Detection method and apparatus for automatic cleaning device, device, and storage medium

Abstract

A detection method and apparatus for an automatic cleaning device, a device, and a storage medium, relating to the technical field of smart home, and aiming to at least solving the problem of low accuracy of detection results caused by low slippage detection efficiency and a high missed detection rate and a high false detection rate in a detection process. The method comprises: acquiring optical flow data representing measured data and acquiring wheel encoder data representing predicted data (S01); and on the basis of the data in two different dimensions, namely, the prediction and measurement dimensions, detecting whether the automatic cleaning device is in a slipping operation state (S02).

Description

Detection method, device, equipment and storage medium for automatic cleaning equipment CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to the application number 202410317112.3 filed with the National Intellectual Property Administration of China on March 19, 2024, entitled “Detection method, device, equipment and storage medium for automatic cleaning equipment,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to the field of smart home technology, and in particular to a detection method, apparatus, device and storage medium for automatic cleaning equipment. Background Art

[0003] With the increasing demand for intelligent life, automatic cleaning equipment or automatic cleaning robots such as sweeping robots, mopping robots, and sweeping and mopping robots have been widely used.

[0004] In actual applications, automatic cleaning robots may slip while cleaning. If timely measures are not taken to address this situation, the normal operation of the automatic cleaning robot will be affected. Currently, to ensure the normal operation of the automatic cleaning robot, the slippage of the automatic cleaning robot is usually determined based on whether the running distance of the left and right wheels of the automatic cleaning robot reaches the predicted distance within a preset time. However, the above-mentioned slippage detection method based on the running distance and the preset distance requires the automatic cleaning robot to run for a period of time before detection is detected, which has low detection efficiency. Moreover, when the machine is running at a high speed, the possibility of missed detection or false detection of slippage is high, resulting in low detection accuracy. Summary of the Invention

[0005] The present disclosure provides a detection method, apparatus, device and storage medium for automatic cleaning equipment.

[0006] According to a first aspect of an embodiment of the present disclosure, a detection method for an automatic cleaning device is provided, the method comprising: acquiring optical flow data and acquiring wheel speed meter data; and determining whether the automatic cleaning device is slipping based on the optical flow data and the wheel speed meter data.

[0007] In one possible implementation, the method also includes: obtaining gyroscope data detected by a gyroscope; determining the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data; and determining whether the automatic cleaning device is slipping based on the optical flow data and the wheel speed meter data, including: determining whether the automatic cleaning device is slipping based on the confidence of the optical flow data and the confidence of the wheel speed meter data and the optical flow data and the wheel speed meter data.

[0008] In another possible implementation, determining whether the automatic cleaning device is slipping is performed based on the optical flow data and the wheel speed meter data, including: using the optical flow data to correct the wheel speed meter data to obtain a corrected speed; the wheel speed meter data includes a first operating speed of the automatic cleaning device predicted by the wheel speed meter; the optical flow data includes a second operating speed of the automatic cleaning device observed by the optical flow sensor; and determining whether the automatic cleaning device is slipping based on the difference between the corrected speed and the first operating speed.

[0009] In another possible implementation, whether the automatic cleaning device is slipping is determined based on the difference between the corrected speed and the first operating speed, including: when the difference between the corrected speed and the first operating speed exceeds a preset threshold range, determining that the automatic cleaning device is slipping; when the difference between the corrected speed and the first operating speed is within the preset threshold range, determining that the automatic cleaning device is not slipping.

[0010] In another possible implementation, optical flow data is used to correct the wheel speed meter data to obtain a corrected correction speed, including: determining the first rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter as the data in the wheel speed meter data; and determining the second rotational angular velocity of the automatic cleaning device observed by the optical flow sensor as the data in the optical flow data; based on the Kalman filter algorithm, the optical flow data is used to correct the data in the wheel speed meter data that is interfered with by the signal to obtain target correction data including the corrected speed.

[0011] In another possible implementation, based on the Kalman filter algorithm, optical flow data is used to correct the data in the wheel speed meter data that is affected by signal interference to obtain target correction data including the corrected speed, including: constructing a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise based on the correspondence between the Kalman gain and the covariance in the Kalman filter algorithm; obtaining the target Kalman gain corresponding to the wheel speed meter data and the optical flow data at the current moment based on the first preset relationship; determining the target correction data including the corrected speed and the third rotational angular velocity based on the target Kalman gain and the corrected correction data and the target mapping relationship between the Kalman gain, the wheel speed meter data and the optical flow data.

[0012] In another possible implementation, the method also includes: obtaining the fourth rotational angular velocity of the automatic cleaning device at the current moment detected by the gyroscope; determining the target prediction system noise based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtaining the target observation noise generated by the optical flow sensor at the current moment based on the rotational angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment.

[0013] The target prediction system noise is used to characterize the confidence level of the wheel speedometer data, while the target observation noise is used to characterize the confidence level of the optical flow data. Furthermore, the target prediction system noise indicates the degree of interference with the wheel speedometer and is negatively correlated with the confidence level of the wheel speedometer data. That is, greater the target prediction system noise, the lower the confidence level of the wheel speedometer data. The target observation noise indicates the degree of interference with the optical flow sensor and is negatively correlated with the confidence level of the optical flow data. That is, greater the degree of interference with the optical flow sensor, the lower the confidence level of the optical flow data.

[0014] In another possible implementation, the target predicted system noise is determined based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment, including: obtaining the current process noise of the wheel speed meter at the current moment based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtaining the target predicted system noise at the next moment corresponding to the current process noise at the current moment based on a second preset relationship between the current process noise at different moments before the current moment and the corresponding current system noise and the predicted system noise at the next moment corresponding to the different moments.

[0015] In another possible implementation, the wheel speed meter data includes a first operating speed and a first rotation angle; obtaining the wheel speed meter data includes: obtaining the left wheel operating speed and the right wheel operating speed of the automatic cleaning device detected by the wheel speed meter, and determining the average speed of the left wheel operating speed and the right wheel operating speed as the first operating speed; and determining the ratio of the speed difference between the right wheel operating speed and the left wheel operating speed to the differential wheel axle length as the first rotational angular velocity.

[0016] In another possible implementation, before determining the target correction data including the correction speed and the third rotational angular velocity based on the target Kalman gain and the target mapping relationship between the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data, the method also includes: determining an observation model based on the position information of the optical flow sensor installed on the automatic cleaning device; the observation model characterizes the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operation data of the automatic cleaning device; using the actual operation data in the observation model as the corrected correction data, and constructing a target mapping relationship based on the Kalman gain that characterizes the weight relationship between the wheel speed meter data and the optical flow data in the Kalman algorithm.

[0017] In another possible implementation, the position information includes the relative horizontal distance in the horizontal direction and the relative vertical distance in the vertical direction between the optical flow sensor and the automatic cleaning device in the same horizontal plane, as well as the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane, where the horizontal plane and the vertical plane are perpendicular to each other.

[0018] According to a second aspect of an embodiment of the present disclosure, a detection device for an automatic cleaning device is provided, which includes: an acquisition unit configured to acquire optical flow data and wheel speed meter data; and a determination unit configured to determine whether the automatic cleaning device is slipping based on the optical flow data and the wheel speed meter data.

[0019] In one possible implementation, the device also includes: a correction unit configured to obtain gyroscope data detected by the gyroscope; determine the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data; the determination unit is specifically configured to: determine whether the automatic cleaning device is slipping based on the confidence of the optical flow data and the confidence of the wheel speed meter data as well as the optical flow data and the wheel speed meter data.

[0020] In another possible implementation, the determination unit is specifically configured to: use optical flow data to correct the wheel speed meter data to obtain a corrected speed; the wheel speed meter data includes a first operating speed of the automatic cleaning device predicted by the wheel speed meter; the optical flow data includes a second operating speed of the automatic cleaning device observed by the optical flow sensor; and determine whether the automatic cleaning device is slipping based on the difference between the corrected speed and the first operating speed.

[0021] In another possible implementation, the determination unit is specifically configured to: determine that the automatic cleaning device is slipping when the difference between the corrected speed and the first operating speed exceeds a preset threshold range; and determine that the automatic cleaning device is not slipping when the difference between the corrected speed and the first operating speed is within a preset threshold range.

[0022] In another possible implementation, the determination unit is specifically configured to: determine the first rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter as data in the wheel speed meter data; and determine the second rotational angular velocity of the automatic cleaning device observed by the optical flow sensor as data in the optical flow data; based on the Kalman filtering algorithm, use the optical flow data to correct the data in the wheel speed meter data that is affected by signal interference to obtain target correction data including the corrected speed.

[0023] In another possible implementation, the determination unit is specifically configured to: construct a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise based on the correspondence between the Kalman gain and the covariance in the Kalman filter algorithm; obtain the target Kalman gain corresponding to the wheel speed meter data and the optical flow data at the current moment based on the first preset relationship; determine the target correction data including the correction speed and the third rotational angular velocity according to the target mapping relationship between the target Kalman gain and the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data.

[0024] In another possible implementation, the determination unit is further configured to: obtain the fourth rotational angular velocity of the automatic cleaning device at the current moment detected by the gyroscope; determine the target prediction system noise based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtain the target observation noise generated by the optical flow sensor at the current moment based on the rotational angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment.

[0025] The target prediction system noise is used to characterize the confidence of the wheel speed meter data, and the target observation noise is used to characterize the confidence of the optical flow data.

[0026] In another possible implementation, the determination unit is further configured to: obtain a current process noise of the wheel speed meter at the current moment based on a rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtain a target predicted system noise at the next moment corresponding to the current process noise at the current moment based on a second preset relationship between the current process noise at different moments before the current moment and the corresponding current system noise and the predicted system noise at the next moment corresponding to the different moments.

[0027] In another possible implementation, the wheel speed meter data includes a first operating speed and a first rotation angle; the acquisition unit is further configured to: obtain the left wheel operating speed and the right wheel operating speed of the automatic cleaning device detected by the wheel speed meter, and determine the average speed of the left wheel operating speed and the right wheel operating speed as the first operating speed; and determine the ratio of the speed difference between the right wheel operating speed and the left wheel operating speed to the differential wheel axle length as the first rotational angular velocity.

[0028] In another possible implementation, before determining the target correction data including the correction speed and the third rotational angular velocity based on the target Kalman gain and the target mapping relationship between the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data, the determination unit is further configured to: determine the observation model based on the position information of the optical flow sensor installed on the automatic cleaning device; the observation model represents the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operation data of the automatic cleaning device; use the actual operation data in the observation model as the corrected correction data, and construct the target mapping relationship based on the Kalman gain that represents the weight relationship between the wheel speed meter data and the optical flow data in the Kalman algorithm.

[0029] In another possible implementation, the position information includes the relative horizontal distance in the horizontal direction and the relative vertical distance in the vertical direction between the optical flow sensor and the automatic cleaning device in the same horizontal plane, as well as the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane, where the horizontal plane and the vertical plane are perpendicular to each other.

[0030] According to a third aspect of an embodiment of the present disclosure, an automatic cleaning device is provided, which is configured to perform the detection method of the first aspect and any possible implementation thereof.

[0031] According to the fourth aspect of an embodiment of the present disclosure, a control device is provided, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute the executable instructions to implement a detection method for an automatic cleaning device such as the first aspect and any possible implementation thereof.

[0032] According to the fifth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of a control device, the control device is enabled to perform a detection method for an automatic cleaning device such as the first aspect and any possible implementation thereof.

[0033] According to the sixth aspect of an embodiment of the present disclosure, a computer program product is provided, which includes computer instructions. When the computer instructions are run on a control device, the control device executes the detection method for an automatic cleaning device of the above-mentioned first aspect and any possible implementation thereof.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0036] FIG1 is a flowchart 1 of a detection method according to an exemplary embodiment;

[0037] FIG2 is a second flowchart of a detection method according to an exemplary embodiment;

[0038] FIG3 is a third flowchart of a detection method according to an exemplary embodiment;

[0039] FIG4 is a schematic diagram showing a slip detection process according to an exemplary embodiment;

[0040] FIG5 is a block diagram of a detection device according to an exemplary embodiment;

[0041] Fig. 6 is a schematic diagram showing a control device according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] In order to enable ordinary people in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0043] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0044] Before giving a detailed introduction to the detection method for the automatic cleaning device provided in the embodiment of the present application, a brief introduction to the application scenarios involved in the embodiment of the present application is first given.

[0045] In actual applications, automatic cleaning robots may slip while cleaning. If timely measures are not taken to address this situation, the normal operation of the automatic cleaning robot will be affected. Currently, to ensure the normal operation of the automatic cleaning robot, the determination of whether the automatic cleaning robot has slipped is usually based on whether the travel distance of the left and right wheels of the automatic cleaning robot reaches a predicted distance within a preset time. However, the above-mentioned slip detection method based on the travel distance and the predicted distance requires the automatic cleaning robot to run for a period of time before detection can be made, resulting in low detection efficiency. Moreover, when the machine is running at a high speed, the possibility of missed detection or false detection of slip conditions is high, resulting in low detection accuracy.

[0046] In response to the above problems, the present application provides a detection method for automatic cleaning equipment, which obtains optical flow data representing measurement data from the wheel speed meter and wheel speed meter data representing prediction data from the optical flow sensor. Based on the above-mentioned data of two different dimensions of prediction and measurement, it is possible to more accurately detect whether the automatic cleaning equipment is slipping. In the above-mentioned slip detection method, the two-dimensional data based on it are the original detection data of the equipment itself, which can be obtained in real time and can quickly characterize the operating state of the automatic cleaning equipment. Compared with the related art that performs slip detection based on a distance variable that requires a certain reaction time, the present application performs slip detection based on the data of the two dimensions of the machine itself, which has higher detection efficiency and more accurate detection accuracy.

[0047] The detection method for an automatic cleaning device provided in the embodiments of this application can be applied to automatic cleaning devices or robots with automatic cleaning functions, such as sweeping robots, mopping robots, and sweeping and mopping robots. The automatic cleaning device includes a gyroscope, a wheel speed meter, and an optical flow sensor. For ease of understanding, the detection method for an automatic cleaning device provided in this application is described in detail below with reference to the accompanying drawings.

[0048] FIG1 is a flow chart showing a method for detecting an automatic cleaning device according to an exemplary embodiment. As shown in FIG1 , the method for detecting an automatic cleaning device includes the following steps S01 and S02 .

[0049] S01, obtain optical flow data and wheel speed meter data.

[0050] The wheel speed meter data includes a first running speed and a first rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter, and the optical flow data includes a second running speed and a second rotational angular velocity of the automatic cleaning device observed by the optical flow sensor.

[0051] Specifically, the first rotational angular velocity and the first running speed of the automatic cleaning device predicted by the wheel speed meter are determined as data in the wheel speed meter data; and the second rotational angular velocity and the second running speed of the automatic cleaning device observed by the optical flow sensor are determined as data in the optical flow data.

[0052] S02: Determine whether the automatic cleaning device is slipping based on the optical flow data and the wheel speed meter data.

[0053] In one embodiment, the automatic cleaning device obtains gyroscope data detected by the gyroscope from the gyroscope, and determines the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data.

[0054] Based on this embodiment, the above step S02 can be implemented by the following steps: determining whether the automatic cleaning device is slipping based on the confidence of the optical flow data and the confidence of the wheel speed meter data as well as the optical flow data and the wheel speed meter data.

[0055] Through the above-described implementation, based on the above-described prediction and measurement of optical flow data and wheel speedometer data in two different dimensions, the operating status of the automatic cleaning device can be more accurately detected. In this slip detection method, the two dimensions of data used are the device's own original detection data, which can be obtained in real time and quickly characterize the automatic cleaning device's operating status. Compared to related art methods that perform slip detection based on a distance variable that requires a certain reaction time, this application performs slip detection based on data from two machine-specific dimensions, achieving higher efficiency and precision.

[0056] As a refinement and expansion of the above embodiment, and in order to fully illustrate the specific implementation process of this embodiment, the present application provides other detection methods for automatic cleaning equipment. As shown in Figure 2, the detection method for automatic cleaning equipment also includes the following steps S11, S12 and S13.

[0057] S11, acquiring wheel speed meter data from a wheel speed meter; and acquiring optical flow data from an optical flow sensor.

[0058] In some embodiments, the wheel speed meter can obtain wheel speed meter data based on a differential motion model. In the process of obtaining the wheel speed meter data, the wheel speed meter is modeled based on the spatial position coordinate system of the automatic cleaning device itself.

[0059] Alternatively, to further simplify the wheel speedometer data acquisition process, the X-axis direction is defined as the direction directly in front of the automatic cleaning device, the Y-axis direction is defined as the direction perpendicular to the horizontal ground plane directly in front of the automatic cleaning device, and the Z-axis direction is defined as the direction perpendicular to the horizontal ground plane. In this way, the automatic cleaning device's operating speed only moves along the X-axis of the device's spatial coordinate system, while the speed along the Y-axis is zero. Therefore, when acquiring the first operating speed included in the wheel speedometer data, only the speed along the X-axis can be used as the first operating speed.

[0060] In one embodiment, wheel speed meter data is obtained from a wheel speed meter in the following manner. The automatic cleaning device controls the wheel speed meter to detect the operating speeds of the left and right wheels of the automatic cleaning device, thereby obtaining the detected left and right wheel operating speeds. Furthermore, the average of the left and right wheel operating speeds is determined as a first operating speed in the wheel speed meter data. Simultaneously, the ratio of the speed difference between the right and left wheel operating speeds to the differential axle length is determined as a first rotational angular velocity, thereby obtaining the first rotational angular velocity of the automatic cleaning device from the wheel speed meter.

[0061] The differential wheel axle length is the center distance between the left and right wheels of the automatic cleaning device. The center distance is the distance between the center point of the left wheel and the center point of the right wheel.

[0062] The relationship between the first rotational angular velocity and the first operating speed is exemplarily described based on the following formula (1) and formula (2): x ′=(V R +V L ) / 2 Formula (1) w′=(V R -V L ) / Len Formula (2) Where, V RV is the rotation speed of the right wheel of the automatic cleaning device detected by the wheel speed meter, that is, the right wheel running speed; L V is the rotation speed of the left wheel of the automatic cleaning device detected by the wheel speed meter, that is, the left wheel speed; x ' is the first operating speed of the automatic cleaning device predicted by the wheel speed meter, w' is the rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter, that is, the first rotational angular velocity; Len is the differential wheel axle length.

[0063] Furthermore, the second operating speed of the automatic cleaning device observed by the optical flow sensor is first directly obtained from the optical flow sensor. Then, based on the position information of the installation position of the optical flow sensor and the second operating speed, the second rotational angular velocity is obtained, so as to obtain the rotational angular velocity of the automatic cleaning device observed by the optical flow sensor from the optical flow sensor.

[0064] The position information may include one or more of the following: a relative horizontal distance and a relative vertical distance between the optical flow sensor and the automatic cleaning device in the same horizontal plane, and a relative offset angle between the optical flow sensor and the automatic cleaning device in a vertical plane, wherein the horizontal plane and the vertical plane are perpendicular to each other.

[0065] The relationship between the second rotational angular velocity and the second rotational angular velocity is exemplarily described based on the following formula (3) and formula (4): Vm=[V mx V my ] Formula (3) w m =(sin(t θ )*V mx )+cos(t θ )*V my ) / t x Formula (4) Where, V m The matrix is ​​composed of the second running speed of the automatic cleaning device detected by the optical flow sensor, and the second running speed includes the running speed V of the automatic cleaning device in the X-axis direction. mx And the automatic cleaning equipment runs at a speed V in the Y-axis direction my ;w m The second rotation angular velocity of the automatic cleaning device is obtained from the optical flow sensor; t x is the relative horizontal distance between the optical flow sensor and the automatic cleaning device in the same horizontal plane; t θ is the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane.

[0066] S12, based on the Kalman filter algorithm, the wheel speed meter data is corrected using the optical flow data to obtain a corrected speed.

[0067] In the aforementioned Kalman filter algorithm, the prediction step is implemented using wheel speed meter data, and the update or correction step is implemented using optical flow data to complete the state estimation of the actual data. Specifically, the prediction step uses the system model and the state estimate at the previous moment to predict the current state, resulting in the predicted value of the wheel speed meter data. The update step uses the observed or measured values ​​of the optical flow data provided by the optical flow sensor. By comparing the observed value with the predicted value, the Kalman gain is calculated, and the Kalman gain is used to correct the predicted value of the wheel speed meter data, resulting in a more accurate state estimate of the target corrected data (e.g., the corrected speed).

[0068] The wheel speed meter data is corrected using the optical flow data to obtain corrected data, which includes a corrected speed and a third rotational angular velocity.

[0069] S13 , when the difference between the corrected speed and the first operating speed exceeds a preset threshold range, determining that the automatic cleaning device is slipping.

[0070] The correction speed is compared with the first operating speed. When the predicted first operating speed is significantly different from the corrected speed, it indicates that the operating speed of the automatic cleaning device deviates significantly from the normal operating speed, that is, the automatic cleaning device has slipped.

[0071] Furthermore, when the difference between the corrected speed and the first operating speed is within the preset threshold range, that is, the predicted first operating speed is smaller than the corrected speed after correction, it means that the operating speed of the automatic cleaning device does not deviate much from the normal operating speed, that is, it is determined that the automatic cleaning device has not slipped.

[0072] Through the above-described embodiment, wheel speed data is obtained from the wheel speed meter and optical flow data is obtained from the optical flow sensor. Based on the Kalman filter algorithm, the observed value or measured value of the optical flow data observed by the optical flow sensor is used to correct the predicted value of the wheel speed data predicted by the wheel speed meter. This allows the system to estimate the amount of system status data of the automatic cleaning device while taking into account both the predicted value and the measured value, thereby obtaining corrected data with higher estimation accuracy. This ensures a more accurate prediction of the operating status data of the automatic cleaning device, and furthermore, more accurately determines whether the automatic cleaning device is slipping based on the difference between the corrected speed in the corrected data and the predicted first operating speed, thereby improving the accuracy of the slip detection results.

[0073] This slip detection method determines the device's slip condition based on the device's operating speed and rotational angular velocity in different acquisition dimensions. The speed variable can be acquired and changed in real time, enabling a more rapid characterization of the device's operating status. Compared to related technologies that rely on distance variables for slip detection, speed-based slip detection offers greater efficiency and precision.

[0074] As shown in FIG. 3 in conjunction with FIG. 2 , the above step S12 can be specifically implemented through the following steps S121 , S122 and S123 .

[0075] S121, based on the corresponding relationship between the Kalman gain and the covariance in the Kalman filter algorithm, construct a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise.

[0076] As an implementation manner, a fourth rotation angular velocity of the automatic cleaning device at the current moment detected by the gyroscope is acquired.

[0077] Furthermore, based on this embodiment, the process of determining the target prediction system noise and the target observation noise is as follows: the target prediction system noise is determined based on the angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and the target observation noise generated by the optical flow sensor at the current moment is obtained based on the angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment.

[0078] Specifically, the target predicted system noise is determined as follows: The current process noise of the wheel speed meter at the current moment is determined based on the angular velocity difference between the first and fourth rotational angular velocities at the current moment. The target predicted system noise at the next moment corresponding to the current process noise at the current moment is determined based on a second preset relationship. The second preset relationship refers to the relationship between the current process noise at different moments before the current moment, the corresponding current system noise, and the predicted system noise at the next moment corresponding to the different moments.

[0079] S122: Based on the first preset relationship, obtain the target Kalman gain corresponding to the wheel speed meter data and the optical flow data at the current moment.

[0080] As a specific implementation method, the target prediction system noise at the next moment corresponding to the current process noise of the wheel speed meter at the current moment is used as the prediction error covariance, and the target observation noise generated by the optical flow sensor at the current moment is used as the observation error covariance. According to the first preset relationship established between the Kalman gain and the prediction error covariance and the observation error covariance in the Kalman algorithm, the target Kalman gain is obtained.

[0081] The target prediction system noise is used to characterize the confidence level of the wheel speedometer data, while the target observation noise is used to characterize the confidence level of the optical flow data. Furthermore, the target prediction system noise indicates the degree of interference with the wheel speedometer and is negatively correlated with the confidence level of the wheel speedometer data. That is, the greater the target prediction system noise, the lower the confidence level of the corresponding wheel speedometer data. The target observation noise indicates the degree of interference with the optical flow sensor and is negatively correlated with the confidence level of the optical flow data. That is, the greater the interference with the optical flow sensor, the lower the confidence level of the corresponding optical flow data.

[0082] The target Kalman gain is used to represent the importance of the wheel speedometer data and optical flow data at the current moment, that is, the weight of the wheel speedometer data and optical flow data at the current moment. The size of the weight is positively correlated with the importance of the wheel speedometer data and optical flow data at the current moment.

[0083] As a method for determining the target Kalman gain, the automatic cleaning device first obtains the current process noise of the wheel speed meter at the current moment based on the difference between the first rotational angular velocity detected by the wheel speed meter at the current moment and the fourth rotational angular velocity detected by the gyroscope of the automatic cleaning device. Exemplarily, the determination of the current process noise association relationship is expressed based on formula (6). And, based on the difference between the second rotational angular velocity of the optical flow sensor at the current moment and the fourth rotational angular velocity of the automatic cleaning device detected by the gyroscope, the target observation noise generated by the optical flow sensor at the current moment is obtained. Exemplarily, the determination of the target observation noise association relationship is expressed based on formula (7).

[0084] Furthermore, based on a second preset relationship between the current process noise at different moments and the corresponding current system noise, and the predicted system noise at the next moment corresponding to the different moments, the second preset relationship is determined, for example, based on formula (8). Thus, based on the second preset relationship, the target predicted system noise at the next moment corresponding to the current process noise at the current moment is obtained.

[0085] Specifically, if a second preset relationship between the current process noise and the corresponding current system noise at different moments and the predicted system noise at the next moment corresponding to the different moments has been determined, and the current process noise at different moments and the current system noise at the initial moment have also been determined, based on the second preset relationship, the predicted system noise at each moment is successively deduced or accumulated starting from the initial moment to obtain the predicted system noise at the next moment. o =(V R -V L ) / Len Formula (5) Q=a*I*(w o -w g ) 2Formula (6) R=a*I*(w m -w g ) 2 Formula (7) P′=P+Q Formula (8) Where, w g w is the fourth rotation angular velocity of the automatic cleaning device detected by the gyroscope; o is the first rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter; a is an adjustable parameter and a positive constant; P′ is the matrix corresponding to the prediction system noise at the next moment, that is, the prediction error covariance matrix; I is the two-dimensional unit matrix; Q is the matrix corresponding to the current process noise; R is the matrix corresponding to the current system noise, that is, the observation error covariance matrix or the measurement error covariance matrix; P is the matrix corresponding to the prediction system noise at the current moment.

[0086] In some implementations, the current process noise can also be understood as the confidence level of the wheel speed data of the wheel speed meter, and the prediction system noise can also be understood as the confidence level of the optical flow data of the optical flow sensor.

[0087] Furthermore, based on the first preset relationship established between the Kalman gain and the prediction error covariance and the observation error covariance in the Kalman algorithm, the determination of the first preset relationship is represented, for example, based on formulas (9) and (10). Here, the prediction error covariance is the target prediction system noise at the next moment corresponding to the current process noise of the wheel speed meter at the current moment, and the observation error covariance is the target observation noise generated by the optical flow sensor at the current moment. K = P'*H T / (H*P′*H T +R) Formula (9) P=(IK*H)*P′ Formula (10) Where H is the measurement matrix corresponding to the optical flow sensor; H T is the matrix transpose of H, and K is the Kalman gain.

[0088] S123: Determine target correction data including a correction speed and a third rotational angular velocity according to a target mapping relationship between the target Kalman gain and the corrected correction data and the Kalman gain, the wheel speed meter data, and the optical flow data.

[0089] Based on the target mapping relationship between the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data, the target correction data corresponding to the target Kalman gain, the wheel speed meter data and the optical flow data at the current moment are determined.

[0090] The target correction data includes the correction speed and the third rotational angular velocity of the automatic cleaning device.

[0091] Specifically, the process of constructing the target mapping relationship representing the correspondence between the corrected data and the wheel speed meter data, the optical flow data and the Kalman gain is as follows: Based on the position information of the optical flow sensor installed in the automatic cleaning device, an observation model is determined.

[0092] The observation model represents the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operating data of the automatic cleaning device. For example, the conversion relationship of the observation model is further explained based on the following formulas (11) to (16). Based on this, in order to ensure that the target correction data is more consistent with the actual operating data, the actual operating data in the observation model is used as the corrected target correction data, and the target mapping relationship is constructed based on the Kalman gain of the wheel speed meter data and the optical flow data weight represented in the Kalman algorithm. For example, the target mapping relationship is further explained based on the following formula (17). mx =cos(t θ )*v x +(sin(t θ )*t x -cos(t θ )*t y )*w Formula (11) V my =-sin(t θ )*v x +(sin(t θ )*t y )+cos(t θ )*t y )*w formula (12) Vm=H*X Formula (14) X=[v x w] Formula (15) X′=[v x ′ w′] Formula (16) X new =X′+K*(V m -H*X′) Formula (17) Where, t y is the relative vertical distance between the optical flow sensor and the automatic cleaning device in the same horizontal plane; X is the matrix composed of the actual operation data of the automatic cleaning device at the next moment, which includes the actual operation speed and the actual rotation angular velocity; v x is the actual running speed, w is the actual rotation angular velocity; X new is the matrix composed of the corrected data, and X′ is the matrix corresponding to the tachometer data.

[0093] As a specific implementation, the skid detection process of the automatic cleaning device is described below as shown in FIG4 .

[0094] S1, obtains optical flow data, gyroscope data and tachometer data from the optical flow sensor, gyroscope and tachometer respectively.

[0095] The gyroscope data includes a fourth rotational angular velocity of the automatic cleaning device detected by the gyroscope.

[0096] S2, obtaining optical flow data confidence based on the optical flow data and the gyroscope data, and obtaining tachometer data confidence based on the tachometer data and the gyroscope data.

[0097] S3: Based on the confidence of the optical flow data and the confidence of the tachometer data, the optical flow data and the tachometer data are fused to obtain fused data.

[0098] The fused data is the corrected target data. The specific fusion process is the same as the process of correcting the tachometer data using optical flow data, and will not be repeated here.

[0099] The fusion data includes a fusion speed and a fusion angular speed, ie, a corrected speed and a third rotational angular speed of the automatic cleaning device.

[0100] S4, judging whether the corrected speed in the fused data is greater than the first running speed of the tachometer data, if yes, proceeding to step S5; if no, proceeding to step S6.

[0101] S5, determining that the automatic cleaning device is slipping.

[0102] S6, confirm that the automatic cleaning device does not slip.

[0103] In order to achieve the above functions, the detection device of the automatic cleaning equipment includes a hardware structure and / or software module that performs each function. It should be easy for those skilled in the art to realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] An embodiment of the present application also provides an automatic cleaning device, which includes a gyroscope, an optical flow sensor, a tachometer and a controller; the controller is configured to execute the detection method as described above.

[0105] An embodiment of the present application further provides a detection device for an automatic cleaning device as shown in FIG4 , which includes: an acquisition unit 401 , a determination unit 402 , and a correction unit 403 .

[0106] The acquiring unit 401 is configured to acquire optical flow data and wheel speed meter data.

[0107] The determination unit 402 is configured to determine whether the automatic cleaning device is slipping according to the optical flow data and the wheel speed meter data.

[0108] In one possible implementation, the device also includes: a correction unit 403, configured to obtain gyroscope data detected by the gyroscope; determine the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data; the determination unit is specifically configured to: determine whether the automatic cleaning device is slipping based on the confidence of the optical flow data and the confidence of the wheel speed meter data as well as the optical flow data and the wheel speed meter data.

[0109] In another possible implementation, the determination unit 402 is specifically configured to: use optical flow data to correct the wheel speed meter data to obtain a corrected speed; the wheel speed meter data includes a first operating speed of the automatic cleaning device predicted by the wheel speed meter; the optical flow data includes a second operating speed of the automatic cleaning device observed by the optical flow sensor; and determine whether the automatic cleaning device is slipping based on the difference between the corrected speed and the first operating speed.

[0110] In another possible implementation, the determination unit 402 is specifically configured to: determine that the automatic cleaning device is slipping when the difference between the corrected speed and the first operating speed exceeds a preset threshold range; and determine that the automatic cleaning device is not slipping when the difference between the corrected speed and the first operating speed is within a preset threshold range.

[0111] In another possible implementation, the determination unit 402 is specifically configured to: determine the first rotational angular velocity of the automatic cleaning device predicted by the wheel speed meter as the data in the wheel speed meter data; and determine the second rotational angular velocity of the automatic cleaning device observed by the optical flow sensor as the data in the optical flow data; based on the Kalman filtering algorithm, use the optical flow data to correct the data in the wheel speed meter data that is affected by signal interference to obtain target correction data including the corrected speed.

[0112] In another possible implementation, the determination unit 402 is specifically configured to: construct a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise based on the correspondence between the Kalman gain and the covariance in the Kalman filter algorithm; obtain the target Kalman gain corresponding to the wheel speed meter data and the optical flow data at the current moment based on the first preset relationship; determine the target correction data including the correction speed and the third rotational angular velocity according to the target mapping relationship between the target Kalman gain and the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data.

[0113] In another possible implementation, the determination unit 402 is further configured to: obtain the fourth rotational angular velocity of the automatic cleaning device at the current moment detected by the gyroscope; determine the target prediction system noise based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtain the target observation noise generated by the optical flow sensor at the current moment based on the rotational angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment.

[0114] The target prediction system noise is used to characterize the confidence of the wheel speed meter data, and the target observation noise is used to characterize the confidence of the optical flow data.

[0115] In another possible implementation, the determination unit 402 is further configured to: obtain the current process noise of the wheel speed meter at the current moment based on the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; and obtain the target predicted system noise at the next moment corresponding to the current process noise at the current moment based on a second preset relationship between the current process noise at different moments before the current moment and the corresponding current system noise and the predicted system noise at the next moment corresponding to the different moments.

[0116] In another possible implementation, the wheel speed meter data includes a first operating speed and a first rotation angle; the acquisition unit 401 is further configured to: obtain the left wheel operating speed and the right wheel operating speed of the automatic cleaning device detected by the wheel speed meter, and determine the average speed of the left wheel operating speed and the right wheel operating speed as the first operating speed; and determine the ratio of the speed difference between the right wheel operating speed and the left wheel operating speed to the differential wheel axle length as the first rotational angular velocity.

[0117] In another possible implementation, before determining the target correction data including the correction speed and the third rotational angular velocity based on the target Kalman gain and the target mapping relationship between the corrected correction data and the Kalman gain, the wheel speed meter data and the optical flow data, the determination unit 402 is further configured to: determine the observation model based on the position information of the optical flow sensor installed on the automatic cleaning device; the observation model represents the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operation data of the automatic cleaning device; the actual operation data in the observation model is used as the corrected correction data, and the target mapping relationship is constructed based on the Kalman gain that represents the weight relationship between the wheel speed meter data and the optical flow data in the Kalman algorithm.

[0118] In another possible implementation, the position information includes the relative horizontal distance in the horizontal direction and the relative vertical distance in the vertical direction between the optical flow sensor and the automatic cleaning device in the same horizontal plane, as well as the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane, where the horizontal plane and the vertical plane are perpendicular to each other.

[0119] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0120] Figure 6 is a schematic diagram of a control device provided herein. As shown in Figure 6 , the control device 60 may include at least one processor 601 and a memory 603 for storing processor-executable instructions. The processor 601 is configured to execute the instructions in the memory 603 to implement the detection method for an automatic cleaning device described in the following embodiments.

[0121] In addition, the control device 60 may further include a communication bus 602 , at least one communication interface 604 , an input device 606 , and an output device 605 .

[0122] The processor 601 may be a central processing unit (CPU), a microprocessor unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0123] The communication bus 602 may include a pathway for transmitting information between the aforementioned components.

[0124] The communication interface 604 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0125] The input device 606 is used to receive input signals and the output device 605 is used to output signals.

[0126] The memory 603 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0127] The memory 603 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the instructions stored in the memory 603, thereby realizing the functions of the method of the present application.

[0128] In a specific implementation, as an embodiment, the processor 601 may include one or more CPUs, such as CPU0 and CPU1 in FIG6 .

[0129] In a specific implementation, as an embodiment, the control device 60 may include multiple processors, such as processor 601 and processor 607 in FIG6 . Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0130] As shown in FIG6 , the control device includes a processor 601 and a memory 603 for storing executable instructions for the processor 601 . The processor 601 is configured to execute the executable instructions to implement the detection method for an automatic cleaning device according to any of the above-described possible embodiments. The aforementioned methods achieve the same technical effects and are not described again here to avoid repetition.

[0131] The present application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of a detection device or a control device of an automatic cleaning device, the detection device or the control device of the automatic cleaning device can perform the detection method of the automatic cleaning device according to any of the possible embodiments described above. The same technical effects can be achieved, and to avoid repetition, they are not described here.

[0132] The present application also provides a computer program product, including a computer program or instructions, which is executed by a processor to implement the detection method for an automatic cleaning device according to any of the above possible embodiments. The same technical effects can be achieved, and to avoid repetition, they are not described here.

[0133] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: obtaining optical flow data representing the measured data and wheel speed meter data representing the predicted data. Based on the above-mentioned data of two different dimensions of prediction and measurement, the operating state of whether the automatic cleaning equipment is slipping can be detected more accurately. In the above-mentioned slip detection method, the two-dimensional data based on it are the original detection data of the equipment itself, which can be obtained in real time and can quickly characterize the operating state of the automatic cleaning equipment. Compared with the related art that performs slip detection based on a distance variable that requires a certain reaction time, the present application performs slip detection based on the data of two dimensions of the machine itself, which has higher detection efficiency and more accurate detection accuracy.

[0134] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0135] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for detecting an automatic cleaning device, the method comprising: Obtain optical flow data and obtain wheel speed meter data; Determine whether the automatic cleaning device is slipping according to the optical flow data and the wheel speed meter data.

2. The method according to claim 1, further comprising: Get the gyroscope data detected by the gyroscope; Determining the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data, Wherein, determining whether the automatic cleaning device is slipping according to the optical flow data and the wheel speed meter data includes: It is determined whether the automatic cleaning device is slipping according to the confidence of the optical flow data and the confidence of the wheel speed meter data and the optical flow data and the wheel speed meter data.

3. The method according to claim 1 or 2, wherein The determining, based on the optical flow data and the wheel speed meter data, whether the automatic cleaning device is slipping includes: Correcting the wheel speed meter data using the optical flow data to obtain a corrected speed, wherein the wheel speed meter data includes a first operating speed of the automatic cleaning device predicted by the wheel speed meter, and the optical flow data includes a second operating speed of the automatic cleaning device observed by the optical flow sensor; It is determined whether the automatic cleaning device is slipping according to the difference between the corrected speed and the first operating speed.

4. The method according to claim 3, wherein: Determining whether the automatic cleaning device is slipping according to the difference between the corrected speed and the first operating speed includes: When the difference between the corrected speed and the first operating speed exceeds a preset threshold range, determining that the automatic cleaning device is slipping; When the difference between the corrected speed and the first operating speed is within the preset threshold range, it is determined that the automatic cleaning device does not slip.

5. The method according to claim 3, wherein: The method of correcting the wheel speed meter data using the optical flow data to obtain the corrected speed includes: determining a first rotational angular velocity of the automatic cleaning device predicted by a wheel speed meter as data in the wheel speed meter data; and determining a second rotational angular velocity of the automatic cleaning device observed by an optical flow sensor as data in the optical flow data; Based on the Kalman filter algorithm, the optical flow data is used to correct the data of the wheel speed meter data that is interfered with by the signal, so as to obtain target correction data including the corrected speed.

6. The method according to claim 5, wherein: The Kalman filter algorithm is based on which the optical flow data is used to correct the data in the wheel speed meter data that is subject to signal interference, thereby obtaining target correction data including the corrected speed, including: According to the corresponding relationship between the Kalman gain and the covariance in the Kalman filter algorithm, a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise is established; Based on the first preset relationship, obtaining a target Kalman gain corresponding to the wheel speed meter data and the optical flow data at a current moment; Target correction data including the correction speed and the third rotational angular velocity is determined according to a target mapping relationship between the target Kalman gain and the corrected correction data, the Kalman gain, the wheel speed meter data, and the optical flow data.

7. The method according to claim 6, further comprising: Acquiring a fourth rotational angular velocity of the automatic cleaning device at the current moment detected by the gyroscope; determining the target prediction system noise according to a rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at a current moment; and The target observation noise generated by the optical flow sensor at the current moment is obtained based on the rotational angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment. The target prediction system noise represents the confidence of the wheel speed meter data, and the target observation noise represents the confidence of the optical flow data.

8. The method according to claim 7, wherein: The determining the target prediction system noise according to the rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at a current moment includes: obtaining a current process noise of the wheel speed meter at the current moment based on a rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; According to a second preset relationship between the current process noise at different moments before the current moment and the corresponding current system noise and the predicted system noise at the next moment corresponding to the different moments, the target predicted system noise at the next moment corresponding to the current process noise at the current moment is obtained.

9. The method according to any one of claims 1 to 8, wherein The wheel speed meter data includes a first operating speed and a first rotation angle; The step of obtaining wheel speed meter data includes: Obtaining the left wheel running speed and the right wheel running speed of the automatic cleaning device detected by a wheel speed meter, and determining the average speed of the left wheel running speed and the right wheel running speed as the first running speed; and The ratio of the speed difference between the right wheel running speed and the left wheel running speed to the differential wheel axle length is determined as the first rotational angular velocity.

10. The method according to claim 6 or 7, wherein: Before determining the target correction data including the correction speed and the third rotational angular velocity based on the target mapping relationship between the target Kalman gain and the corrected correction data and the Kalman gain, the wheel speed meter data, and the optical flow data, the method further includes: Determining an observation model based on the position information of the optical flow sensor installed on the automatic cleaning device, wherein the observation model represents the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operation data of the automatic cleaning device; The target mapping relationship is constructed by using the actual operating data in the observation model as the corrected data and based on the Kalman gain in the Kalman algorithm that characterizes the weight relationship between the wheel speed meter data and the optical flow data.

11. The method according to claim 10, wherein: The position information includes the relative horizontal distance in the horizontal direction and the relative vertical distance in the vertical direction between the optical flow sensor and the automatic cleaning device in the same horizontal plane, as well as the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane, where the horizontal plane and the vertical plane are perpendicular to each other.

12. A detection device for an automatic cleaning device, the device comprising: an acquisition unit configured to acquire optical flow data and acquire wheel speed meter data; The determining unit is configured to determine whether the automatic cleaning device is slipping according to the optical flow data and the wheel speed meter data.

13. The apparatus according to claim 12, further comprising: The correction unit is configured to: obtain gyroscope data detected by the gyroscope, and determine the confidence of the optical flow data and the confidence of the wheel speed meter data based on the gyroscope data, The determining unit is further configured to determine whether the automatic cleaning device is slipping according to the confidence of the optical flow data and the confidence of the wheel speed meter data and the optical flow data and the wheel speed meter data.

14. The device according to claim 12 or 13, wherein The determining unit is further configured to: use the optical flow data to correct the wheel speed meter data to obtain a corrected speed, wherein: The wheel speed meter data includes a first operating speed of the automatic cleaning device predicted by a wheel speed meter, and the optical flow data includes a second operating speed of the automatic cleaning device observed by an optical flow sensor; It is determined whether the automatic cleaning device is slipping according to the difference between the corrected speed and the first operating speed.

15. The device according to claim 14, wherein The determining unit is further configured to: When the difference between the corrected speed and the first operating speed exceeds a preset threshold range, determining that the automatic cleaning device is slipping; When the difference between the corrected speed and the first operating speed is within the preset threshold range, it is determined that the automatic cleaning device does not slip.

16. The device according to claim 14, wherein The determining unit is further configured to: determining a first rotational angular velocity of the automatic cleaning device predicted by a wheel speed meter as data in the wheel speed meter data; determining a second rotational angular velocity of the automatic cleaning device observed by an optical flow sensor as data in the optical flow data; Based on the Kalman filter algorithm, the optical flow data is used to correct the data of the wheel speed meter data that is interfered with by the signal, so as to obtain target correction data including the corrected speed.

17. The device according to claim 16, wherein The determining unit is further configured to: According to the corresponding relationship between the Kalman gain and the covariance in the Kalman filter algorithm, a first preset relationship between the Kalman gain and the target prediction system noise and the target observation noise is established; Based on the first preset relationship, obtaining a target Kalman gain corresponding to the wheel speed meter data and the optical flow data at a current moment; Target correction data including the correction speed and the third rotational angular velocity is determined according to a target mapping relationship between the target Kalman gain and the corrected correction data, the Kalman gain, the wheel speed meter data, and the optical flow data.

18. The device according to claim 17, wherein The determining unit is further configured to: Acquiring a fourth rotational angular velocity of the automatic cleaning device at the current moment detected by the gyroscope; determining the target prediction system noise according to a rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at a current moment; The target observation noise generated by the optical flow sensor at the current moment is obtained based on the rotational angular velocity difference between the second rotational angular velocity and the fourth rotational angular velocity at the current moment. The target prediction system noise is used to characterize the confidence of the wheel speed meter data, and the target observation noise is used to characterize the confidence of the optical flow data.

19. The device according to claim 18, wherein The determining unit is further configured to: obtaining a current process noise of the wheel speed meter at the current moment based on a rotational angular velocity difference between the first rotational angular velocity and the fourth rotational angular velocity at the current moment; According to a second preset relationship between the current process noise and the corresponding current system noise at different moments before the current moment and the predicted system noise at the next moment corresponding to the different moments, the target predicted system noise at the next moment corresponding to the current process noise at the current moment is obtained.

20. The device according to any one of claims 12 to 19, wherein The wheel speed meter data includes a first operating speed and a first rotation angle; and The acquisition unit is further configured to: Obtaining the left wheel running speed and the right wheel running speed of the automatic cleaning device detected by a wheel speed meter, and determining the average speed of the left wheel running speed and the right wheel running speed as the first running speed; The ratio of the speed difference between the right wheel running speed and the left wheel running speed to the differential wheel axle length is determined as the first rotational angular velocity.

21. The device according to claim 17 or 18, wherein Before determining the target correction data including the correction speed and the third rotational angular velocity based on the target Kalman gain and the target mapping relationship between the corrected correction data and the Kalman gain, the wheel speed meter data, and the optical flow data, the determining unit is further configured to: Determining an observation model based on the position information of the optical flow sensor installed on the automatic cleaning device, wherein the observation model represents the corresponding conversion relationship between the optical flow data observed by the optical flow sensor and the actual operation data of the automatic cleaning device; The target mapping relationship is constructed by using the actual operating data in the observation model as the corrected data and based on the Kalman gain in the Kalman algorithm that characterizes the weight relationship between the wheel speed meter data and the optical flow data.

22. The device according to claim 21, wherein The position information includes the relative horizontal distance in the horizontal direction and the relative vertical distance in the vertical direction between the optical flow sensor and the automatic cleaning device in the same horizontal plane, as well as the relative offset angle between the optical flow sensor and the automatic cleaning device in the vertical plane, where the horizontal plane and the vertical plane are perpendicular to each other.

23. An automatic cleaning device, wherein: The automatic cleaning device comprises a wheel speed meter and an optical flow sensor, and is configured to execute the detection method for the automatic cleaning device according to any one of claims 1 to 11.

24. A computer-readable storage medium having instructions stored thereon, wherein: When the instructions in the computer-readable storage medium are executed by a processor of a control device, the control device is enabled to perform the detection method for an automatic cleaning device according to any one of claims 1 to 11.

Images