Sweeping robot control method, device and equipment and storage medium

Abstract

The embodiment of the invention provides a control method, device and equipment of a sweeping robot and a storage medium, and the method comprises the steps: firstly obtaining point cloud data collected by a line laser sensor of the sweeping robot, then determining the point cloud number and the point cloud range value of at least one frame of point cloud data, and according to the point cloud number and the point cloud range value of the at least one frame of point cloud data, determining the point cloud value of the sweeping robot; and determining whether a wall surface exists or not, and controlling the sweeping robot to clean along the wall when determining that the wall surface exists. The point cloud number and the point cloud range value of at least one frame of point cloud data are determined according to the point cloud data collected by the line laser sensor, then whether the wall exists or not is determined according to the point cloud number and the point cloud range value, and whether the wall exists or not is determined in this way, so that the accuracy of wall recognition is improved, and the wall recognition efficiency is improved. And the wall cleaning capability of the robot is improved.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a control method, device, equipment and storage medium for a sweeping robot. Background Art

[0002] In smart sweeping robots, wall cleaning is a key function that ensures thorough cleaning of room edges and corners. To achieve this function, the sweeping robot needs to have accurate wall detection and stable wall-driving capabilities.

[0003] At present, sweeping robots generally rely on infrared sensors or collision detectors to detect and avoid obstacles. These methods work well when dealing with larger obstacles (such as furniture and tables), but when identifying walls, especially in complex environments such as walls decorated with decorations, they may make misjudgments or have difficulty in accurate identification, thus affecting the robot's ability to clean along walls. Summary of the invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a control method, device, equipment and storage medium for a sweeping robot that overcomes the above problems or at least partially solves the above problems.

[0005] In order to solve the above problems, an embodiment of the present invention discloses a control method of a sweeping robot, characterized in that the method comprises:

[0006] Acquire point cloud data collected by the line laser sensor of the sweeping robot;

[0007] Determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data;

[0008] Determine whether there is a wall according to the number of point clouds and the extreme difference value of the point clouds in the at least one frame;

[0009] When it is determined that there is a wall, the sweeping robot is controlled to clean along the wall.

[0010] Optionally, the point cloud data includes angles, distances, and intensities of each point cloud, and when it is determined that there is a wall, controlling the sweeping robot to clean along the wall includes:

[0011] Determine the vertical distance between each point cloud and the wall according to the angle and distance of each point cloud;

[0012] Determining the distance between the cleaning robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall;

[0013] According to the distance between the cleaning robot and the wall, the cleaning robot is controlled to clean along the wall.

[0014] Optionally, determining the distance between the cleaning robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall includes:

[0015] According to the strength of each point cloud, a weighted average is performed on the vertical distance between each point cloud and the wall to obtain the distance between the sweeping robot and the wall.

[0016] Optionally, determining whether a wall exists according to the number of point clouds and the point cloud extreme difference value of the at least one frame includes:

[0017] Determining whether the number of point clouds in the at least one frame is greater than a preset number of point clouds;

[0018] If the number of point clouds in the at least one frame is greater than the preset number of point clouds, determining whether the point cloud range value is greater than the preset point cloud range value;

[0019] If the point cloud range value is less than the preset point cloud range value, it is determined that a wall exists.

[0020] Optionally, before determining the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data, the method further includes:

[0021] The point cloud data collected by the line laser sensor is preprocessed.

[0022] Optionally, the preprocessing of the point cloud data collected by the line laser sensor includes:

[0023] Based on the sampling frequency of the line laser sensor, selecting a preset number of continuous frames of point cloud data from the point cloud data;

[0024] According to the angles and distances of the point clouds in the preset number of consecutive frames of point cloud data, comparing the distances of the point clouds in one frame of point cloud data with the corresponding point clouds in other frames of point cloud data;

[0025] If the distance between the point cloud in one of the frames of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold, the point cloud in the one of the frames of point cloud data is determined to be a noise point, and the noise point is filtered out.

[0026] Optionally, the preprocessing of the point cloud data collected by the line laser sensor includes:

[0027] Determining abnormal intensity point clouds according to the intensity of each point cloud;

[0028] The abnormal intensity point cloud is eliminated.

[0029] Accordingly, an embodiment of the present invention discloses a control device for a sweeping robot, the device comprising:

[0030] A point cloud data acquisition module, used to acquire point cloud data collected by the line laser sensor of the sweeping robot;

[0031] A data determination module, used to determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data;

[0032] A wall determination module, used for determining whether a wall exists according to the number of point clouds and the extreme difference value of the point clouds in the at least one frame;

[0033] The wall cleaning module is used to control the sweeping robot to clean along the wall when it is determined that there is a wall.

[0034] Optionally, the point cloud data includes the angle, distance and intensity of each point cloud, and the wall cleaning module includes:

[0035] A vertical distance determination submodule, used to determine the vertical distance between each point cloud and the wall according to the angle and distance of each point cloud;

[0036] A wall distance determination submodule, used to determine the distance between the sweeping robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall;

[0037] The wall cleaning submodule is used to control the sweeping robot to perform wall cleaning according to the distance between the sweeping robot and the wall.

[0038] Optionally, the wall distance determination submodule includes:

[0039] The weighted averaging unit is used to perform weighted averaging of the vertical distances between each point cloud and the wall according to the strength of each point cloud, so as to obtain the distance between the sweeping robot and the wall.

[0040] Optionally, the wall determination module includes:

[0041] A point cloud quantity determination submodule, used to determine whether the point cloud quantity of at least one frame is greater than a preset point cloud quantity;

[0042] A point cloud extreme difference value judgment submodule, used for judging whether the point cloud extreme difference value is greater than a preset point cloud extreme difference value if the point cloud quantity of the at least one frame is greater than the preset point cloud quantity;

[0043] The wall determination submodule is used to determine the existence of a wall if the point cloud extreme difference value is less than the preset point cloud extreme difference value.

[0044] Optionally, before determining the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data, the device further includes:

[0045] The preprocessing submodule is used to preprocess the point cloud data collected by the line laser sensor.

[0046] Optionally, the preprocessing submodule further includes:

[0047] A point cloud data selection unit, configured to select a preset number of consecutive frames of point cloud data from the point cloud data based on a sampling frequency of the line laser sensor;

[0048] A distance comparison unit, configured to compare the distances between the point cloud in one frame of the point cloud data and the corresponding point clouds in other frames of the point cloud data according to the angles and distances of the point clouds in the point cloud data of the preset continuous number of frames;

[0049] The noise filtering unit is used to determine that the point cloud in one of the frames of point cloud data is a noise point and perform noise filtering if the distance between the point cloud in one of the frames of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold.

[0050] Optionally, the preprocessing submodule further includes:

[0051] An abnormal intensity point cloud determining unit, used for determining an abnormal intensity point cloud according to the intensity of each point cloud;

[0052] The abnormal intensity point cloud removal unit is used to remove the abnormal intensity point cloud.

[0053] Correspondingly, an embodiment of the present invention discloses an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the various steps of the control method embodiment of the above-mentioned sweeping robot are implemented.

[0054] Accordingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each step of the control method embodiment of the above-mentioned sweeping robot is implemented.

[0055] The embodiments of the present invention include the following advantages:

[0056] A control method for a sweeping robot according to an embodiment of the present invention first obtains point cloud data collected by a line laser sensor of the sweeping robot, then determines the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, determines whether a wall exists based on the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, and controls the sweeping robot to clean along the wall when it is determined that a wall exists. By determining the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data collected by the line laser sensor, and then determining whether a wall exists based on the point cloud quantity and point cloud extreme difference value, determining whether a wall exists in this way improves the accuracy of wall recognition and improves the robot's ability to clean along walls. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flowchart of a control method of a sweeping robot according to an embodiment of the present invention;

[0058] Figure 2 It is a structural block diagram of a control device of a sweeping robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] In smart sweeping robots, wall cleaning is a key function that ensures thorough cleaning of room edges and corners. To achieve this function, the sweeping robot needs to have accurate wall detection and stable wall-driving capabilities.

[0061] At present, sweeping robots generally rely on infrared sensors or collision detectors to detect and avoid obstacles. These methods work well when dealing with larger obstacles (such as furniture and tables), but when identifying walls, especially in complex environments such as walls decorated with decorations, they may make misjudgments or have difficulty in accurate identification, thus affecting the robot's ability to clean along walls.

[0062] One of the core concepts of an embodiment of the present invention is to determine the number of point clouds and the point cloud extreme difference value of at least one frame of point cloud data based on the point cloud data collected by the line laser sensor, and then determine whether there is a wall based on the number of point clouds and the point cloud extreme difference value. In this way, determining whether there is a wall improves the accuracy of wall recognition and improves the robot's wall cleaning ability.

[0063] Reference Figure 1 , shows a flow chart of a control method of a sweeping robot according to an embodiment of the present invention, which may specifically include the following steps:

[0064] Step 101, obtaining point cloud data collected by the line laser sensor of the sweeping robot.

[0065] Specifically, the sweeping robot is provided with a line laser sensor. For example, the line laser sensor can be provided in the front right or right side of the sweeping robot. The line laser sensor can emit a line laser from top to bottom to the front right, so as to determine whether there is a wall on the right side. Of course, the position of the line laser sensor can be set according to actual needs in actual applications, and the embodiment of the present invention does not limit this.

[0066] Line laser sensor is a device used for 3D scanning and measurement. Its working principle is based on laser triangulation. It emits a laser line to the surface of the object to be measured, and then uses a camera or photodetector to capture the image formed by the laser line on the surface of the object. By analyzing the deformation of the laser line, the 3D coordinates of the surface of the object can be calculated. Through the line laser sensor, the sweeping robot can perceive the environment more accurately, achieve smarter cleaning and navigation, and improve user experience and cleaning efficiency.

[0067] When the sweeping robot is started, the line laser sensor of the sweeping robot emits a beam of laser line, usually using infrared laser, because it is safer for human eyes and not easily disturbed by ambient light. The laser line is irradiated to the ground or the surface of an object, and then reflected back from the surface of the object. The camera or photodetector captures the reflected laser line image. The reflected image of the laser line is usually composed of many reflection points, each reflection point corresponds to a point on the laser line. The laser line image is processed by an image processing algorithm to obtain point cloud data.

[0068] When the sweeping robot is started, the line laser sensor of the sweeping robot will also start and emit laser lines, and the point cloud data returned by the laser lines emitted by the line laser sensor of the sweeping robot can be obtained.

[0069] Step 102: determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data.

[0070] Specifically, determining the number of point clouds in at least one frame of point cloud data means determining the number of points in at least one frame of point cloud data.

[0071] Determine the point cloud extreme value in the at least one frame of point cloud data, which is the difference between the maximum and minimum values ​​of all points in the at least one frame of point cloud data. Exemplarily, the line laser sensor emits a laser line and captures a reflected image, identifies the position and shape of the laser line through an image processing algorithm, and calculates the three-dimensional coordinates of the object surface using the known laser emission angle, the geometric parameters of the imaging system, and the deformation of the laser line. The point cloud data includes the position of each point in three-dimensional space, usually expressed as (x, y, z), finds the maximum and minimum values ​​of each coordinate axis in the point cloud data, calculates the difference between the maximum and minimum values, and obtains the point cloud extreme value in the at least one frame of point cloud data.

[0072] Step 103: Determine whether there is a wall according to the number of point clouds and the point cloud extreme difference value of the at least one frame.

[0073] Specifically, after determining the number of point clouds and the extreme difference values ​​of the point clouds in at least one frame, it is determined whether there is a wall based on the number of point clouds and the extreme difference values ​​of the point clouds in at least one frame. For example, the wall has no bumps and is perpendicular to the ground. It is also possible to determine whether there is a box based on the number of point clouds and the extreme difference values ​​of the point clouds in at least one frame. The box is a box without any bumps and is perpendicular to the ground.

[0074] Step 104: When it is determined that there is a wall, control the sweeping robot to clean along the wall.

[0075] Specifically, when it is determined that there is a wall, the sweeping robot is controlled to switch to a cleaning mode close to the wall to ensure that no blind spots are missed, so as to achieve a more thorough cleaning effect. For example, close to the wall means keeping one centimeter away from the wall, not directly touching the wall, so as to prevent scratching the wall. Of course, the distance from the wall when close to the wall can be set according to specific needs, and the embodiment of the present invention does not limit this.

[0076] Exemplarily, a line laser sensor is set at the right front of the sweeping robot, and the line laser sensor emits a laser line to the right front, obtains the point cloud data emitted by the line laser sensor and returned by the laser line, determines the number of point clouds and the point cloud extreme difference value of at least one frame of point cloud data, and judges the existence of a wall according to the number of point clouds and the point cloud extreme difference value of at least one frame of point cloud data. At this time, the sweeping robot is controlled to switch to a cleaning mode close to the wall to ensure that no dead corners are missed, so as to achieve a more thorough cleaning effect; if it is judged that there is no wall according to the number of point clouds and the point cloud extreme difference value of at least one frame of point cloud data, in order to avoid the sweeping robot from colliding and affecting its positioning, the sweeping robot is controlled to perform a normal cleaning mode. Although some dead corners may be left uncleaned in this mode, the stability and continuous operation of the sweeping robot can be effectively guaranteed.

[0077] A control method for a sweeping robot according to an embodiment of the present invention first obtains point cloud data collected by a line laser sensor of the sweeping robot, then determines the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, determines whether a wall exists based on the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, and controls the sweeping robot to clean along the wall when it is determined that a wall exists. By determining the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data collected by the line laser sensor, and then determining whether a wall exists based on the point cloud quantity and point cloud extreme difference value, determining whether a wall exists in this way improves the accuracy of wall recognition and improves the robot's ability to clean along walls.

[0078] In the embodiment of the present invention, the point cloud data includes the angle, distance and intensity of each point cloud. When it is determined that there is a wall, the step 104 controls the sweeping robot to clean along the wall, which may specifically include the following sub-steps:

[0079] Sub-step S11, determining the vertical distance between each point cloud and the wall according to the angle and distance of each point cloud.

[0080] Specifically, after the line laser sensor is started, each laser point will return three data: angle, distance, and intensity. The angle can include horizontal angle and vertical angle. The horizontal angle is the angle of the laser line in the horizontal direction, and the vertical angle is the angle of the laser line in the vertical direction. Through the angle data, the position of the laser point in three-dimensional space can be determined; the distance is the distance from the laser line to the surface of the object; the intensity is the intensity of the laser reflection, which represents the energy of the reflected light. Through the intensity, different materials and surface features in the environment can be sensed, which is used to distinguish surfaces of different materials, such as metal, plastic, wood, etc., and extract the characteristics of the surface of the object, such as texture, color, etc.

[0081] The point cloud data includes the angle, distance and intensity of each point cloud. According to the angle and distance of each point cloud, a mathematical formula can be used to convert it into the vertical distance from the wall. For example, the angle is the angle of the laser line in the horizontal direction, and the distance is the distance from the laser line to the surface of the object. The vertical distance from the wall is calculated using trigonometric functions (such as sine and cosine).

[0082] Sub-step S12, determining the distance between the cleaning robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall.

[0083] Specifically, after determining the vertical distance between each point cloud and the wall, the distance between the sweeping robot and the wall is determined according to the vertical distance between each point cloud and the wall and the intensity of each point cloud.

[0084] Sub-step S13, controlling the sweeping robot to clean along the wall according to the distance between the sweeping robot and the wall.

[0085] Specifically, after determining the distance between the sweeping robot and the wall, the sweeping robot is controlled to move according to the distance between the sweeping robot and the wall, and cleans along the wall. For example, the laser sensor is arranged at the right front of the sweeping robot, and the line laser sensor emits a laser line to the right front, and determines that there is a wall on the right side, and controls the sweeping robot to switch to a cleaning mode close to the wall, and the sweeping robot turns right 90 degrees, moves to a position close to the wall according to the distance between the sweeping robot and the wall, and then turns left 90 degrees, and cleans forward close to the wall.

[0086] In the embodiment of the present invention, the step S22 of determining the distance between the cleaning robot and the wall according to the strength of each point cloud and the vertical distance between each point cloud and the wall includes:

[0087] According to the strength of each point cloud, a weighted average is performed on the vertical distance between each point cloud and the wall to obtain the distance between the sweeping robot and the wall.

[0088] Specifically, according to the strength of each point cloud, the vertical distance between each point cloud and the wall is weighted averaged to calculate the distance between the sweeping robot and the wall. Points with stronger signal strength will be given higher weights. By taking a weighted average of the vertical distance between each point cloud and the wall according to the strength of each point cloud, the accuracy of distance measurement can be improved, which can more accurately reflect the actual wall position.

[0089] The vertical distance between each point cloud and the wall can be input into the Kalman filter. The Kalman filter algorithm dynamically adjusts the distance measurement data and performs weighted fusion of the measurement values ​​from different time points. It can effectively suppress random noise and provide smooth distance estimation, thereby improving the accuracy of distance measurement.

[0090] The Kalman filter is a recursive filter used to estimate the state of a system, and is particularly suitable for processing noisy measurement data. It provides an optimal estimate of the system state by combining the system's dynamic model and measurement data. The state space model of the Kalman filter includes a state equation, which is used to describe the change of the system state over time, and an observation equation, which is used to describe the relationship between the measurement data and the system state. The Kalman filter steps include a prediction step, which uses the system's state equation to predict the state at the next moment, and an update step, which uses the measurement data to update the predicted state to obtain the optimal estimate.

[0091] In the embodiment of the present invention, the step 103 of determining whether there is a wall according to the number of point clouds and the point cloud extreme difference value of the at least one frame may specifically include the following sub-steps:

[0092] Sub-step S21, determining whether the number of point clouds in the at least one frame is greater than a preset number of point clouds.

[0093] Specifically, after determining the number of at least one frame of point cloud and the extreme difference value of the point cloud, it is determined whether the number of at least one frame of point cloud is greater than the preset number of point clouds. Exemplarily, the preset number of point clouds can be 10, which is set to 10 to ensure sufficient data. Of course, the preset number of point clouds can be set according to actual needs in actual applications, and the embodiment of the present invention does not limit this.

[0094] Sub-step S22: if the number of point clouds in the at least one frame is greater than the preset number of point clouds, determining whether the point cloud range value is greater than the preset point cloud range value.

[0095] Specifically, if the number of point clouds in at least one frame is greater than the preset number of point clouds, it is determined whether the point cloud extreme value is greater than the preset point cloud extreme value. For example, the number of point clouds in a certain frame is 15, and the preset number of point clouds can be 10. Then, the number of point clouds in this frame is greater than the preset number of point clouds, that is, the number of point clouds meets the requirements. At this time, it is determined whether the point cloud extreme value in this frame is greater than the preset point cloud extreme value, that is, the difference between the maximum point cloud value and the minimum point cloud value. The preset point cloud extreme value can be 0.015 meters. Of course, the preset point cloud extreme value can be set according to actual needs in actual applications, and the embodiments of the present invention are not limited to this.

[0096] Sub-step S23: If the point cloud range value is less than the preset point cloud range value, it is determined that a wall exists.

[0097] Specifically, if the point cloud range value is less than the preset point cloud range value, it is determined that there is a wall. For example, the preset point cloud range value is 0.015 meters, and the point cloud range value of this frame is 0.001. Then, the point cloud range value of this frame is less than the preset point cloud range value, which means that the difference between the maximum point cloud value and the minimum point cloud value is less than the preset maximum value, and it is determined that there is a wall.

[0098] Exemplarily, the laser point cloud data is extracted and stored in a data container, and it is checked whether the number of point clouds in the container exceeds 10 to ensure that the data is sufficient. If the number of point clouds meets the requirements, the difference between the maximum point cloud value and the minimum point cloud value is calculated. If the difference is less than 0.015 meters, the condition for the existence of a wall is met; otherwise, the condition for the existence of a wall is not met. If a wall is detected, the previously calculated distance is output and marked as "there is a wall". If no wall is detected, the output distance is 0 meters and marked as "no wall". If no wall is detected, the output distance is 0 meters to facilitate subsequent action processing and improve the simplicity of the code. Subsequent actions can be determined only by distance to determine how to execute.

[0099] In an embodiment of the present invention, before determining the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data, the method further includes:

[0100] The point cloud data collected by the line laser sensor is preprocessed.

[0101] Specifically, traditional sensors are easily affected by environmental interference when detecting distance, such as the reflection and scattering of light or sunlight, which leads to increased ranging errors and noise, thus affecting the robot's ability to clean along walls. In order to solve the influence of interference points (such as wall decorations, reflective surfaces, etc.) on the ranging accuracy during the ranging process, the intensity, position and continuity of the reflected signal are analyzed to filter out abnormal data, ensuring that only the true vertical wall distance information is retained, thereby achieving high-precision ranging.

[0102] The point cloud data collected by the line laser sensor needs to be preprocessed. Preprocessing the point cloud data collected by the line laser sensor is a key step to improve data quality and subsequent processing effects. Preprocessing includes noise removal, filtering, data registration, feature extraction and other operations. Data denoising, the noise sources include sensor noise and environmental noise. Sensor noise is the noise of the sensor itself, such as electronic noise, optical noise, etc. Environmental noise is interference in the environment, such as light changes, poor reflection, etc. Denoising methods include statistical filtering: removing outliers, such as filters based on statistical methods (such as Z-score filtering); spatial filtering: filters based on spatial neighborhoods, such as Gaussian filtering, median filtering, etc. Data filtering includes Gaussian filtering, smoothing point cloud data, removing high-frequency noise; median filtering, removing impulse noise, retaining edge information. Registration methods include iterative nearest point algorithm, which is used to register multiple point cloud data to the same coordinate system; normal distribution transformation, which is used for point cloud registration.

[0103] In an embodiment of the present invention, the preprocessing of the point cloud data collected by the line laser sensor includes:

[0104] Based on the sampling frequency of the line laser sensor, point cloud data of a preset number of consecutive frames are selected from the point cloud data.

[0105] Specifically, based on the sampling frequency of the line laser sensor, point cloud data of a preset continuous frame number are selected from the point cloud data. By way of example, since the sampling frequency is not very high, a preset continuous frame number that is too low will fail to filter out noise, while a preset continuous frame number that is too high will result in untimely processing of information. The preset continuous frame number may be 3-6 frames. Based on the sampling frequency of the line laser sensor, 3-6 frames of continuous point cloud data are selected from the point cloud data. Of course, the preset continuous frame number may be set in actual applications according to actual needs, and the embodiments of the present invention do not impose any restrictions on this.

[0106] The sampling frequency of a line laser sensor refers to the number of times the sensor collects data per unit time, usually in Hertz (Hz). The sampling frequency directly affects the data collection speed and accuracy of the sensor, and is crucial for the environmental perception and navigation of the sweeping robot. The hardware performance of the sensor determines its maximum sampling frequency. The complexity of obstacles and reflective surfaces in the environment will affect the selection of the sampling frequency. The data processing capability of the main control board determines the sampling frequency that can be processed. A high sampling frequency can provide denser point cloud data and improve the accuracy and real-time performance of environmental perception. A high sampling frequency will increase the amount of data and require higher data processing capabilities and storage space. A low sampling frequency can reduce the amount of data and reduce the requirements for data processing capabilities and storage space. A low sampling frequency may lead to insufficient accuracy and real-time performance of environmental perception.

[0107] According to the angles and distances of the point clouds in the preset number of consecutive frames of point cloud data, the distances of the point clouds in one frame of point cloud data and the corresponding point clouds in other frames of point cloud data are compared.

[0108] Specifically, based on the angle and distance of the point clouds in the point cloud data of a preset continuous number of frames, the position of each point cloud in the point cloud data of a preset continuous number of frames in the same three-dimensional coordinate system is determined, and these frames are compared one by one, and the position of the point cloud in the point cloud data of one frame is compared with the position of the corresponding point cloud in the point cloud data of other frames in the preset continuous number of frames, and the distance between the point cloud in one frame of the point cloud data and the position of the corresponding point cloud in the point cloud data of other frames in the preset continuous number of frames is determined.

[0109] If the distance between the point cloud in one of the frames of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold, the point cloud in the one of the frames of point cloud data is determined to be a noise point, and the noise point is filtered out.

[0110] Specifically, if the distance between a point cloud in one frame of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold, the point is determined to be a noise point and filtered out. Since noise points usually only appear in a few frames and then disappear, this method can effectively eliminate short-term noise interference and ensure the accuracy and stability of the ranging data.

[0111] The multi-sampling comparison is based on the sampling frequency of the line laser sensor. First, 3 to 6 frames of continuous data are acquired and these frames are compared one by one. If the distance between a point in a frame and the corresponding point in other frames exceeds the set threshold, the point is determined to be a noise point and filtered out.

[0112] Before multiple sampling comparison, preliminary denoising can be performed to remove obvious noise points. This includes removing isolated points, points with unstable movement, and points with a distance value of 0 to ensure the accuracy and stability of the data. Isolated points are points that are far away from other points, usually due to sensor noise or environmental interference. They can be removed by using filters based on statistical methods, such as Z-score filtering, to remove outliers, or filters based on spatial neighborhoods, such as Gaussian filtering, median filtering, etc. Unstable moving points refer to points with large position changes in consecutive frames, which are usually caused by sensor jitter or environmental interference. The point cloud difference between consecutive frames can be calculated to remove points with large changes, or the Kalman filter can be used to smooth the point cloud data to remove unstable moving points. Points with a distance value of 0 are usually caused by sensor failure or data transmission errors. Points with a distance value of 0 can be removed by distance filtering.

[0113] In an embodiment of the present invention, the preprocessing of the point cloud data collected by the line laser sensor includes:

[0114] Determining abnormal intensity point clouds according to the intensity of each point cloud;

[0115] The abnormal intensity point cloud is eliminated.

[0116] Specifically, for walls, the signal strength at the reflection point usually remains relatively stable. However, when encountering reflective surfaces or decorations, the signal strength may become abnormal. Different materials have different reflection characteristics, such as metal, glass, wood, etc. Different colors have different reflection characteristics, such as dark and light colors, and irregular shapes have different reflection characteristics, such as curved surfaces and concave and convex surfaces.

[0117] By analyzing these intensities, we can identify and remove these abnormal intensity values, thereby ensuring that only stable wall reflection signals are retained. We can calculate the mean and standard deviation of the signal strength to identify points that deviate greatly from the mean, or analyze the distribution of signal strength through a histogram to identify abnormal values ​​and remove these abnormal intensity values. By analyzing the signal strength and identifying and removing abnormal signal strength values, we can ensure the accuracy and stability of the point cloud data, thereby improving the accuracy of wall recognition.

[0118] In this embodiment, a camera can be used for wall detection. First, the laser sensor is started to obtain the laser point cloud data of the right environment, including the distance and signal strength, and the environment image is captured by the camera. The laser data is simply denoised using the captured image to enhance and detect the wall features.

[0119] By analyzing the reflected signal of the line laser, it can accurately determine whether there is a stable vertical wall on the right side, and can identify the vertical features of the wall in a complex environment to avoid misjudgment, thereby ensuring the stability and accuracy of the robot's cleaning along the wall. In order to solve the influence of interference points (such as wall decorations, reflective surfaces, etc.) on the ranging accuracy during the ranging process, the point cloud data collected by the line laser sensor is pre-processed, and the intensity, position and continuity of the reflected signal are analyzed to filter out abnormal data, ensuring that only the true vertical wall distance information is retained, thereby achieving high-precision ranging. The sweeping robot can effectively detect the vertical wall on the right side and filter out possible interference points during the ranging process, ensuring that the vertical wall can be judged efficiently and accurately in a complex environment, achieving the effect of enabling the sweeping robot to clean close to the wall.

[0120] A control method for a sweeping robot according to an embodiment of the present invention first obtains point cloud data collected by a line laser sensor of the sweeping robot, then determines the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, determines whether a wall exists based on the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, and controls the sweeping robot to clean along the wall when it is determined that a wall exists. By determining the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data collected by the line laser sensor, and then determining whether a wall exists based on the point cloud quantity and point cloud extreme difference value, determining whether a wall exists in this way improves the accuracy of wall recognition and improves the robot's ability to clean along walls.

[0121] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0122] Reference Figure 2 , shows a structural block diagram of a control device of a sweeping robot according to an embodiment of the present invention, which may specifically include the following modules:

[0123] The point cloud data acquisition module 201 is used to acquire the point cloud data collected by the line laser sensor of the cleaning robot;

[0124] A data determination module 202, used to determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data;

[0125] A wall determination module 203 is used to determine whether there is a wall according to the number of point clouds and the point cloud extreme difference value of the at least one frame;

[0126] The wall cleaning module 204 is used to control the cleaning robot to clean along the wall when it is determined that there is a wall.

[0127] A control method for a sweeping robot according to an embodiment of the present invention first obtains point cloud data collected by a line laser sensor of the sweeping robot, then determines the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, determines whether a wall exists based on the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data, and controls the sweeping robot to clean along the wall when it is determined that a wall exists. By determining the point cloud quantity and point cloud extreme difference value of at least one frame of point cloud data collected by the line laser sensor, and then determining whether a wall exists based on the point cloud quantity and point cloud extreme difference value, determining whether a wall exists in this way improves the accuracy of wall recognition and improves the robot's ability to clean along walls.

[0128] In an embodiment of the present invention, the point cloud data includes the angle, distance and intensity of each point cloud, and the wall cleaning module includes:

[0129] A vertical distance determination submodule, used to determine the vertical distance between each point cloud and the wall according to the angle and distance of each point cloud;

[0130] A wall distance determination submodule, used to determine the distance between the sweeping robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall;

[0131] The wall cleaning submodule is used to control the sweeping robot to perform wall cleaning according to the distance between the sweeping robot and the wall.

[0132] In an embodiment of the present invention, the wall distance determination submodule includes:

[0133] The weighted averaging unit is used to perform weighted averaging of the vertical distances between each point cloud and the wall according to the strength of each point cloud, so as to obtain the distance between the sweeping robot and the wall.

[0134] In an embodiment of the present invention, the wall determination module includes:

[0135] A point cloud quantity determination submodule, used to determine whether the point cloud quantity of at least one frame is greater than a preset point cloud quantity;

[0136] A point cloud extreme difference value judgment submodule, used for judging whether the point cloud extreme difference value is greater than a preset point cloud extreme difference value if the point cloud quantity of the at least one frame is greater than the preset point cloud quantity;

[0137] The wall determination submodule is used to determine the existence of a wall if the point cloud extreme difference value is less than the preset point cloud extreme difference value.

[0138] In an embodiment of the present invention, before determining the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data, the device further includes:

[0139] The preprocessing submodule is used to preprocess the point cloud data collected by the line laser sensor.

[0140] In an embodiment of the present invention, the preprocessing submodule further includes:

[0141] A point cloud data selection unit, configured to select a preset number of consecutive frames of point cloud data from the point cloud data based on a sampling frequency of the line laser sensor;

[0142] A distance comparison unit, configured to compare the distances between the point cloud in one frame of the point cloud data and the corresponding point clouds in other frames of the point cloud data according to the angles and distances of the point clouds in the point cloud data of the preset continuous number of frames;

[0143] The noise filtering unit is used to determine that the point cloud in one of the frames of point cloud data is a noise point and perform noise filtering if the distance between the point cloud in one of the frames of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold.

[0144] In an embodiment of the present invention, the preprocessing submodule further includes:

[0145] An abnormal intensity point cloud determining unit, used for determining an abnormal intensity point cloud according to the intensity of each point cloud;

[0146] The abnormal intensity point cloud removal unit is used to remove the abnormal intensity point cloud.

[0147] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0148] An embodiment of the present invention further provides an electronic device, including:

[0149] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned control method embodiment of a sweeping robot are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0150] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned control method embodiment of a sweeping robot are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0151] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0152] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0153] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0154] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0156] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0157] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0158] The control method, device, equipment and storage medium of a sweeping robot provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A control method for a sweeping robot, characterized in that: The method comprises: Acquire point cloud data collected by the line laser sensor of the sweeping robot; Determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data; Determine whether there is a wall according to the number of point clouds and the extreme difference value of the point clouds in the at least one frame; When it is determined that there is a wall, the sweeping robot is controlled to clean along the wall.

2. The method according to claim 1, characterized in that The point cloud data includes the angle, distance and intensity of each point cloud. When it is determined that there is a wall, controlling the sweeping robot to clean along the wall includes: Determine the vertical distance between each point cloud and the wall according to the angle and distance of each point cloud; Determining the distance between the cleaning robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall; According to the distance between the cleaning robot and the wall, the cleaning robot is controlled to clean along the wall.

3. The method according to claim 2, characterized in that Determining the distance between the cleaning robot and the wall according to the intensity of each point cloud and the vertical distance between each point cloud and the wall includes: According to the strength of each point cloud, a weighted average is performed on the vertical distance between each point cloud and the wall to obtain the distance between the sweeping robot and the wall.

4. The method according to claim 1, characterized in that: The determining whether there is a wall according to the number of point clouds and the point cloud extreme difference value of the at least one frame includes: Determining whether the number of point clouds in the at least one frame is greater than a preset number of point clouds; If the number of point clouds in the at least one frame is greater than the preset number of point clouds, determining whether the point cloud range value is greater than the preset point cloud range value; If the point cloud range value is less than the preset point cloud range value, it is determined that a wall exists.

5. The method according to claim 2, characterized in that: Before determining the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data, the method further includes: The point cloud data collected by the line laser sensor is preprocessed.

6. The method according to claim 5, characterized in that The preprocessing of the point cloud data collected by the line laser sensor includes: Based on the sampling frequency of the line laser sensor, selecting a preset number of continuous frames of point cloud data from the point cloud data; According to the angles and distances of the point clouds in the preset number of consecutive frames of point cloud data, comparing the distances of the point clouds in one frame of point cloud data with the corresponding point clouds in other frames of point cloud data; If the distance between the point cloud in one of the frames of point cloud data and the corresponding point cloud in other frames of point cloud data is greater than a preset distance threshold, the point cloud in the one of the frames of point cloud data is determined to be a noise point, and the noise point is filtered out.

7. The method according to claim 5, characterized in that The preprocessing of the point cloud data collected by the line laser sensor includes: Determining abnormal intensity point clouds according to the intensity of each point cloud; The abnormal intensity point cloud is eliminated.

8. A control device for a sweeping robot, characterized in that: The device comprises: A point cloud data acquisition module, used to acquire point cloud data collected by the line laser sensor of the sweeping robot; A data determination module, used to determine the point cloud quantity and point cloud extreme difference value of at least one frame of the point cloud data; A wall determination module, used for determining whether a wall exists according to the number of point clouds and the extreme difference value of the point clouds in the at least one frame; The wall cleaning module is used to control the sweeping robot to clean along the wall when it is determined that there is a wall.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the control method of the sweeping robot as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the control method of the cleaning robot as claimed in any one of claims 1 to 7 are implemented.

Images