shopping malls, etc.

[0085] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is 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 can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for self-checking a robot sensor system, wherein the sensor system comprises a laser radar and a stereo vision sensor installed on the robot, and the method comprises: Determine that the parking position of the robot has a preset position relationship with a preset target object; The robot stops in front of the preset target object, the stopping position of the robot is at a preset distance from the preset target object, the robot and the plane where the preset target object is located are perpendicular to each other, and the robot faces the preset target object; Controlling the laser radar to transmit a detection pulse to the surroundings, receiving an echo pulse of the detection pulse, and generating a first point cloud based on the echo pulse; Determine an effective detection area of ​​the laser radar according to the first point cloud, and determine whether the installation position of the laser radar is correct according to the effective detection area; When it is determined that the installation position of the laser radar is correct, obtaining a second point cloud collected by the stereo vision sensor; and Whether the installation position of the stereo vision sensor is correct is determined according to the first point cloud and the second point cloud.

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

3. The method according to claim 1, wherein the step of determining whether the installation position of the laser radar is correct according to the effective detection area comprises: The effective detection area is compared with the preset ideal detection area of ​​the laser radar to determine whether the installation position of the laser radar is correct.

4. According to the method of claim 3, the step of determining whether the installation position of the laser radar is correct according to the effective detection area comprises: If the difference between the effective detection area and the ideal detection area is less than a first threshold, it is determined that the installation position of the laser radar is correct; If the difference between the two is not less than the first threshold, it is determined that the installation position of the laser radar is incorrect.

5. The method according to claim 1, wherein the step of determining the effective detection area of ​​the laser radar comprises: determining a distance and a reflectivity based on the first point cloud; Performing denoising and straight line fitting on the first point cloud; The effective detection area of ​​the laser radar is determined by the distance, reflectivity and the fitted straight line.

6. The method according to claim 1, further comprising: When the installation position of the laser radar is incorrect, an alarm message indicating that the laser radar is installed in an incorrect position is output.

7. The method according to claim 1 or 5, further comprising: Performing point cloud filtering on the second point cloud to remove noise points in the second point cloud; Plane fitting is performed based on the second point cloud.

8. The method according to claim 7, wherein the step of determining whether the installation position of the stereo vision sensor is correct comprises: When the straight line fitted according to the first point cloud overlaps with the plane fitted according to the second point cloud, it is determined whether the installation position of the stereoscopic vision sensor is correct.

9. The method according to claim 8, wherein the step of determining whether the installation position of the stereo vision sensor is correct further comprises: When the straight line fitted according to the first point cloud overlaps with the plane fitted according to the second point cloud, determining the relative position relationship between the laser radar and the stereo vision sensor; When the relative position and posture relationship is less than the ideal position and posture relationship by less than a threshold value, it is determined that the installation position of the stereoscopic vision sensor is correct; When the difference between the relative posture relationship and the ideal posture relationship is greater than a threshold, it is determined that the installation position of the stereoscopic vision sensor is abnormal, and the position parameters of the stereoscopic vision sensor are corrected according to the relative posture relationship.

10. A robot comprising: A main body, having a walking mechanism; A sensor system, including lidar and stereo vision sensors, to detect the robot’s surroundings; A controller is coupled to the walking mechanism and the sensor system, configured to control the walking mechanism and the sensor system, and configured to execute the method as described in any one of claims 1-9.

11. A computer-readable storage medium, comprising computer-executable instructions stored thereon, wherein the executable instructions implement the method according to any one of claims 1 to 9 when executed by a processor.

Images