Anomaly detection method and apparatus, and mobile robot and storage medium

Abstract

An anomaly detection method and apparatus, and a mobile robot and a storage medium. The method comprises: by means of a mobile robot, controlling a first ranging device to perform ranging, so as to obtain a plurality of pieces of ranging data (S101); and by means of the mobile robot, and on the basis of whether the ranging data is empty, or on the basis of whether the proportion of ranging data falling below a first preset value in said ranging data exceeds a preset threshold value, determining whether the ranging performed by the first ranging device is abnormal (S102), wherein the ranging data is data acquired by the first ranging device during the motion of the mobile robot.

Description

Anomaly detection methods, devices, mobile robots, and storage media Cross-references to related applications

[0001] This disclosure claims priority to Chinese patent application No. 202411649021.6, filed on November 18, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to, but is not limited to, the field of anomaly detection technology, and in particular to anomaly detection method, apparatus, mobile robot, and storage medium. Background Technology

[0003] For ranging devices, such as those using Direct Time-of-Flight (DTof) for single-point upward ranging, ranging anomalies may occur, which may manifest as no ranging result or incorrect ranging. Summary of the Invention

[0004] In view of this, the present disclosure provides at least one anomaly detection method, apparatus, mobile robot, and storage medium.

[0005] The technical solution of this disclosure embodiment is implemented as follows:

[0006] On one hand, this disclosure provides an anomaly detection method applied in a mobile robot. The anomaly detection method includes:

[0007] The mobile robot controls the first ranging device to perform ranging and obtain multiple ranging data.

[0008] The mobile robot determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty or whether the proportion of ranging data below a first preset value in the ranging data exceeds a preset threshold.

[0009] The ranging data is the data acquired by the first ranging device when the mobile robot is moving.

[0010] On the other hand, this disclosure provides an anomaly detection device, installed in a mobile robot, the anomaly detection device including:

[0011] The ranging component, controlled by the mobile robot, performs ranging using a first ranging device to obtain multiple ranging data points; and

[0012] The determination component, through the mobile robot, determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty, or whether the proportion of ranging data below a first preset value exceeds a preset threshold.

[0013] The ranging data is the data acquired by the first ranging device when the mobile robot is moving.

[0014] In another aspect, embodiments of this disclosure provide a mobile robot, including a memory and a processor. The memory stores a computer program that can run on the processor, and the processor executes the program to implement some or all of the steps in the above-described method.

[0015] In another aspect, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements some or all of the steps in the above-described method.

[0016] In another aspect, embodiments of this disclosure provide a computer program product including computer program instructions stored in a computer-readable storage medium and adapted to be invoked and executed by a processor to cause a computer device having the processor to perform the steps of the method described in any of the above embodiments.

[0017] In another aspect, embodiments of this disclosure provide a computer program including computer-readable code, which, when run in a computer device, implements the methods described in any of the above embodiments. Attached Figure Description

[0018] Figure 1 is a flowchart illustrating an anomaly detection method provided in an embodiment of this disclosure;

[0019] Figure 2 is a structural schematic diagram of a sweeping robot provided in an embodiment of this disclosure;

[0020] Figure 3 is a flowchart illustrating an example of an anomaly detection method provided in this embodiment of the present disclosure;

[0021] Figure 4 is a schematic diagram of an anomaly detection device provided in an embodiment of this disclosure;

[0022] Figure 5 is a structural schematic diagram of a mobile robot provided in an embodiment of this disclosure. Detailed Implementation

[0023] To make the technical solutions and advantages of this disclosure clearer, the technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this disclosure. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0024] In the following description, references to "some embodiments" describe a subset of all possible embodiments; however, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for descriptive purposes only and is not intended to limit this disclosure.

[0026] According to related technologies, if the ranging device itself does not detect an abnormal state, it is impossible to determine that the ranging device is malfunctioning.

[0027] To address the inability to detect anomalies in ranging devices within mobile robots, this disclosure provides an anomaly detection method applied to mobile robots. Figure 1 is a flowchart illustrating an anomaly detection method provided in this disclosure. As shown in Figure 1, the anomaly detection method may include the following steps S101 and S102.

[0028] S101: The first ranging device is controlled by a mobile robot to measure distances and obtain multiple ranging data.

[0029] In order to achieve anomaly detection of the first ranging device in the mobile robot, in this embodiment of the disclosure, after receiving an anomaly detection command, the mobile robot can control the first ranging device to perform ranging, thereby obtaining multiple ranging data, wherein the ranging data is the data acquired by the first ranging device when the mobile robot is moving.

[0030] In this embodiment of the disclosure, the mobile robot can determine its detection position before controlling the first ranging device to perform distance measurement. It should be noted that the mobile robot in this embodiment can be a sweeping robot for cleaning floors, or a robot for providing certain service functions; this embodiment does not limit the scope of the application.

[0031] The mobile robot includes at least two ranging devices, namely a first ranging device and a second ranging device. The present invention mainly focuses on detecting whether the first ranging device has a ranging abnormality.

[0032] In this embodiment of the disclosure, the mobile robot obtains an anomaly detection instruction, which may be an anomaly detection activation operation issued by the user to the mobile robot's user interface (UI), causing the mobile robot to generate an anomaly detection instruction, or it may be an anomaly detection instruction generated by the mobile robot based on the ranging result of the first ranging device in a specific area (e.g., the target area described below). This embodiment of the disclosure does not limit the specific anomaly detection instruction.

[0033] Upon receiving an anomaly detection command, the mobile robot determines its detection position. The detection data (i.e., the height of the detection position) at this position is greater than a preset height value. This detection data is based on historical map information or determined using any of the robot's ranging devices. In other words, a position with a height greater than the preset value can be selected from historical map information and designated as the detection position. Alternatively, a position with a height greater than the preset value can be determined using the ranging of any ranging device. This allows the mobile robot to determine a suitable detection position for checking whether the ranging of the first ranging device is abnormal.

[0034] It should be noted that both the first and second ranging devices described above have the function of measuring the distance between the mobile robot and the object corresponding to the mobile robot. Specifically, the first ranging device is used to measure the distance between the mobile robot and the object, where the object is located above the mobile robot. For example, the first ranging device may use a DTof (Digital Transient Of) for distance measurement, while the second ranging device may use a line laser or a beam array for distance measurement.

[0035] The number of detection locations of the mobile robot can be one, two, or more, and this embodiment does not limit this.

[0036] In this way, the mobile robot can determine the detection location.

[0037] After determining the detection location, the mobile robot controls its own movement to reach the detection location.

[0038] In this embodiment of the disclosure, when there is one detection position, the mobile robot controls itself to move to the detection position, and controls the first ranging device to perform distance measurement at the detection position; when there are two or more detection positions, the mobile robot controls itself to move to each detection position in sequence, and controls the first ranging device to perform distance measurement at each detection position.

[0039] Through S101, the mobile robot controls the first ranging device to measure distance, thereby obtaining multiple ranging data.

[0040] It should be noted that, for the first ranging device, the mobile robot needs to be moved to the detection position for ranging, while for the second ranging device, ranging at the detection position can be performed at the detection position or at a location adjacent to the detection position. This embodiment does not limit the measurement in this way.

[0041] In addition, when there is only one detection position, the first ranging device is controlled to complete the ranging of that detection position to obtain multiple ranging data. Only then is the ranging of the detection position considered complete. When there are two or more detection positions, the first ranging device needs to be controlled to complete the ranging of each detection position in sequence to obtain multiple ranging data. Only then is the ranging of the detection position considered complete.

[0042] It should be noted that, for each detection position, the mobile robot moves at each detection position to control the first ranging device to collect ranging data. In this way, multiple ranging data can be obtained for each detection position.

[0043] Therefore, when there is only one detection location, the above ranging data refers to the ranging data for that detection location, which may include multiple values. When there are two or more detection locations, the above ranging data includes the ranging data for each detection location, which may include multiple values.

[0044] S102: The mobile robot determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty or whether the proportion of ranging data below the first preset value exceeds a preset threshold.

[0045] After obtaining multiple ranging data points in S101, in S102, the mobile robot determines whether the ranging of the first ranging device is abnormal based on the ranging data. This can be determined by checking if the ranging data is empty, or by checking if the proportion of ranging data points below a first preset value exceeds a preset threshold. This embodiment of the present disclosure does not limit the scope of the determination.

[0046] To determine whether an anomaly detection should be performed, in some embodiments, prior to S101, the following may also be included:

[0047] The mobile robot detects the set of ranging values ​​of the first ranging device, and based on the set of ranging values, it determines whether the mobile robot performs anomaly detection. The set of ranging values ​​includes the ranging values ​​of the first ranging device within a preset time period.

[0048] Understandably, taking the first ranging device as an upward ranging device as an example, the mobile robot can detect the set of ranging values ​​of the upward ranging device, wherein the set of ranging values ​​includes the ranging values ​​of the upward ranging device within a preset time period.

[0049] In this embodiment of the disclosure, the mobile robot obtains a set of ranging values ​​by acquiring the ranging values ​​of the first ranging device within a preset time period, and then determines whether the mobile robot should perform anomaly detection based on the set of ranging values. For example, a preset anomaly detection condition is set, and the robot checks whether the set of ranging values ​​meets the preset anomaly detection condition. If the condition is met, anomaly detection is determined to be performed; otherwise, anomaly detection is determined not to be performed.

[0050] In this way, by obtaining the set of ranging values ​​from the first ranging device, it is possible to determine whether to perform anomaly detection based on the set of ranging values, thus enabling the anomaly detection process to be triggered accurately.

[0051] In order to obtain anomaly detection instructions, in some embodiments, it is determined whether the mobile robot performs anomaly detection, including:

[0052] If the ranging value of the first ranging device is empty within a preset time period, or if the ranging value below the second preset value exceeds a preset proportion, the mobile robot is determined to perform an anomaly detection.

[0053] The second preset value may be equal to or unequal to the first preset value, and this disclosure does not impose any restrictions on this.

[0054] Understandably, when the positioning of the mobile robot indicates that the mobile robot is in the target area, the ranging result (i.e., the set of ranging values) of the first ranging device in the target area is obtained; when the ranging value within a preset time period in the ranging result of the target area is empty, an anomaly detection instruction is generated and an anomaly detection is performed; or, when the ranging value lower than the second preset value in the set of ranging values ​​exceeds a preset proportion, an anomaly detection instruction is generated and an anomaly detection is performed.

[0055] In this embodiment of the disclosure, the mobile robot can know its current location through its own positioning function. If the positioning location indicates that the mobile robot is in a target area, wherein the distance measurement value of the target area (i.e., the height of the target area) is greater than a corresponding preset value, and the area of ​​the target area is greater than a corresponding preset value, that is, the distance measurement result of the area where the mobile robot is located (i.e., the height of the area is greater than a corresponding preset value, and the area of ​​the area is greater than a corresponding preset value), then the distance measurement result of the first ranging device in the target area is obtained.

[0056] Furthermore, the mobile robot can obtain the ranging values ​​within a preset time period from the ranging results of the target area. This preset time period is a period of time before the acquisition time. Then, it can determine whether the ranging values ​​within the preset time period are empty. If they are, it means that the first ranging device cannot measure the distance at this time, thereby activating the anomaly detection function and generating an anomaly detection command.

[0057] If not, first determine whether the distance values ​​in the distance measurement value set that are lower than the second preset value exceed the preset proportion. That is, first calculate the total number of distance measurement values ​​within the preset time period, and count the number of distance measurement values ​​that are lower than the second preset value within the preset time period. Then calculate the ratio to obtain the proportion of distance measurement values ​​in the distance measurement value set that are lower than the second preset value. When the proportion is greater than the preset proportion, the anomaly detection function can be activated to generate an anomaly detection command.

[0058] Thus, by acquiring the set of ranging values ​​of the first ranging device when the mobile robot is in the target area, it is determined whether to activate the anomaly detection function, so that the first ranging device can activate the anomaly detection function in a timely manner when an anomaly occurs.

[0059] To obtain more accurate ranging data, in some embodiments, the movement of the mobile robot is performed at the detection location.

[0060] In other words, the movement of a mobile robot is a rotation or movement at the detection position.

[0061] Understandably, during the process of the mobile robot controlling the first ranging device to perform ranging, it needs to control its own movement. This movement can be a rotation at the detection position, such as a full rotation, or other forms of movement that accompany the acquisition action in order to obtain height measurement data of multiple points, such as a "Z" shape, an "S" shape, etc. This disclosure does not limit this.

[0062] Therefore, using the above two methods of movement makes the obtained ranging data more accurate, which is beneficial to improving the accuracy of anomaly detection.

[0063] Regarding the aforementioned detection location, in some embodiments, the detection location is obtained based on historical map information, or it is a location that is greater than a preset distance from the mobile robot.

[0064] Understandably, the detection locations mentioned above can be obtained based on historical map information, or they can be locations greater than a preset distance from the mobile robot (i.e., the machine's position). In other words, either map data is referenced, or locations greater than a preset distance from the machine's position are used to obtain more suitable detection locations, which helps improve the accuracy of anomaly detection.

[0065] Regarding how to obtain the detection location, in some embodiments, when the mobile robot includes historical map information, the detection location is obtained based on the historical map information; when the mobile robot does not include historical map information, the detection location is a position that is greater than a preset distance from the mobile robot (machine position).

[0066] Understandably, the mobile robot checks whether historical map information is included. If it is, it obtains the detection location based on the historical map information. If it is not, it uses a location that is more than a preset distance from the robot's location as the detection location. In this way, historical map information is used first to determine the detection location based on whether it is included.

[0067] Thus, prioritizing the use of historical map information to determine the detection location can identify a more suitable location for anomaly detection. Furthermore, when historical map information is not included, locations greater than a preset distance from the machine position can be used as detection locations. This allows the first ranging device to determine a suitable location for anomaly detection, thereby achieving anomaly detection and improving its accuracy.

[0068] Furthermore, in order to determine a more suitable detection location, some embodiments may also include:

[0069] Information on target areas with height and area greater than corresponding preset values ​​is obtained based on historical map data; and

[0070] The detection location of the mobile robot is obtained based on the target area information.

[0071] In other words, when an anomaly detection instruction is received and the mobile robot includes historical map information, at least one target area is selected from the historical map information; and the detection position of the mobile robot is selected from the target area.

[0072] In some embodiments, the mobile robot can select at least one target region from historical map information, wherein the distance measured by the target region (i.e., the height of the target region) is greater than a preset value corresponding to the height, and the area of ​​the target region is greater than a preset value corresponding to the area. In some embodiments, the mobile robot can first select regions from historical map information whose distance measured by the target region is greater than the preset value corresponding to the height. A region may have multiple distance measured values, and a distance measured by the target region being greater than the preset value corresponding to the height means that each distance measured by the target region is greater than the preset value. After selecting regions whose distance measured by the target region is greater than the preset value corresponding to the height, regions whose area is greater than the preset value corresponding to the area are then identified and designated as target regions, thereby obtaining at least one target region.

[0073] The number of target regions can be one, two, or more than two, and this embodiment does not limit this.

[0074] It should be noted that the target area can be a regular shape, such as a circle or a rectangle, or it can be an irregular shape. This disclosure does not limit this.

[0075] In addition, when the mobile robot selects the detection position from the target area, it can randomly select the detection position from the target area, or it can determine the center position of the target area and then determine the center position of the mobile robot as the detection position. This disclosure does not limit this.

[0076] In this way, the mobile robot first selects a region that meets the requirements from the historical map information, and then selects a detection location from the region that meets the requirements. This makes the detection location more suitable for detecting whether the ranging of the first ranging device is abnormal, thereby improving the accuracy of anomaly detection.

[0077] For two or more target regions, when there are two or more target regions, no two target regions overlap.

[0078] Understandably, when a mobile robot determines at least two target areas from historical map information, in order to improve the rationality of the distribution of detection positions and thus improve the accuracy of anomaly detection, any two target areas do not overlap. In other words, each determined target area does not overlap with the others, thus making the distance between the determined detection positions more reasonable.

[0079] Thus, when historical map information exists locally, the selection of target areas ensures that no two areas overlap, thereby determining evenly distributed detection locations, improving the rationality of the detection location distribution, and thus improving the accuracy of anomaly detection.

[0080] In addition, for situations where the mobile robot does not have local historical map information, in order to determine a suitable detection location, some embodiments may include:

[0081] When the mobile robot does not include historical map information, the detection location is a position outside the preset distance of the robot's location.

[0082] In other words, when the mobile robot does not contain historical map information, the detection location is a position greater than a preset distance from the mobile robot. When an anomaly detection command is received, and the mobile robot does not contain historical map information, the intermediate position is selected from positions at a preset distance from the robot's location.

[0083] The distance to the object at the middle position is measured by the second ranging device, and the distance measurement result at the middle position is obtained.

[0084] If the distance measurement result at the middle position is greater than the third preset value, the middle position will be determined as the detection position of the mobile robot.

[0085] If the distance measurement result at the middle position is less than the third preset value, the position is selected from the positions at a preset distance from the middle position, with the middle position as the center.

[0086] The selected position is redefined as the center position, and the process returns to the step of measuring the distance of the object at the center position using the second ranging device to obtain the distance measurement result of the center position, until the detection positions of the first preset number of mobile robots are obtained.

[0087] Understandably, after receiving an anomaly detection command, the mobile robot needs to determine whether it contains historical map information. If so, it selects the detection location from the historical map information; if not, it can use a second ranging device to select the detection location.

[0088] In order to select the detection position by means of the second ranging device, the mobile robot first selects the middle position from the positions at a preset distance from the machine position, and then controls the second ranging device to measure the distance of the object at the middle position to obtain the distance measurement result of the middle position.

[0089] It should be noted that the mobile robot can be moved based on the ranging principle of the second ranging device. For example, the second ranging device can only measure the distance at the middle position when it is close to the middle position, or the second ranging device can only measure the distance at the middle position when it is in the middle position. The mobile robot can control the second ranging device to measure the distance at the middle position according to the ranging principle of the second ranging device, and obtain the distance measurement result at the middle position.

[0090] Next, the distance measurement result at the middle position is compared with the third preset value. If it is greater than the third preset value, it means that the middle position meets the standard for detection position, so the middle position can be used as the detection position of the mobile robot. If it is less than the third preset value, it means that the middle position does not meet the standard for detection position, so it is necessary to continue to determine the detection position that meets the requirements. Therefore, here, we can take the middle position as the center and select a position from the positions at a preset distance from the middle position, and use it as the middle position. Then, we return to the second ranging device to measure the distance of the object at the middle position and obtain the distance measurement result of the middle position, until the first preset number of detection positions of the mobile robot are obtained.

[0091] Furthermore, in cases where the ranging result at the intermediate position is less than the third preset value, to further determine a suitable detection position, a position can be selected from positions at a preset distance from the current position of the mobile robot, using the current position of the mobile robot as the center. This selected position can then be used as the intermediate position again. The process of returning to the second ranging device to measure the distance of the object at the intermediate position and obtaining the ranging result of the intermediate position can continue until the detection positions of the first preset number of mobile robots are obtained. This embodiment of the present disclosure does not limit this approach.

[0092] The first preset number can be one, two, or more than two. This embodiment of the present disclosure does not limit this.

[0093] Thus, without including historical map information, the second ranging device is used to help filter out the detection locations that meet the requirements, thereby determining the detection locations suitable for anomaly detection of the first ranging device, and thus improving the accuracy of anomaly detection.

[0094] To further improve the accuracy of anomaly detection, in some embodiments, when the first preset number is greater than one, the distance between any two positions in the mobile robot detection positions is greater than a preset distance.

[0095] Understandably, for cases where the first preset number is greater than one, that is, when the mobile robot determines two or more detection positions, the distance between any two detection positions is greater than a preset distance, thus ensuring that the determined detection positions are evenly distributed.

[0096] Furthermore, where practical considerations allow, both the first and second preset numbers are greater than one. The second preset number is the number of detection locations of the mobile robot selected from historical map information. In other words, the number of detection locations determined by the second ranging device and the number of detection locations determined from historical map information are both greater than or equal to two. This is because a larger number of the first and second preset numbers allows for the identification of more detection locations, thus ensuring the accuracy of anomaly detection.

[0097] Thus, for cases where local data does not include historical map information, if the first preset number is greater than one, the distance between any two detection locations is made greater than the preset distance, so that the detection locations cover a larger area as much as possible, thereby improving the rationality of the distribution of detection locations and thus improving the accuracy of anomaly detection.

[0098] Regarding the aforementioned historical map information, in some embodiments, the historical map information is obtained by ranging using a first ranging device or a second ranging device.

[0099] In other words, the aforementioned historical map information can be obtained by ranging through the first ranging device or by ranging through the second ranging device. Here, this embodiment does not specifically limit the specific range.

[0100] In this way, historical map information can be obtained through the first or second ranging device, which provides a reference for determining a suitable and accurate detection location.

[0101] To determine whether the ranging of the first ranging device is abnormal based on ranging data, some embodiments may include:

[0102] If the mobile robot detects only one location and the first proportion is greater than the preset proportion, the ranging of the first ranging device is determined to be abnormal.

[0103] If the mobile robot detects two or more locations, and the proportion of each location is greater than the preset proportion, the ranging of the first ranging device is determined to be abnormal.

[0104] Here, the preset percentage can be understood as the preset threshold in the aforementioned embodiments.

[0105] Understandably, after determining the ranging data, the mobile robot needs to check if the ranging data is empty. If it is empty, it means that the first ranging device cannot perform ranging at this time, so it is determined that the ranging of the first ranging device is abnormal.

[0106] For a mobile robot detecting only one location, the first proportion is the ratio of the number of values ​​in the ranging data that are less than a first preset value to the total number of values ​​in the ranging data. In other words, it is necessary to count the total number of values ​​in the ranging data and the number of values ​​less than the first preset value, and then determine the ratio of the number of values ​​less than the first preset value to the total number of values ​​in the ranging data. If the first proportion is greater than the preset proportion, it indicates that the ranging of the first ranging device is abnormal.

[0107] For cases where the mobile robot detects two or more locations, the second ratio is the ratio of the number of values ​​less than a first preset value at each detection location to the total number of values ​​at each detection location. In other words, it is necessary to count the total number of distance measurements at each detection location and the number of values ​​less than the first preset value at each location, then determine the ratio of the number of values ​​less than the first preset value at each location to the total number of values ​​at each location. If the ratio at each detection location is greater than the preset ratio, it indicates that the distance measurement of the first ranging device is abnormal.

[0108] The preset ratio can be determined based on the ratio of the number of values ​​less than a first preset value at a certain detection position to the total number of values ​​at that detection position when the first ranging device malfunctions. Thus, by comparing the ranging data with the results obtained when the malfunction occurs, based on the different number of detection positions, it can be accurately determined whether the first ranging device is malfunctioning.

[0109] In addition to comparing the ranging data with the results obtained in case of anomalies as described above, other methods can be used to determine whether the ranging of the first ranging device is abnormal. For example, in some embodiments, the following methods can be used to determine whether the ranging of the first ranging device is abnormal:

[0110] If the difference between the measured distance data and the detected distance data does not fall within the preset error range, the ranging of the first ranging device is determined to be abnormal. Here, the detected distance data is the standard value obtained by the first ranging device under normal conditions.

[0111] Understandably, after obtaining the ranging data, the mobile robot can subtract the ranging data from the detection data and check whether the difference falls within the preset error range. If it does, the ranging of the first ranging device is determined to be normal; if it does not, the ranging of the first ranging device is determined to be abnormal.

[0112] It should be noted that since the above ranging data includes multiple ranging values ​​for each detection position, multiple differences can be obtained here. Therefore, it is necessary to determine whether all differences fall within the preset error range. If at least one difference does not fall within the preset error range, the ranging of the first ranging device is determined to be abnormal.

[0113] Of course, multiple differences can also be processed. For example, after removing outliers from multiple differences, the average value can be calculated, and whether the average value falls within a preset error range can be used to determine whether the ranging of the first ranging device is abnormal. This disclosure does not limit this.

[0114] Thus, by determining whether the ranging of the first ranging device is abnormal based on whether the difference between the ranging data and the detection data falls within the preset error range, that is, by comparing the ranging data with the standard value, the accuracy of anomaly detection can be further improved.

[0115] It should be noted that in the embodiments of this disclosure, each value used as a threshold may be equal or unequal. For example, the first preset value, the second preset value, and the third preset value may be equal or unequal, and the preset threshold and the preset ratio may be equal or unequal. This disclosure does not impose any restrictions on this.

[0116] This disclosure provides an anomaly detection method. A mobile robot controls a first ranging device to perform distance measurement, obtaining multiple distance measurement data points. The mobile robot determines whether the distance measurement of the first ranging device is abnormal based on whether the distance measurement data is empty or whether the proportion of distance measurement data below a first preset value exceeds a preset threshold. The distance measurement data is the data acquired by the first ranging device while the mobile robot is moving. In other words, in this disclosure, the mobile robot controls the movement of the mobile robot, enabling the first ranging device to measure distance and obtain multiple distance measurement data points. The method then determines whether the first ranging device is abnormal based on whether the distance measurement data is empty or whether the proportion of distance measurement data below a first preset value exceeds a preset threshold. Here, by acquiring multiple distance measurement data points from the first ranging device during the movement of the mobile robot, the distance measurement data can more comprehensively reflect the actual distance measurement situation of the first ranging device, thereby making the anomaly judgment of the first ranging device more accurate and improving the accuracy of anomaly detection.

[0117] The following examples illustrate the anomaly detection methods described in one or more of the above embodiments.

[0118] Taking a robotic vacuum cleaner as an example, Figure 2 is a structural schematic diagram of a robotic vacuum cleaner provided in an embodiment of this disclosure. As shown in Figure 2, the robotic vacuum cleaner 200 includes: a first ranging device 21 and a second ranging device 22; wherein, the second ranging device 22 may include: a third ranging device 221 and a fourth ranging device 222.

[0119] As shown in Figure 2, the third ranging device 221 uses a line laser for ranging, and the fourth ranging device 222 uses a planar laser array for ranging. With the direction of travel of the robotic vacuum cleaner 200 as the forward direction, the third ranging device 221 and the fourth ranging device 222 are positioned in front of the robotic vacuum cleaner. The first ranging device 21 is a single-point upward ranging device that uses DTof for ranging. As shown in Figure 2, the first ranging device 21 is positioned above the robotic vacuum cleaner 200 and can also be referred to as a DTof device.

[0120] For the aforementioned DTof devices, ranging anomalies may occur, which may manifest as no ranging result or incorrect ranging (for example, the ranging result is usually less than a certain value). If the ranging device itself does not detect the abnormal state, the ranging anomaly cannot be detected.

[0121] Based on the structure of Figure 2 above, Figure 3 is a flowchart illustrating an example of an anomaly detection method provided by an embodiment of this disclosure. As shown in Figure 3, the anomaly detection method may include:

[0122] S301: The robot vacuum cleaner reads the distance measurement value of the first ranging device within a preset time period T.

[0123] Wherein, T is equivalent to the preset duration in the above embodiments.

[0124] S302: Determine if the ranging value is empty. If not, proceed to S303; if yes, proceed to S304.

[0125] S303: Determine whether the proportion of distance values ​​below the preset height A exceeds the preset ratio R. If yes, execute S304; if no, return to execute S301.

[0126] Wherein, A above is equivalent to the second preset value in the above embodiment.

[0127] In this disclosed example, when the robot vacuum cleaner is started in an open area (equivalent to the target area mentioned above), after the robot vacuum cleaner starts, for example, after leaving the base station and / or completing positioning, it can read all the ranging values ​​within a preset time T of the first ranging device. If there is no ranging result (i.e., the ranging value is empty) or the proportion of the ranging values ​​lower than the preset height A exceeds the preset ratio R (e.g., 0 or 30%), then the subsequent abnormal detection strategy of S304-S310 is entered.

[0128] S304: Determine if a historical altimetry map exists locally. If yes, proceed to S305; otherwise, proceed to S306.

[0129] S305: Select an open area from the historical altimetry map, and select detection position P within the open area until the second preset number of detection positions are selected; execute S309.

[0130] S306: Select a middle position at a preset distance S from the current position, control the robot vacuum to move so that the second ranging device measures the height of the object at the middle position, and use this height as the ranging value of the middle position; execute S307. Here, the height of the object can be understood as the distance between the object and the robot vacuum.

[0131] S307: Determine whether the distance measurement value at the middle position is greater than the preset height A. If yes, execute S308; if no, execute S306.

[0132] The preset height A here is equivalent to the third preset value in the above embodiment, that is, the third preset value and the second preset value can be equal in this embodiment.

[0133] S308: Determine the middle position as the detection position until the first preset number of detection positions are obtained; execute S309.

[0134] S309: Control the sweeping robot to move to the detection position, control the first ranging device to measure the distance at the detection position, and obtain the height value of the detection position; execute S310.

[0135] S310: Determine whether the ranging of the first ranging device is abnormal based on the height measurement value of the detection position.

[0136] Here, the robot vacuum cleaner checks whether there is a historical elevation map (equivalent to the historical map information in the above embodiment). The historical elevation map can be recorded by the historical elevation measurement results of at least one of the first or second ranging devices. The historical elevation map records the elevation measurement results of each location. Each location can be a specific location point or a square or rectangular area that can be matched with the historical elevation map, such as a continuous square with a length and width of 5 centimeters generated by dividing the sweeping area.

[0137] If a historical altimetry map exists, a point within an open area on the historical altimetry map (this open area is an area where all altimetry values ​​are higher than a preset height A and the area is greater than a preset size B, equivalent to the target area in the above embodiment; the preset height A here is equivalent to the preset value corresponding to the height in the above embodiment, that is, in this embodiment of the disclosure, the preset value corresponding to the height and the second preset value can be equal; B is equivalent to the preset value corresponding to the area in the above embodiment) is selected as the detection location P.

[0138] The robot vacuum then moves to point P and rotates once, recording the elevation values ​​of the first ranging device (equivalent to the ranging data in the above embodiment). If the proportion of elevation values ​​lower than the preset height A exceeds a preset threshold R1 (e.g., 0), a new open area is searched. If no new open area is found, or after trying N (e.g., 2) open areas, the elevation values ​​at the detection location in each open area all satisfy the condition that the proportion of elevation values ​​lower than the preset height A exceeds the preset threshold R1, then the first ranging device is judged to be abnormal, and the robot vacuum ignores the ranging values ​​of the first ranging device in subsequent cleaning. Since the historical elevation map has already marked the detection location as an open area (elevation value should be greater than or equal to the preset height A), N is preferably 2. That is, in this case, if two consecutive judgments result in an abnormality, then it is truly abnormal.

[0139] If there is no historical height measurement map, then find a location that is greater than a preset distance S (e.g., 1 meter) from the current location of the robot vacuum cleaner. Use a second ranging device to measure the height of the object at that location near that location. Only when the measured height value is greater than the preset height A will the location be determined as the detection location.

[0140] The robot walks to the detection position and rotates once, recording the height measurement value of the first ranging device during this rotation (equivalent to the ranging data in the above embodiment). If the proportion of height measurements below a preset height A exceeds a preset threshold R1, a new detection position is sought. If, after trying M (e.g., 3) detection positions, the height measurement value at each position satisfies the condition that the proportion of height measurements below a preset height A exceeds the preset threshold R1, then the first ranging device is judged to be abnormal, and the robot vacuum cleaner ignores the distance measurement value of the first ranging device in subsequent cleaning.

[0141] In this way, even if the first ranging device malfunctions but the hardware fails to detect the abnormality, the software can determine the ranging abnormality, thus preventing the robot vacuum cleaner from being interfered with in its cleaning behavior by the malfunctioning first ranging device.

[0142] Since there is no historical height measurement map as a reference, it is uncertain whether the detection location is in an open area (the height measurement value should be greater than or equal to the preset height A). M is preferably 3. That is to say, in this case, if the judgment result is abnormal three times in a row, it will be considered as a real abnormality.

[0143] Based on the same inventive concept as the foregoing embodiments, this disclosure provides an anomaly detection device, which is disposed in a mobile robot. Figure 4 is a schematic structural diagram of an anomaly detection device provided in this disclosure. As shown in Figure 4, the anomaly detection device 400 includes: a ranging component 41 and a judgment component 42, wherein:

[0144] The ranging component 41, controlled by a mobile robot, performs ranging measurements using a first ranging device to obtain multiple ranging data points; and

[0145] The judgment component 42, through the mobile robot, determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty, or whether the proportion of ranging data below a first preset value exceeds a preset threshold.

[0146] The ranging data is the data acquired by the first ranging device when the mobile robot is moving.

[0147] In some embodiments, the determining component 42 is further configured to:

[0148] The mobile robot detects the set of ranging values ​​of the first ranging device, and based on the set of ranging values, it determines whether the mobile robot performs anomaly detection. The set of ranging values ​​includes the ranging values ​​of the first ranging device within a preset time period.

[0149] In some embodiments, the determining component 42 is used for:

[0150] If the ranging value of the first ranging device is empty within a preset time period, or if the ranging value below the second preset value exceeds a preset proportion, the mobile robot is determined to perform an anomaly detection.

[0151] In some embodiments, the movement of the mobile robot is a rotation or movement at the detection location.

[0152] In some embodiments, the detected location is obtained based on historical map information, or it is a location that is greater than a preset distance from the mobile robot.

[0153] In some embodiments, when the mobile robot includes historical map information, the detected location is obtained based on the historical map information;

[0154] When the mobile robot does not include historical map information, the detected location is a position that is greater than a preset distance from the mobile robot.

[0155] In some embodiments, the anomaly detection device further includes an acquisition module for:

[0156] Information on target areas with height and area greater than corresponding preset values ​​is obtained based on historical map data; and

[0157] The detection location of the mobile robot is obtained based on the target area information.

[0158] In some embodiments, historical map information is obtained by ranging using a first ranging device or a second ranging device.

[0159] In some embodiments, when the mobile robot does not include historical map information, the detected location is a location that is greater than a preset distance from the mobile robot.

[0160] In practical applications, the ranging component 41 and the judgment component 42 can be implemented by a processor located on the anomaly detection device, which can be a central processing unit (CPU), microprocessor unit (MPU), digital signal processor (DSP), or field programmable gate array (FPGA), etc.

[0161] This disclosure also provides a mobile robot, including a memory and a processor. The memory stores a computer program that can run on the processor, wherein the processor executes the program to implement the anomaly detection method described in one or more of the above embodiments.

[0162] Figure 5 is a structural schematic diagram of a mobile robot provided in an embodiment of this disclosure. As shown in Figure 5, this embodiment of the disclosure provides a mobile robot 500, including:

[0163] The processor 51 and the storage medium 52 (which may be a memory) storing the processor-executable instructions; the storage medium 52 performs operations dependent on the processor 51 via a communication bus 53, and when the instructions are executed by the processor, the abnormal detection method executed on the processor side in one or more of the above embodiments is performed.

[0164] It should be noted that in practical applications, the various components in the electronic device are coupled together via the communication bus 53. The communication bus 53 is understood to be used to achieve communication between these components. In addition to the data bus, the communication bus 53 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as communication bus 53 in Figure 5.

[0165] This disclosure provides a computer storage medium storing a computer program. When the computer program is executed by one or more processors, the processors execute the anomaly detection method described in one or more of the above embodiments.

[0166] The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.

[0167] This disclosure also provides a computer program product including computer program instructions stored in a computer-readable storage medium and adapted to be called and executed by a processor to cause a computer device having the processor to perform the steps of the method described in any of the above embodiments.

[0168] This disclosure also provides a computer program including computer-readable code, which, when run in a computer device, implements the methods described in any of the above embodiments.

[0169] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0170] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0171] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0172] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0173] The above description is merely a preferred embodiment of this disclosure and is not intended to limit the scope of protection of this disclosure.

[0174] All embodiments disclosed herein can be executed individually or in combination with other embodiments, and are all considered to be within the scope of protection claimed by this disclosure.

Claims

1. An anomaly detection method, applied in a mobile robot, the anomaly detection method comprising: The mobile robot controls the first ranging device to perform ranging and obtain multiple ranging data. The mobile robot determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty or whether the proportion of ranging data below a first preset value in the ranging data exceeds a preset threshold. The ranging data is the data acquired by the first ranging device when the mobile robot is moving.

2. The abnormality detection method according to claim 1, wherein The method further includes: The mobile robot detects the set of distance measurement values ​​of the first ranging device, and based on the set of distance measurement values, it determines whether the mobile robot performs anomaly detection. The set of distance measurement values ​​includes the distance measurement values ​​of the first ranging device within a preset time period.

3. The abnormality detection method according to claim 2, wherein The step of determining whether the mobile robot performs anomaly detection includes: If the ranging value of the first ranging device is empty within the preset time period, or if the ranging value below the second preset value exceeds a preset proportion, the mobile robot is determined to perform the anomaly detection.

4. The abnormality detection method according to any one of claims 1 to 3, wherein The movement of the mobile robot is a rotation or movement performed at the detection position.

5. The abnormality detection method according to claim 4, wherein The detection location is obtained based on historical map information, or it is a location that is greater than a preset distance from the mobile robot.

6. The anomaly detection method as described in claim 5, wherein, When the mobile robot includes the historical map information, the detected location is obtained based on the historical map information.

7. The anomaly detection method as described in claim 6, further comprising: Based on the historical map information, obtain target area information whose height and area are greater than the corresponding preset values; as well as The detection position of the mobile robot is obtained based on the target area information.

8. The abnormality detection method according to any one of claims 5 to 7, wherein The historical map information is obtained by ranging through the first ranging device or the second ranging device.

9. The abnormality detection method according to any one of claims 5 to 8, wherein When the mobile robot does not include the historical map information, the detected location is a location that is greater than the preset distance from the mobile robot.

10. An anomaly detection device, installed on a mobile robot, the anomaly detection device comprising: The ranging component, controlled by the mobile robot, performs ranging by controlling the first ranging device to obtain multiple ranging data; as well as The determination component, through the mobile robot, determines whether the ranging of the first ranging device is abnormal based on whether the ranging data is empty, or whether the proportion of ranging data below a first preset value exceeds a preset threshold. The ranging data is the data acquired by the first ranging device when the mobile robot is moving.

11. A mobile robot comprising a memory and a processor, said memory storing a computer program operable on the processor, wherein, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer readable storage medium having stored thereon a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

13. A computer program product comprising computer program instructions stored in a computer-readable storage medium and adapted to be invoked and executed by a processor to cause a computer device having the processor to perform the steps of the method as claimed in any one of claims 1-9.

14. A computer program comprising computer readable code which, when run in a computer device, implements the method of any of claims 1 to 9.

Images