Cleaning assembly control method of robot, chip and robot

Abstract

The invention discloses a cleaning assembly control method of a robot, a chip and the robot, and relates to the field of robotics.A laser radar is arranged on the robot, an ultrasonic sensor is arranged on a cleaning assembly, and high-precision positioning of a photovoltaic panel is achieved through measurement data of the ultrasonic sensor and measurement data of the laser radar; therefore, by adjusting the pose of the cleaning assembly, the cleaning assembly is parallel to the photovoltaic panel, at the moment, measurement data of the ultrasonic sensor do not jump, the pose of the cleaning assembly can be accurately adjusted through the measurement data of the ultrasonic sensor, the cleaning assembly is attached to the photovoltaic panel, and the photovoltaic panel is prevented from being damaged.

Description

Technical Field

[0001] This application relates to the field of robot technology, and particularly to a method for controlling a cleaning component of a robot, a chip, and a robot. Background Art

[0002] The photovoltaic panels in a photovoltaic power station are exposed to the outdoor environment for a long time, and are extremely likely to accumulate impurities such as dust and leaves, seriously affecting the power generation efficiency of the photovoltaic panels.

[0003] Some photovoltaic power stations use cleaning robots to clean the impurities on the photovoltaic panels. The cleaning robots are provided with cleaning components (such as a roller brush), and according to the measurement data of the ultrasonic sensors on the cleaning components, the relative position between the cleaning components and the photovoltaic panels is adjusted, so as to clean the photovoltaic panels by using the cleaning components.

[0004] When the cleaning component is not parallel to the photovoltaic panel, the ultrasonic sensors on the cleaning component are also not parallel to the photovoltaic panel. The sound waves emitted by the ultrasonic sensors are reflected through multiple paths, resulting in jumps in the measurement data of the ultrasonic sensors. According to the measurement data, the relative position between the cleaning component and the photovoltaic panel cannot be accurately adjusted, and it is possible to cause the cleaning component to damage the photovoltaic panel. Summary of the Invention

[0005] In view of the above problems, this application provides a method for controlling a cleaning component of a robot, a chip, and a robot, which can improve the control accuracy of the cleaning component and reduce the damage to the photovoltaic panel. The specific solutions are as follows: In a first aspect of this application, a method for controlling a cleaning component of a robot is provided. A lidar is provided on the robot, and ultrasonic sensors are provided on the cleaning component. The method for controlling the cleaning component of the robot includes: Adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensors and the measurement data of the lidar, so that the cleaning component is parallel to the photovoltaic panel; In the case where the cleaning component is parallel to the photovoltaic panel, adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensors, so that the cleaning component fits the photovoltaic panel.

[0006] In a possible implementation, adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensors and the measurement data of the lidar includes: In the case where the measurement data of the ultrasonic sensors jumps, comparing and verifying the measurement data of the ultrasonic sensors and the measurement data of the lidar bidirectionally, and adjusting the pose of the cleaning component so that the cleaning component is parallel to the photovoltaic panel.

[0007] In a possible implementation, the measurement data of the ultrasonic sensor and the measurement data of the lidar are compared and verified bidirectionally, and the pose of the cleaning component is adjusted, including: Calculate the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and output the first state vector according to the first angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; Calculate the second angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar, and output the first measurement vector according to the second angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; Use the Kalman filter algorithm to predict the first state vector at the next moment based on the first state vector and the first measurement vector; Adjust the pose of the cleaning component according to the first state vector at the next moment, so that the cleaning component is parallel to the photovoltaic panel.

[0008] In a possible implementation, N ultrasonic sensors are arranged on the cleaning component, N is a positive integer and N≥4, and calculating the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensors includes: Respectively obtain the measurement data of N ultrasonic sensors within a preset time window; Respectively calculate the average value of the measurement data of N ultrasonic sensors within the preset time window; Calculate the first angle data of the inclination angle of the photovoltaic panel according to the average value of the measurement data of N ultrasonic sensors within the preset time window.

[0009] In a possible implementation, calculating the second angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar includes: Perform downsampling processing on the measurement data of the lidar to obtain target point cloud data; Perform ground segmentation and plane fitting on the target point cloud data to extract the point cloud data of the photovoltaic panel plane; Calculate the second angle data of the inclination angle of the photovoltaic panel according to the point cloud data of the photovoltaic panel plane.

[0010] In a possible implementation, adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor includes: When the measurement data of the ultrasonic sensor does not change abruptly, adjust the pose of the cleaning component according to the distance between the cleaning component and the photovoltaic panel detected by the ultrasonic sensor, so that the cleaning component fits the photovoltaic panel.

[0011] In a possible implementation, adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor includes: When the measurement data of the ultrasonic sensor does not change abruptly, compare and verify the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally, and adjust the pose of the cleaning component to make the cleaning component fit the photovoltaic panel.

[0012] In a possible implementation, comparing and verifying the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally, and adjusting the pose of the cleaning component includes: Calculate the third angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and output a second state vector according to the third angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component and the photovoltaic panel detected by the ultrasonic sensor; Calculate the fourth angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar, and output a second measurement vector according to the fourth angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component and the photovoltaic panel detected by the lidar; Use the Kalman filtering algorithm to predict the second state vector at the next moment based on the second state vector and the second measurement vector; According to the second state vector at the next moment, adjust the pose of the cleaning component to make the cleaning component fit the photovoltaic panel.

[0013] A second aspect of the present application provides a chip, which is arranged on a robot. The robot is also provided with a lidar and a cleaning component, and an ultrasonic sensor is arranged on the cleaning component; The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to realize adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the measurement data of the lidar, so that the cleaning component is parallel to the photovoltaic panel; when the cleaning component is parallel to the photovoltaic panel, adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor to make the cleaning component fit the photovoltaic panel.

[0014] A third aspect of the present application provides a robot, including: a robot body, a robotic arm, and a cleaning component at the end of the robotic arm; The robot body includes a lidar and the chip of the second aspect; An ultrasonic sensor is arranged on the cleaning component.

[0015] With the above technical solution, a method for controlling a cleaning component of a robot provided by this application sets a lidar on the robot and an ultrasonic sensor on the cleaning component. By using the measurement data of the ultrasonic sensor and the measurement data of the lidar, high-precision positioning of the photovoltaic panel is achieved. Then, by adjusting the pose of the cleaning component, the cleaning component is made parallel to the photovoltaic panel. At this time, there is no jump in the measurement data of the ultrasonic sensor. By using the measurement data of the ultrasonic sensor, the pose of the cleaning component can be accurately adjusted to make the cleaning component fit the photovoltaic panel, avoiding damage to the photovoltaic panel. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and components are not necessarily drawn to scale.

[0017] Figure 1 FIG. [ID] is a schematic structural diagram of a robot provided by an embodiment of this application; Figure 2 FIG. [ID] is a schematic flowchart of a method for controlling a cleaning component of a robot provided by an embodiment of this application; Figure 3 FIG. [ID] is a schematic flowchart of another method for controlling a cleaning component of a robot provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following describes the embodiments of this application in combination with the drawings in the embodiments of this application. The terms used in the embodiments of this application are only for explaining the specific embodiments of this application and are not intended to limit this application.

[0019] The following describes the embodiments of this application in combination with the drawings. Those skilled in the art will know that with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0020] The terms "first", "second", etc. in the specification, claims and above drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of this application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these processes, methods, products or devices.

[0021] SeeFigure 1 , Figure 1 shows a schematic structural diagram of a robot. The robot includes: a robot body 101, a robotic arm 102, and a cleaning component 103 at the end of the robotic arm 102.

[0022] Among them, the cleaning component 103 can be a rotary brush, a flat brush, a pneumatic cleaning device, a dust suction device, etc., and the present application does not make specific limitations.

[0023] The robot body 101 includes: a lidar 104 and a chip ( Figure 1 not shown).

[0024] In a possible implementation, the lidar 104 is disposed on one side of the robot body and set at a preset upward angle so that the lidar 104 can face the photovoltaic panel directly.

[0025] The chip is configured to control the movement of the robotic arm 102. Since the cleaning component 103 is disposed at the end of the robotic arm 102, when the chip controls the movement of the robotic arm 102, the robotic arm 102 drives the cleaning component 103 to move.

[0026] An ultrasonic sensor is disposed on the cleaning component 103 ( Figure 1 not shown).

[0027] In a possible implementation, N ultrasonic sensors are disposed on the cleaning component 103, where N is a positive integer and N≥4. The N ultrasonic sensors are disposed at the end of the cleaning component 103 and are parallel to the cleaning component 103.

[0028] By disposing a lidar on the robot and an ultrasonic sensor on the cleaning component, and using the measurement data of the ultrasonic sensor and the measurement data of the lidar, high-precision positioning of the photovoltaic panel is achieved. Thus, by coarsely adjusting the pose of the cleaning component, the cleaning component is made parallel to the photovoltaic panel. At this time, there is no jump in the measurement data of the ultrasonic sensor, and the pose of the cleaning component can be accurately adjusted using the measurement data of the ultrasonic sensor, so that the cleaning component fits the photovoltaic panel, which can not only avoid damaging the photovoltaic panel but also improve the cleaning efficiency of the photovoltaic panel.

[0029] The embodiment of the present application provides a method for controlling a cleaning component of a robot. The method for controlling the cleaning component of the robot in the embodiment of the present application will be introduced in detail below with reference to the accompanying drawings.

[0030] Referring to Figure 2 , Figure 2 is a schematic flow diagram of a method for controlling a cleaning component of a robot provided by an embodiment of the present application. As Figure 2 shown, the method for controlling a cleaning component of a robot provided by an embodiment of the present application may include steps 201 to 202, and these steps will be described in detail below.

[0031] 201: Adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the lidar, so that the cleaning component is parallel to the photovoltaic panel. Ultrasonic technology is a technology that uses the reflection and propagation characteristics of ultrasonic waves to detect the internal structure and surface contour of an object, and can quickly and nondestructively obtain two-dimensional and three-dimensional information of the object. When the cleaning component is not parallel to the photovoltaic panel, the ultrasonic sensor on the cleaning component is also not parallel to the photovoltaic panel. The sound waves emitted by the ultrasonic sensor are reflected through multiple paths, resulting in jumps in the measurement data of the ultrasonic sensor. For example, within a preset time window, the measurement data of a certain ultrasonic sensor is (20, 23, 34, 10, 21, 22, 22.5), then 34 and 10 may be the results received after the sound waves are reflected through multiple paths, which are outliers with large deviations from the true values.

[0032] Lidar technology is a technology that uses lasers to measure distances and the shape contours of objects, and can quickly and accurately obtain three-dimensional information of objects. In this embodiment, by combining the measurement data of the ultrasonic sensor and the lidar, the inclination angle of the photovoltaic panel can be accurately obtained, and thus the pose of the cleaning component can be roughly adjusted according to the inclination angle of the photovoltaic panel, so that the cleaning component is parallel to the photovoltaic panel.

[0033] 202: When the cleaning component is parallel to the photovoltaic panel, adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor, so that the cleaning component fits the photovoltaic panel.

[0034] When the cleaning component is parallel to the photovoltaic panel, in order to improve the cleaning effect, it is necessary to make the cleaning component fit the photovoltaic panel. Since there is no jump in the measurement data of the ultrasonic sensor when the cleaning component is parallel to the photovoltaic panel, the inclination angle of the photovoltaic panel and the distance between the cleaning component and the photovoltaic panel can be accurately calculated using the measurement data of the ultrasonic sensor. Then, according to the inclination angle of the photovoltaic panel and the distance between the cleaning component and the photovoltaic panel, the pose of the cleaning component can be finely adjusted accurately, so that the cleaning component fits the photovoltaic panel, which can not only avoid damaging the photovoltaic panel but also improve the cleaning efficiency of the photovoltaic panel.

[0035] In this embodiment, when the cleaning component is not parallel to the photovoltaic panel, the pose of the cleaning component is adjusted according to the measurement data of the ultrasonic sensor and the lidar, which can achieve a large-range adjustment of the cleaning component and overcome the disadvantage in the related technology that the tilt angle adjustment range of the electric cleaning component is limited.

[0036] In a possible implementation, it is determined whether the cleaning component is parallel to the photovoltaic panel according to whether the measurement data of the ultrasonic sensor jumps. Among them, when the measurement data of the ultrasonic sensor jumps, the cleaning component is not parallel to the photovoltaic panel; when the measurement data of the ultrasonic sensor does not jump, the cleaning component is parallel to the photovoltaic panel. A possible implementation method for determining whether the measurement data of the ultrasonic sensor jumps is as follows: Obtain the measurement data of the ultrasonic sensor within a preset time window. If the difference between the measurement data of the ultrasonic sensor at adjacent sampling times is greater than the threshold, or the difference between the maximum value and the minimum value in the measurement data of the ultrasonic sensor within the preset time window is greater than the threshold, it is determined that the measurement data of the ultrasonic sensor jumps.

[0037] When the measurement data of the ultrasonic sensor jumps, that is, when the cleaning component is not parallel to the photovoltaic panel, the measurement data of the ultrasonic sensor and the measurement data of the lidar are compared and verified bidirectionally, and the pose of the cleaning component is adjusted. For example: The measurement data of the ultrasonic sensor is used as the state value of the cleaning component, and the measurement data of the lidar is used as the observation value of the cleaning component. When the state value and the observation value of the cleaning component are inconsistent, it indicates that the measurement data of the ultrasonic sensor is inaccurate and the cleaning component is not parallel to the photovoltaic panel. Using the Kalman filter algorithm, the adaptive Kalman filter algorithm, the extended Kalman filter algorithm, etc., based on the current state value and observation value of the cleaning component, predict the state value of the cleaning component at the next moment, so as to adjust the pose of the cleaning component according to the state value of the cleaning component at the next moment until the cleaning component is parallel to the photovoltaic panel. At this time, the state value and the observation value of the cleaning component are consistent. During the process of adjusting the pose of the cleaning component, the measurement data of the ultrasonic sensor and the measurement data of the lidar are compared and verified bidirectionally to accurately adjust the pose of the cleaning component until the cleaning component is parallel to the photovoltaic panel.

[0038] In a possible implementation, in the above embodiment, comparing and verifying the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally and adjusting the pose of the cleaning component includes the following steps 2021-2024: 2021: Calculate the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and output the first state vector according to the first angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; Exemplarily, N ultrasonic sensors are arranged on the cleaning component, where N is a positive integer and N≥4.

[0039] Taking the example of arranging 4 ultrasonic sensors on the cleaning component, the 4 ultrasonic sensors form a rectangle, and the measurement data of every two ultrasonic sensors can determine a straight line on the photovoltaic panel. According to the principle of trigonometric functions, the first angle data of the inclination angle of the photovoltaic panel can be calculated.

[0040] When the cleaning component is not parallel to the photovoltaic panel, the measurement data of the ultrasonic sensor jumps. To calculate the first angle data of the photovoltaic panel inclination as accurately as possible, the first angle data of the photovoltaic panel inclination is calculated based on the average value of the measurement data of N ultrasonic sensors within the predicted time window.

[0041] Output the first state vector according to the first angle data of the photovoltaic panel inclination and the pose of the cleaning component .

[0042] Among them, P, V and represent the pose of the cleaning component, P represents the position of the cleaning component, V represents the speed of the cleaning component, represents the acceleration of the cleaning component, represents the first angle data of the photovoltaic panel inclination.

[0043] 2022: Calculate the second angle data of the photovoltaic panel inclination according to the measurement data of the lidar, and output the first measurement vector according to the second angle data of the photovoltaic panel inclination and the pose of the cleaning component; The measurement data of the lidar is point cloud data. The point cloud data obtained by the lidar is downsampled to reduce the data volume to obtain the target point cloud data. Then, the target point cloud data is subjected to ground segmentation and plane fitting to extract the point cloud data of the photovoltaic panel plane. A plane equation is constructed based on the point cloud data of the photovoltaic panel plane, and the normal vector of the photovoltaic panel plane is calculated. Thus, the second angle data of the photovoltaic panel inclination is calculated according to the plane equation and the normal vector of the photovoltaic panel plane.

[0044] Output the first measurement vector according to the second angle data of the photovoltaic panel inclination and the pose of the cleaning component .

[0045] Among them, represents the first angle data of the photovoltaic panel inclination.

[0046] 2023: Use the Kalman filter algorithm to predict the first state vector at the next moment based on the first state vector and the first measurement vector; According to the first state vector at time t-1 to predict the first state vector at time t , that is, the first state vector , and the calculation formula is: .

[0047] Among them, A represents the coefficient of the first state vector changing with time, B represents the control input (such as speed V, acceleration The influence coefficients of (such as) on the first state vector, A and B are set according to the moving state of the cleaning component. For example, by collecting multiple groups of first state vectors at different times, these two influence coefficients are approximately fitted.

[0048] According to the error covariance matrix at time t - 1 to predict the error covariance matrix at the current time t , the error covariance is used to represent the uncertainty of the state vector, and the calculation formula is: , where Q represents the process noise covariance matrix, which is used to describe the characteristics of the uncertainty of the Kalman filter algorithm model, is the transpose matrix of A.

[0049] Calculate the Kalman gain : The Kalman gain is used to fuse the first state vector with the first measurement vector to obtain a more accurate estimated result of the first state vector. The calculation formula is: , where H is used to describe the relationship between the first measurement vector and the first state vector, and R is used to describe the statistical characteristics of the first measurement vector noise, is the transpose matrix of H.

[0050] Then, according to the Kalman gain update the state vector: The updated state vector at time t , and the calculation formula is: ; Calculate the updated error covariance , and the calculation formula is: , where I represents the identity matrix.

[0051] Predicting the first state vector at time t + 1 from time t is the same as predicting the first state vector at time t above. Predict and iteratively update according to the above steps until there is no first measurement vector input to the Kalman filter algorithm, that is, the cleaning component is parallel to the photovoltaic panel.

[0052] 2024: Adjust the pose of the cleaning component according to the first state vector at the next moment to make the cleaning component parallel to the photovoltaic panel.

[0053] That is, adjust the pose of the cleaning component according to the pose of the cleaning component in the first state vector at the next moment to make the cleaning component parallel to the photovoltaic panel.

[0054] Steps 2021 - 2024 are executed cyclically. That is, when the first state vector of the cleaning component is inconsistent with the first measurement vector, the first angle data and the second angle data of the inclination angle of the photovoltaic panel are inconsistent, the measurement data of the ultrasonic sensor has a jump, and the cleaning component is not parallel to the photovoltaic panel. By using the Kalman filtering algorithm, the first state vector at the next moment is predicted based on the first state vector and the first measurement vector. According to the first state vector at the next moment, the pose of the cleaning component is adjusted until the first state vector of the cleaning component is consistent with the first measurement vector, making the cleaning component parallel to the photovoltaic panel. The whole process is verified by two-way comparison of the measurement data of the ultrasonic sensor and the measurement data of the lidar, improving the control accuracy of the cleaning component.

[0055] When the cleaning component is parallel to the photovoltaic panel, the measurement data of the ultrasonic sensor does not have a jump. Using the measurement data of the ultrasonic sensor can accurately represent the distance between the cleaning component and the photovoltaic panel. According to the distance between the cleaning component and the photovoltaic panel, the pose of the cleaning component can be accurately adjusted to make the cleaning component fit the photovoltaic panel.

[0056] In a possible implementation, when the cleaning component is parallel to the photovoltaic panel, the measurement data of the ultrasonic sensor does not have a jump. The measurement data of the ultrasonic sensor and the measurement data of the lidar can also be verified by two-way comparison, and the pose of the cleaning component is adjusted to make the cleaning component fit the photovoltaic panel.

[0057] Please refer to Figure 3 the schematic flow chart of another cleaning component control method of the robot shown. A cleaning component control method of a robot provided by an embodiment of the present application may include steps 301 - 310: 301: Obtain the measurement data of the ultrasonic sensor; 302: Determine whether there is a jump in the measurement data of the ultrasonic sensor; If there is a jump in the measurement data of the ultrasonic sensor, execute 303: Calculate the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and output the first state vector according to the first angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; 304: Calculate the second angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar, and output the first measurement vector according to the second angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; 305: Use the Kalman filtering algorithm to predict the first state vector at the next moment based on the first state vector and the first measurement vector; 306: Adjust the pose of the cleaning component according to the first state vector at the next moment to make the cleaning component parallel to the photovoltaic panel; If there is no jump in the measurement data of the ultrasonic sensor, execute 307: Calculate the third angle data of the inclination angle of the photovoltaic panel based on the measurement data of the ultrasonic sensor, and output the second state vector according to the third angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component detected by the ultrasonic sensor and the photovoltaic panel; Second state vector 。

[0058] Among them, represents the third angle data of the inclination angle of the photovoltaic panel, represents the distance between the cleaning component detected by the ultrasonic sensor and the photovoltaic panel, and can be represented by the measurement average value of N ultrasonic sensors.

[0059] 308: Calculate the fourth angle data of the inclination angle of the photovoltaic panel based on the measurement data of the lidar, and output the second measurement vector according to the fourth angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component detected by the lidar and the photovoltaic panel; Second measurement vector 。

[0060] Among them, represents the third angle data of the inclination angle of the photovoltaic panel, represents the distance between the cleaning component detected by the lidar and the photovoltaic panel.

[0061] 309: Use the Kalman filter algorithm to predict the second state vector at the next moment based on the second state vector and the second measurement vector; Using the Kalman filter algorithm to predict the second state vector at the next moment based on the second state vector and the second measurement vector is the same as the principle of step 2023 in the above embodiment, and will not be elaborated here.

[0062] 310: Adjust the pose of the cleaning component according to the second state vector at the next moment to make the cleaning component fit the photovoltaic panel.

[0063] In the case where the cleaning component is parallel to the photovoltaic panel, use the Kalman filter algorithm to locally adjust the cleaning component to keep it parallel to the photovoltaic panel, which can be regarded as the prediction and iterative update of local variables in the above Kalman filter algorithm.

[0064] A cleaning component control method for a robot disclosed in this embodiment, in the case where the cleaning component is parallel to the photovoltaic panel, by comparing and verifying the measurement data of the ultrasonic sensor and the lidar bidirectionally, adjusts the pose of the cleaning component, improves the adjustment accuracy of the cleaning component, and makes the cleaning component fit the photovoltaic panel accurately.

[0065] In this embodiment, the pose of the cleaning component is adjusted through an algorithm, without the need for a complex mechanical structure. The adjustment process is fast and can quickly respond to changes in the inclination angles of different photovoltaic panels, overcoming the disadvantages of complex pose adjustment structures and slow adjustment processes in related technologies.

[0066] An embodiment of the present application also provides a chip. The chip is arranged on a robot, and the robot is also provided with a lidar and a cleaning component. An ultrasonic sensor is arranged on the cleaning component; The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the measurement data of the lidar, so that the cleaning component is parallel to the photovoltaic panel; in the case where the cleaning component is parallel to the photovoltaic panel, adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor to make the cleaning component fit the photovoltaic panel.

[0067] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions run on an electronic device, the electronic device is enabled to implement any cleaning component control method of the robot provided by the embodiments of the present application.

[0068] An embodiment of the present application also provides a computer-readable storage medium. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device is enabled to implement any cleaning component control method of the robot provided by the embodiments of the present application.

[0069] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines.

[0070] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions accomplished by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits, or dedicated circuits. However, for this application, software program implementation is a better embodiment in more cases. Based on such understanding, the technical solution of this application, in essence or the part that makes contributions to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disc of a computer, and includes several instructions to enable a computer device (which can be a personal computer, training device, or network device, etc.) to execute the methods described in various embodiments of this application.

[0071] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0072] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, training device, or data center to another website, computer, training device, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store, or a data storage device such as a training device or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

Claims

1. A method for controlling a cleaning component of a robot, characterized in that, A lidar is provided on the robot, and an ultrasonic sensor is provided on the cleaning component. The method for controlling the cleaning component of the robot includes: Adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the measurement data of the lidar, so that the cleaning component is parallel to the photovoltaic panel; When the cleaning component is parallel to the photovoltaic panel, adjust the pose of the cleaning component according to the measurement data of the ultrasonic sensor, so that the cleaning component fits the photovoltaic panel.

2. The cleaning component control method of the robot according to claim 1, wherein, Adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the measurement data of the lidar includes: When the measurement data of the ultrasonic sensor jumps, compare and verify the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally, and adjust the pose of the cleaning component so that the cleaning component is parallel to the photovoltaic panel.

3. The method for controlling a cleaning component of a robot according to claim 2, wherein Comparing and verifying the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally and adjusting the pose of the cleaning component includes: Calculate the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and output a first state vector according to the first angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; Calculate the second angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar, and output a first measurement vector according to the second angle data of the inclination angle of the photovoltaic panel and the pose of the cleaning component; Use the Kalman filter algorithm to predict the first state vector at the next moment based on the first state vector and the first measurement vector; Adjust the pose of the cleaning component according to the first state vector at the next moment, so that the cleaning component is parallel to the photovoltaic panel.

4. The method for controlling the cleaning component of the robot according to claim 3, wherein N ultrasonic sensors are provided on the cleaning component, N is a positive integer and N≥4. Calculating the first angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor includes: Respectively obtain the measurement data of N ultrasonic sensors within a preset time window; Respectively calculate the average value of the measurement data of N ultrasonic sensors within the preset time window; Calculate the first angle data of the inclination angle of the photovoltaic panel according to the average value of the measurement data of N ultrasonic sensors within the preset time window.

5. The method for controlling a cleaning component of a robot according to claim 3, characterized in that, Calculating the second angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar includes: Perform downsampling processing on the measurement data of the lidar to obtain target point cloud data; Perform ground segmentation and plane fitting on the target point cloud data to extract the point cloud data of the photovoltaic panel plane; Calculate the second angle data of the inclination angle of the photovoltaic panel according to the point cloud data of the photovoltaic panel plane.

6. The cleaning component control method of the robot according to claim 1, characterized in that, Adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor includes: When the measurement data of the ultrasonic sensor does not jump, adjust the pose of the cleaning component according to the distance between the cleaning component and the photovoltaic panel detected by the ultrasonic sensor, so that the cleaning component fits the photovoltaic panel.

7. The method for controlling a cleaning component of a robot according to claim 1, wherein Adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor includes: When the measurement data of the ultrasonic sensor does not change abruptly, the measurement data of the ultrasonic sensor and the measurement data of the lidar are compared and verified bidirectionally, and the pose of the cleaning component is adjusted to make the cleaning component fit the photovoltaic panel.

8. The method for controlling a cleaning component of a robot according to claim 7, characterized in that, Comparing and verifying the measurement data of the ultrasonic sensor and the measurement data of the lidar bidirectionally and adjusting the pose of the cleaning component includes: Calculating third angle data of the inclination angle of the photovoltaic panel according to the measurement data of the ultrasonic sensor, and outputting a second state vector according to the third angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component and the photovoltaic panel detected by the ultrasonic sensor; Calculating fourth angle data of the inclination angle of the photovoltaic panel according to the measurement data of the lidar, and outputting a second measurement vector according to the fourth angle data of the inclination angle of the photovoltaic panel, the pose of the cleaning component, and the distance between the cleaning component and the photovoltaic panel detected by the lidar; Using the Kalman filter algorithm to predict the second state vector at the next moment based on the second state vector and the second measurement vector; According to the second state vector at the next moment, adjusting the pose of the cleaning component to make the cleaning component fit the photovoltaic panel.

9. A chip, characterized in that, The chip is arranged on the robot, the robot is also provided with a lidar and a cleaning component, and an ultrasonic sensor is arranged on the cleaning component; The chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to realize adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor and the measurement data of the lidar to make the cleaning component parallel to the photovoltaic panel; when the cleaning component is parallel to the photovoltaic panel, adjusting the pose of the cleaning component according to the measurement data of the ultrasonic sensor to make the cleaning component fit the photovoltaic panel.

10. A robot, characterized in that, Including: A robot body, a robotic arm, and a cleaning component at the end of the robotic arm; The robot body includes a lidar and the chip according to claim 9; An ultrasonic sensor is arranged on the cleaning component.

Images